Jonathan J. Deeks. Issues in the selection of a summary statistic for
meta-analysis of clinical trials with binary outcomes. Statistics in
Medicine. 2002;21(11):1575-1600. Abstract: "Meta-analysis of binary data
involves the computation of a weighted average of summary statistics
calculated for each trial. The selection of the appropriate summary statistic
is a subject of debate due to conflicts in the relative importance of
mathematical properties and the ability to intuitively interpret results. This
paper explores the process of identifying a summary statistic most likely to
be consistent across trials when there is variation in control group event
rates. Four summary statistics are considered: odds ratios (OR); risk
differences (RD) and risk ratios of beneficial (RR(B)); and harmful outcomes (RR(H)).
Each summary statistic corresponds to a different pattern of predicted
absolute benefit of treatment with variation in baseline risk, the greatest
difference in patterns of prediction being between RR(B) and RR(H). Selection
of a summary statistic solely based on identification of the best-fitting
model by comparing tests of heterogeneity is problematic, principally due to
low numbers of trials. It is proposed that choice of a summary statistic
should be guided by both empirical evidence and clinically informed debate as
to which model is likely to be closest to the expected pattern of treatment
benefit across baseline risks. Empirical investigations comparing the four
summary statistics on a sample of 551 systematic reviews provide evidence that
the RR and OR models are on average more consistent than RD, there being no
difference on average between RR and OR. From a second sample of 114
meta-analyses evidence indicates that for interventions aimed at preventing an
undesirable event, greatest absolute benefits are observed in trials with the
highest baseline event rates, corresponding to the model of constant RR(H).
The appropriate selection for a particular meta-analysis may depend on
understanding reasons for variation in control group event rates; in some
situations uncertainty about the choice of summary statistic will remain.
Copyright � 2002 John Wiley & Sons, Ltd." [Accessed December 18, 2009].
Available at:
http://dx.doi.org/10.1002/sim.1188.
Thomas B Newman. The power of stories over statistics. BMJ.
2003;327(7429):1424-1427. Excerpt: "Neonatal jaundice and infant safety on
aeroplanes provide two lessons on the power of narrative, rather than
statistical evidence, in determining practice." [Accessed December 10,
2009]. Available at: http://www.bmj.com.
Raj Bhopal. Seven mistakes and potential solutions in epidemiology,
including a call for a World Council of Epidemiology and Causality.
Emerging Themes in Epidemiology. 2009;6(1):6. Abstract: "All sciences make
mistakes, and epidemiology is no exception. I have chosen 7 illustrative
mistakes and derived 7 solutions to avoid them. The mistakes (Roman numerals
denoting solutions) are: 1. Failing to provide the context and definitions of
study populations. (I Describe the study population in detail.). 2.
Insufficient attention to evaluation of error. (II Don't pretend error does
not exist.). 3. Not demonstrating comparisons are like-for-like. (III Start
with detailed comparisons of groups.). 4. Either overstatement or
understatement of the case for causality. (IV Never say this design cannot
contribute to causality or imply causality is ensured by your design.). 5. Not
providing both absolute and relative summary measures. (V Give numbers, rates
and comparative measures, and adjust summary measures such as odds ratios
appropriately.). 6. In intervention studies not demonstrating general health
benefits. (VI Ensure general benefits (mortality/morbidity) before
recommending application of cause-specific findings.). 7. Failure to utilise
study data to benefit populations. (VII Establish a World Council on
Epidemiology to help infer causality from associations and apply the work
internationally.). Analysis of these and other common mistakes is needed to
benefit from the increasing discovery of associations that will be multiplying
as data mining, linkage, and large-scale scale epidemiology become
commonplace." [Accessed December 10, 2009]. Available at:
http://www.ete-online.com/content/6/1/6.
Nathaniel D. Mercaldo, Kit F. Lau, Xiao H. Zhou. Confidence intervals
for predictive values with an emphasis to case-control studies. Statistics
in Medicine. 2007;26(10):2170-2183. Abstract: "The accuracy of a
binary-scale diagnostic test can be represented by sensitivity (Se),
specificity (Sp) and positive and negative predictive values (PPV and NPV).
Although Se and Sp measure the intrinsic accuracy of a diagnostic test that
does not depend on the prevalence rate, they do not provide information on the
diagnostic accuracy of a particular patient. To obtain this information we
need to use PPV and NPV. Since PPV and NPV are functions of both the accuracy
of the test and the prevalence of the disease, constructing their confidence
intervals for a particular patient is not straightforward. In this paper, a
novel method for the estimation of PPV and NPV, as well as their confidence
intervals, is developed. For both predictive values, standard, adjusted and
their logit transformed-based confidence intervals are compared using coverage
probabilities and interval lengths in a simulation study. These methods are
then applied to two case-control studies: a diagnostic test assessing the
ability of the e4 allele of the apolipoprotein E gene (ApoE.e4) on
distinguishing patients with late-onset Alzheimer's disease (AD) and a
prognostic test assessing the predictive ability of a 70-gene signature on
breast cancer metastasis. Copyright � 2006 John Wiley & Sons, Ltd."
[Accessed December 10, 2009]. Available at:
http://dx.doi.org/10.1002/sim.2677.
Byron Wallace, Christopher Schmid, Joseph Lau, Thomas Trikalinos.
Meta-Analyst: software for meta-analysis of binary, continuous and diagnostic
data. BMC Medical Research Methodology. 2009;9(1):80. Abstract:
"BACKGROUND: Meta-analysis is increasingly used as a key source of evidence
synthesis to inform clinical practice. The theory and statistical foundations
of meta-analysis continually evolve, providing solutions to many new and
challenging problems. In practice, most meta-analyses are performed in general
statistical packages or dedicated meta-analysis programs. RESULTS: Herein, we
introduce Meta-Analyst, a novel, powerful, intuitive, and free meta-analysis
program for the meta-analysis of a variety of problems. Meta-Analyst is
implemented in C# atop of the Microsoft .NET framework, and features a
graphical user interface. The software performs several meta-analysis and
meta-regression models for binary and continuous outcomes, as well as analyses
for diagnostic and prognostic test studies in the frequentist and Bayesian
frameworks. Moreover, Meta-Analyst includes a flexible tool to edit and
customize generated meta-analysis graphs (e.g., forest plots) and provides
output in many formats (images, Adobe PDF, Microsoft Word-ready RTF). The
software architecture employed allows for rapid changes to be made to either
the Graphical User Interface (GUI) or to the analytic modules. We verified the
numerical precision of Meta-Analyst by comparing its output with that from
standard meta-analysis routines in Stata over a large database of 11,803
meta-analyses of binary outcome data, and 6,881 meta-analyses of continuous
outcome data from the Cochrane Library of Systematic Reviews. Results from
analyses of diagnostic and prognostic test studies have been verified in a
limited number of meta-analyses versus MetaDisc and MetaTest. Bayesian
statistical analyses use the OpenBUGS calculation engine (and are thus as
accurate as the standalone OpenBUGS software). CONCLUSION: We have developed
and validated a new program for conducting meta-analyses that combines the
advantages of existing software for this task." [Accessed December 9,
2009]. Available at:
http://www.biomedcentral.com/1471-2288/9/80.
Miguel Roig. Avoiding plagiarism, self-plagiarism, and other
questionable writing practices: A guide to ethical writing. Excerpt:
"In recognizing the importance of educating aspiring scientists in the
responsible conduct of research (RCR), the Office of Research Integrity (ORI),
began sponsoring in 2002 the creation of instructional resources to address
this pressing need. The present guide on avoiding plagiarism and other
inappropriate writing practices was created, in part, to meet this need. Its
purpose is to help students, as well as professionals, identify and prevent
such practices and to develop an awareness of ethical writing. This guide is
one of the many products stemming from ORI�s educational initiatives in the
RCR." [Accessed December 7, 2009]. Available at:
http://facpub.stjohns.edu/~roigm/plagiarism/Index.html.
PSCA International. Privacy needed for patients' data. Excerpt:
"Approximately one half of patients and the general public believe that
identifiable patient data should never be used for research without consent.
Whilst only 11 per cent of researchers believed this should never happen, 53
per cent of the general public and 46 per cent of patients thought it was
unacceptable without prior consent. But more than half of researchers thought
patient identifiable data should be used without patient consent if it had
first been reviewed by the Patient Information Advisory Group (PIAG). Only 30
per cent of both patients and the general public agreed." [Accessed
December 5, 2009]. Available at:
http://www.publicservice.co.uk/news_story.asp?id=11486.
Trisha Greenhalgh. Narrative based medicine: Narrative based medicine
in an evidence based world. BMJ. 1999;318(7179):323-325. Excerpt: "In a
widely quoted riposte to critics who accused them of naive empiricism, Sackett
and colleagues claimed that "the practice of evidence based medicine means
integrating individual clinical expertise with the best available external
clinical evidence .... By individual clinical expertise we mean the
proficiency and judgment that individual clinicians acquire through clinical
experience and clinical practice." Sackett and colleagues were anxious to
acknowledge that there is an art to medicine as well as an objective empirical
science but they did not attempt to define or categorise the elusive quality
of clinical competence. This article explores the dissonance between the
"science" of objective measurement and the "art" of clinical proficiency and
judgment, and attempts to integrate these different perspectives on clinical
method." [Accessed December 5, 2009]. Available at:
http://www.bmj.com/cgi/content/full/318/7179/323.
Vera Kalitzkus, Peter F. Matthiessen. Narrative-Based Medicine:
Potential, Pitfalls, and Practice. The Permanente Journal. 13(1):80-86.
Excerpt: "Narratives have always been a vital part of medicine. Stories about
patients, the experience of caring for them, and their recovery from illness
have always been shared�among physicians as well as among patients and their
relatives. With the evolution of �modern� medicine, narratives were
increasingly neglected in favor of �facts and findings,� which were regarded
as more scientific and objective. Now, in recent years medical narrative is
changing�from the stories about patients and their illnesses, patient
narratives and the unfolding and interwoven story between health care
professionals and patients are both gaining momentum, leading to the creation
or defining of narrative-based medicine (NBM). The term was coined
deliberately to mark its distinction from evidence-based medicine (EBM); in
fact, NBM was propagated to counteract the shortcomings of EBM.1,2 But what is
NBM? Is it a specific therapeutic tool, a special form of physician-patient
communication, a qualitative research tool, or does it simply signify a
particular attitude towards patients and doctoring? It can be all of the above
with different forms or genres of narrative or practical approach called for
depending on the field of application. In this article we will give a
systematic overview of NBM: a short historic background; the various narrative
genres; and an analysis of how the genres can be effectively applied in
theory, research, and practice in the medical field, with a focus on
possibilities and limitations of a narrative approach. " [Accessed
December 5, 2009]. Available at:
http://xnet.kp.org/permanentejournal/winter09/narrativemedicine.html.
David C. Howell. Resampling Statistics: Randomization and the Bootstrap.
Excerpt: "This set of pages is intended to serve two purposes. On the one
hand, it was written to accompany a set of Windows� programs that I have
written. The main program is named Resampling.exe, and is available on disk
and can be downloaded from www.uvm.edu/~dhowell/StatPages/Resampling/ResamplingPackage
.zip. The second purpose of these pages is to elaborate on resampling
techniques and the theory behind them. " [Accessed December 5, 2009].
Available at:
http://www.uvm.edu/~dhowell/StatPages/Resampling/Resampling.html.
Julian L. Simon. Resampling: The New Statistics. Excerpt: "This
text grew out of chapters in the 1969 edition of Basic Research Methods in
Social Science by the same author, and contains the first published example of
what was later called the bootstrap. Simon is best known for his research in
demography, population and the economics of natural resources, and gained fame
when the noted biologist Paul Ehrlich selected five commodities and bet Simon
that scarcity would drive their prices up over the period of the bet (in fact,
their prices all dropped). Resampling: The New Statistics contains a number of
examples in Resampling Stats, a computer program originated by Simon, but can
be read on its own without the program." [Accessed December 5, 2009].
Available at:
http://www.resample.com/content/text/index.shtml.
November
Mei-Wei Chang, Roger Brown, Susan Nitzke. Participant recruitment and
retention in a pilot program to prevent weight gain in low-income overweight
and obese mothers. BMC Public Health. 2009;9(1):424. Abstract:
Background Recruitment and retention are key functions for programs promoting
nutrition and other lifestyle behavioral changes in low-income populations.
This paper describes strategies for recruitment and retention and presents
predictors of early (two-month post intervention) and late (eight-month post
intervention) dropout (non retention) and overall retention among young,
low-income overweight and obese mothers participating in a community-based
randomized pilot trial called Mothers In Motion. Methods Low-income overweight
and obese African American and white mothers ages 18 to 34 were recruited from
the Special Supplemental Nutrition Program for Women, Infants, and Children in
southern Michigan. Participants (n = 129) were randomly assigned to an
intervention (n = 64) or control (n = 65) group according to a stratification
procedure to equalize representation in two racial groups (African American
and white) and three body mass index categories (25.0-29.9 kg/m2, 30.0-34.9
kg/m2, and 35.0-39.9 kg/m2). The 10-week theory-based culturally sensitive
intervention focused on healthy eating, physical activity, and stress
management messages that were delivered via an interactive DVD and reinforced
by five peer-support group teleconferences. Forward stepwise multiple logistic
regression was performed to examine whether dietary fat, fruit and vegetable
intake behaviors, physical activity, perceived stress, positive and negative
affect, depression, and race predicted dropout as data were collected two-
month and eight-month after the active intervention phase. Results Trained
personnel were successful in recruiting subjects. Increased level of
depression was a predictor of early dropout (odds ratio = 1.04; 95% CI = 1.00,
1.08; p = 0.03). Greater stress predicted late dropout (odds ratio = 0.20; 95%
CI = 0.00, 0.37; p = 0.01). Dietary fat, fruit, and vegetable intake
behaviors, physical activity, positive and negative affect, and race were not
associated with either early or late dropout. Less negative affect was a
marginal predictor of participant retention (odds ratio = 0.57; 95% CI = 0.31,
1.03; p = 0.06). CONCLUSIONS:Dropout rates in this study were higher for
participants who reported higher levels of depression and stress. Trial
registration: Current Controlled Trials NCT00944060 [Accessed November 30,
2009]. Available at:
http://www.biomedcentral.com/1471-2458/9/424.
Cora Craig, Christine Cameron, Joe Griffiths, et al. Non-response bias
in physical activity trend estimates. BMC Public Health. 2009;9(1):425.
Abstract: BACKGROUND: Increases in reported leisure time physical activity
(PA) and obesity have been observed in several countries. One hypothesis for
these apparently contradictory trends is differential bias in estimates over
time. The purpose of this short report is to examine the potential impact of
changes in response rates over time on the prevalence of adequate PA in
Canadian adults. METHODS:Participants were recruited in representative
national telephone surveys of PA from 1995-2007. Differences in PA prevalence
estimates between participants and those hard to reach were assessed using
Student's t tests adjusted for multiple comparisons. RESULTS:The number of
telephone calls required to reach and speak with someone in the household
increased over time, as did the percentage of selected participants who
initially refused during the first interview attempt. A higher prevalence of
adequate PA was observed with 5-9 attempts to reach anyone in the household in
1999-2002, but this was not significant after adjustment for multiple
comparisons. CONCLUSIONS:No significant impact on PA trend estimates was
observed due to differential non response rates. It is important for health
policy makers to understand potential biases and how these may affect secular
trends in all aspects of the energy balance equation. [Accessed November
29, 2009]. Available at:
http://www.biomedcentral.com/1471-2458/9/425.
Tracey Sach, David Whynes. Men and women: beliefs about cancer and
about screening. BMC Public Health. 2009;9(1):431. Abstract:
BACKGROUND:Cancer screening programmes in England are publicly-funded.
Professionals' beliefs in the public health benefits of screening can conflict
with individuals' entitlements to exercise informed judgement over whether or
not to participate. The recognition of the importance of individual autonomy
in decision making requires greater understanding of the knowledge, attitudes
and beliefs upon which people's screening choices are founded. Until recently,
the technology available required that cancer screening be confined to women.
This study aimed to discover whether male and female perceptions of cancer and
of screening differ.METHODS:Data on the public's cancer beliefs were collected
by means of a postal survey (anonymous questionnaire). Two general practices
based in Nottingham and in Mansfield, in east-central England, sent
questionnaires to registered patients aged 30 to 70 years. 1,808 completed
questionnaires were returned for analysis, 56.5 per cent from women.
RESULTS:Women were less likely to underestimate overall cancer incidence,
although each sex was more likely to cite a sex-specific cancer as being
amongst the most common cancer site. In terms of risk factors, men were most
uncertain about the role of stress and sexually-transmitted diseases, whereas
women were more likely to rate excessive alcohol and family history as major
risk factors. The majority of respondents believed the public health care
system should provide cancer screening, but significantly more women than men
reported having benefiting from the nationally-provided screening services.
Those who were older, in better health or had longer periods of formal
education were less worried about cancer than those who had illness
experiences, lower incomes, or who were smokers. Actual or potential
participation in bowel screening was higher amongst those who believed bowel
cancer to be common and amongst men, despite women having more substantial
worries about cancer than men. CONCLUSIONS:Our results suggest that men's and
women's differential knowledge of cancer correlates with women's closer
involvement with screening. Even so, men were neither less positive about
screening nor less likely to express a willingness to participate in relevant
screening in the future. It is important to understand gender-related
differences in knowledge and perceptions of cancer, if health promotion
resources are to be allocated efficiently. [Accessed November 30, 2009].
Available at:
http://www.biomedcentral.com/1471-2458/9/431.
Kerrie Sanders, Amanda Stuart, Elizabeth Merriman, et al. Trials and
tribulations of recruiting 2,000 older women onto a clinical trial
investigating falls and fractures: Vital D study. BMC Medical Research
Methodology. 2009;9(1):78. Abstract: BACKGROUND: Randomised,
placebo-controlled trials are needed to provide evidence demonstrating safe,
effective interventions that reduce falls and fractures in the elderly. The
quality of a clinical trial is dependent on successful recruitment of the
target participant group. This paper documents the successes and failures of
recruiting over 2,000 women aged at least 70 years and at higher risk of falls
or fractures onto a placebo-controlled trial of six years duration. The
characteristics of study participants at baseline are also described for this
study.METHODS:The Vital D Study recruited older women identified at high risk
of fracture through the use of an eligibility algorithm, adapted from
identified risk factors for hip fracture. Participants were randomised to
orally receive either 500,000 IU vitamin D3 (cholecalciferol) or placebo every
autumn for three to five consecutive years. A variety of recruitment
strategies were employed to attract potential participants. RESULTS:Of the
2,317 participants randomised onto the study, 74% (n= 1716/ 2317) were
consented onto the study in the last five months of recruiting. This was
largely due to the success of a targeted mail-out. Prior to this only 541
women were consented in the 18 months of recruiting. A total of 70% of all
participants were recruited as a result of targeted mail-out. The response
rate from the letters increased from 2 to 7% following revision of the
material by a public relations company. Participant demographic or risk factor
profile did not differ between those recruited by targeted mail-outs compared
with other methods.CONCLUSIONS:The most successful recruitment strategy was
the targeted mail-out and the response rate was no higher in the local region
where the study had extensive exposure through other recruiting strategies.
The strategies that were labour-intensive and did not result in successful
recruitment include the activities directed towards the GP medical centres.
Comprehensive recruitment programs employ overlapping strategies
simultaneously with ongoing assessment of recruitment rates. In our
experience, and others direct mail-outs work best although rights to privacy
must be respected. Trial registration: ISRCTN83409867 and ACTR12605000658617.
[Accessed November 30, 2009]. Available at:
http://www.biomedcentral.com/1471-2288/9/78.
Fujian Song, Sheetal Parekh-Bhurke, Lee Hooper, et al. Extent of
publication bias in different categories of research cohorts: a meta-analysis
of empirical studies. BMC Medical Research Methodology. 2009;9(1):79.Abstract:
BACKGROUND:The validity of research synthesis is threatened if published
studies comprise a biased selection of all studies that have been conducted.
We conducted a meta-analysis to ascertain the strength and consistency of the
association between study results and formal publication. METHODS:The Cochrane
Methodology Register Database, MEDLINE and other electronic bibliographic
databases were searched (to May 2009) to identify empirical studies that
tracked a cohort of studies and reported the odds of formal publication by
study results. Reference lists of retrieved articles were also examined for
relevant studies. Odds ratios were used to measure the association between
formal publication and significant or positive results. Included studies were
separated into subgroups according to starting time of follow-up, and results
from individual cohort studies within the subgroups were quantitatively
pooled. RESULTS:We identified 12 cohort studies that followed up research from
inception, four that included trials submitted to a regulatory authority, 28
that assessed the fate of studies presented as conference abstracts, and four
cohort studies that followed manuscripts submitted to journals. The pooled
odds ratio of publication of studies with positive results, compared to those
without positive results (publication bias) was 2.78 (95% CI: 2.10 to 3.69) in
cohorts that followed from inception, 5.00 (95% CI: 2.01 to 12.45) in trials
submitted to regulatory authority, 1.70 (95% CI: 1.44 to 2.02) in abstract
cohorts, and 1.06 (95% CI: 0.80 to 1.39) in cohorts of manuscripts.
CONCLUSIONS:Dissemination of research findings is likely to be a biased
process. Publication bias appears to occur early, mainly before the
presentation of findings at conferences or submission of manuscripts to
journals. [Accessed November 29, 2009]. Available at:
http://www.biomedcentral.com/1471-2288/9/79.
Jon Cohen. Mission Improbable: A Concise and Precise Definition of
P-Value. ScienceNOW Daily News, October 30, 2009. Excerpt: Victor De
Gruttola, the chair of biostatistics at the Harvard School of Public Health,
is passionate about his p-values. That's why he was apoplectic last month when
an esteemed colleague and prominent AIDS vaccine researcher spoke with him
about the widely publicized results of the largest ever AIDS vaccine trial.
"The probability that this vaccine didn't work was only 4%," said his
colleague, whom we will call Thor to spare from further embarrassment.
[Accessed November 18, 2009]. Available at:
http://sciencenow.sciencemag.org/cgi/content/full/2009/1030/1
Wynn L, Paul H. Mason, and Kristina Everett. Social Sciences Ethics
Training - Macquarie University. Excerpt: Welcome to Macquarie
University's Online Ethics Training Module! This free educational resource
examines the particular ethical issues raised by social science and humanities
research. The training module is divided into 6 basic parts. You can start and
stop reading at any point in the module, and you can close it and return to it
later. After you have reviewed the entire module, there is a quiz that tests
your comprehension of the material. [Accessed November 17, 2009].
Available at:
http://www.mq.edu.au/ethics_training/
Carley S, Dosman S, Jones SR, Harrison M. Simple nomograms to calculate
sample size in diagnostic studies. Emerg Med J. 2005;22(3):180-181.
Abstract: Objectives: To produce an easily understood and accessible tool
for use by researchers in diagnostic studies. Diagnostic studies should have
sample size calculations performed, but in practice, they are performed
infrequently. This may be due to a reluctance on the part of researchers to
use mathematical formulae. Methods: Using a spreadsheet, we derived nomograms
for calculating the number of patients required to determine the precision of
a test�s sensitivity or specificity. Results: The nomograms could be easily
used to determine the sensitivity and specificity of a test. Conclusions: In
addition to being easy to use, the nomogram allows deduction of a missing
parameter (number of patients, confidence intervals, prevalence, or
sensitivity/specificity) if the other three are known. The nomogram can also
be used retrospectively by the reader of published research as a rough
estimating tool for sample size calculations. [Accessed November 16,
2009]. Available at:
http://emj.bmj.com/cgi/content/abstract/22/3/180
Baron J. R site search. Excerpt: This search will allow you to
search the contents of the R functions, package vignettes, task views, and
R-help mail archives. [Accessed November 13, 2009]. Available at:
http://search.r-project.org/nmz.html
Pearl DK. Consortium for the Advancement of Undergraduate Statistics
Education (CAUSE). Excerpt: Arising from a strategic initiative of the
American Statistical Association, CAUSE is a national organization whose
mission is to support and advance undergraduate statistics education, in four
target areas: resources, professional development, outreach, and research. The
overarching goals in each area are: * Resources: Collect, review, develop, and
disseminate resources for members of the undergraduate statistics education
community. * Professional Development: Coordinate, develop, and disseminate
opportunities, programs, and workshops for teachers and others involved in
statistics education projects and initiatives, present and future. * Outreach:
Establish and promote communication and collaborations among statistics
educators, as well as with other professional organizations and disciplines
that are concerned with undergraduate statistics education. * Research:
Establish the area of statistics education research as a recognized discipline
with a visible presence. Prepare and connect researchers from all disciplines
that conduct research in statistics education. Our primary vehicle for
communication is CAUSEweb.org, which is supported by a grant from the National
Science Foundation. [Accessed November 11, 2009]. Available at:
http://www.causeweb.org/
Hamza T, Arends L, van Houwelingen H, Stijnen T. Multivariate random
effects meta-analysis of diagnostic tests with multiple thresholds. BMC
Medical Research Methodology. 2009;9(1):73. Abstract: Bivariate random
effects meta-analysis of diagnostic tests is becoming a well established
approach when studies present one two-by-two table or one pair of sensitivity
and specificity. When studies present multiple thresholds for test positivity,
usually meta-analysts reduce the data to a two-by-two table or take one
threshold value at a time and apply the well developed meta-analytic
approaches. However, this approach does not fully exploit the data. In this
paper we generalize the bivariate random effects approach to the situation
where test results are presented with k thresholds for test positivity,
resulting in a 2 by (k+1) table per study. The model can be fitted with
standard likelihood procedures in statistical packages such as SAS (Proc
NLMIXED). We follow a multivariate random effects approach; i.e., we assume
that each study estimates a study specific ROC curve that can be viewed as
randomly sampled from the population of all ROC curves of such studies. In
contrast to the bivariate case, where nothing can be said about the shape of
study specific ROC curves without additional untestable assumptions, the
multivariate model can be used to describe study specific ROC curves. The
models are easily extended with study level covariates. Results The method is
illustrated using published meta-analysis data. The SAS NLMIXED syntax is
given in the appendix. We conclude that the multivariate random effects
meta-analysis approach is an appropriate and convenient framework to meta-analyse
studies with multiple threshold without losing any information by
dichotomizing the test results. [Accessed November 11, 2009]. Available
at:
http://www.biomedcentral.com/1471-2288/9/73
Verlen J. Product Naming Guide. Description: In a move that is
quite surprising to me, SPSS decided to rename all of its products. The basic
SPSS program is now called PASW Statistics. PASW is an acronym for Predictive
Analytics Software. This letter from the Vice President R&D and Chief Product
Strategist of SPSS Inc. explains why the names were changed and offers a guide
between old and new names of products of SPSS, Inc. [Accessed November 11,
2009]. Available at:
http://www.spss.com/software/product-name-guide/
October
Greenhalgh T, Peacock R. Effectiveness and efficiency of search methods
in systematic reviews of complex evidence: audit of primary sources. BMJ.
2005;331(7524):1064-1065. Excerpt: In systematic reviews of complex and
heterogeneous evidence (such as those undertaken for management and
policymaking questions) formal protocol-driven search strategies may fail to
identify important evidence. Informal approaches such as browsing, "asking
around," and being alert to serendipitous discovery can substantially increase
the yield and efficiency of search efforts. "Snowball" methods such as
pursuing references of references and electronic citation tracking are
especially powerful for identifying high quality sources in obscure locations.
[Accessed October 29, 2009] Available at:
http://www.bmj.com/cgi/content/abstract/331/7524/1064.
Sherman K, Hawkes R, Ichikawa L, et al. Comparing recruitment
strategies in a study of acupuncture for chronic back pain. BMC Medical
Research Methodology. 2009;9(1):69. Abstract: Background Meeting
recruitment goals is challenging for many clinical trials conducted in primary
care populations. Little is known about how the use of different recruitment
strategies affects the types of individuals choosing to participate or the
conclusions of the study. Methods A secondary analysis was performed using
data from participants recruited to a clinical trial evaluating acupuncture
for chronic back pain among primary care patients in a large integrated health
care organization. We used two recruitment methods: mailed letters of
invitation and an advertisement in the health plan's magazine. For these two
recruitment methods, we compared recruitment success (% randomized, treatment
completers, drop outs and losses to follow-up), participant characteristics,
and primary clinical outcomes. A linear regression model was used to test for
interaction between treatment group and recruitment method. Results
Participants recruited via mailed letters closely resembled those responding
to the advertisement in terms of demographic characteristics, most aspects of
their back pain history and current episode and beliefs and expectations about
acupuncture. No interaction between method of recruitment and treatment group
was seen, suggesting that study outcomes were not affected by recruitment
strategy. Conclusion In this trial, the two recruitment strategies yielded
similar estimates of treatment effectiveness. However, because this finding
may not apply to other recruitment strategies or trial circumstances, trials
employing multiple recruitment strategies should evaluate the effect of
recruitment strategy on outcome. Trial registration: Clinical Trials.gov NCT
00065585. [Accessed October 28, 2009]. Available at:
http://www.biomedcentral.com/1471-2288/9/69
University of Georgia. Archives of SPSSX-L@LISTSERV.UGA.EDU.
Description: This site allows you to join the email discussion group about
SPSS or to review its archives. Available at:
http://www.listserv.uga.edu/archives/spssx-l.html [Accessed October 15,
2009].
Garfield J. Assessment Resource Tools for Improving Statistical
Thinking. Excerpt: Our goal is to help teachers assess statistical
literacy, statistical reasoning, and statistical thinking in first courses of
statistics. This Web site provides a variety of assessment resources for
teaching first courses in Statistics. Available at:
https://app.gen.umn.edu/artist/index.html [Accessed October 15,
2009].
U.S. Food and Drug Administration. Guidance for the Use of Bayesian
Statistics in Medical Device Clinical Trials. Excerpt: This document
provides guidance on statistical aspects of the design and analysis of
clinical trials for medical devices that use Bayesian statistical methods. The
purpose of this guidance is to discuss important statistical issues in
Bayesian clinical trials for medical devices and not to describe the content
of a medical device submission. Further, while this document provides guidance
on many of the statistical issues that arise in Bayesian clinical trials, it
is not intended to be all-inclusive. The statistical literature is rich with
books and papers on Bayesian theory and methods; a selected bibliography has
been included for further discussion of specific topics. FDA�s guidance
documents, including this guidance, do not establish legally enforceable
responsibilities. Instead, guidances describe the Agency�s current thinking on
a topic and should be viewed only as recommendations, unless specific
regulatory or statutory requirements are cited. The use of the word should in
Agency guidances means that something is suggested or recommended, but not
required. Available at:
www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/GuidanceDocuments/ucm071072.htm
[Accessed October 13, 2009].
du Prie M. Standards for Research in Child Health. Description:
This website is an effort to develop guidleines for pediatric research that is
evidence-based where possible and a consensus among experts where there is no
evidence. Available at:
http://www.starchildhealth.org/ [Accessed October 11, 2009].
McKay J, Bradley N, Lough M, Bowie P. A review of significant events
analysed in general practice: implications for the quality and safety of
patient care. BMC Family Practice. 2009;10(1):61. Abstract: BACKGROUND:
Significant event analysis (SEA) is promoted as a team-based approach to
enhancing patient safety through reflective learning. Evidence of SEA
participation is required for appraisal and contractual purposes in UK general
practice. A voluntary educational model in the west of Scotland enables
general practitioners (GPs) and doctors-in-training to submit SEA reports for
feedback from trained peers. We reviewed reports to identify the range of
safety issues analysed, learning needs raised and actions taken by GP teams.
METHOD: Content analysis of SEA reports submitted in an 18 month period
between 2005 and 2007. RESULTS: 191 SEA reports were reviewed. 48 described
patient harm (25.1%). A further 109 reports (57.1%) outlined circumstances
that had the potential to cause patient harm. Individual 'error' was cited as
the most common reason for event occurrence (32.5%). Learning opportunities
were identified in 182 reports (95.3%) but were often non-specific
professional issues not shared with the wider practice team. 154 SEA reports
(80.1%) described actions taken to improve practice systems or professional
behaviour. However, non-medical staff were less likely to be involved in the
changes resulting from event analyses describing patient harm (p < 0.05)
CONCLUSION: The study provides some evidence of the potential of SEA to
improve healthcare quality and safety. If applied rigorously, GP teams and
doctors in training can use the technique to investigate and learn from a wide
variety of quality issues including those resulting in patient harm. This
leads to reported change but it is unclear if such improvement is sustained.
Available at:
http://www.biomedcentral.com/1471-2296/10/61 [Accessed October 11, 2009].
Klotsche J, Ferger D, Pieper L, Rehm J, Wittchen H. A novel
nonparametric approach for estimating cut-offs in continuous risk indicators
with application to diabetes epidemiology. BMC Medical Research
Methodology. 2009;9(1):63. Abstract: BACKGROUND: Epidemiological and
clinical studies, often including anthropometric measures, have established
obesity as a major risk factor for the development of type 2 diabetes.
Appropriate cut-off values for anthropometric parameters are necessary for
prediction or decision purposes. The cut-off corresponding to the Youden-Index
is often applied in epidemiology and biomedical literature for dichotomizing a
continuous risk indicator. METHODS: Using data from a representative large
multistage longitudinal epidemiological study in a primary care setting in
Germany, this paper explores a novel approach for estimating optimal cut-offs
of anthropomorphic parameters for predicting type 2 diabetes based on a
discontinuity of a regression function in a nonparametric regression
framework. RESULTS: The resulting cut-off corresponded to values obtained by
the Youden Index (maximum of the sum of sensitivity and specificity, minus
one), often considered the optimal cut-off in epidemiological and biomedical
research. The nonparametric regression based estimator was compared to results
obtained by the established methods of the Receiver Operating Characteristic
plot in various simulation scenarios and based on bias and root mean square
error, yielded excellent finite sample properties. CONCLUSION: It is thus
recommended that this nonparametric regression approach be considered as
valuable alternative when a continuous indicator has to be dichotomized at the
Youden Index for prediction or decision purposes. Available at:
http://www.biomedcentral.com/1471-2288/9/63 [Accessed October 11, 2009].
September
Dyas J, Apeky T, Tilling M, Siriwardena A. Strategies for improving
patient recruitment to focus groups in primary care: a case study reflective
paper using an analytical framework. BMC Medical Research Methodology.
2009;9(1):65. Excerpt: Recruitment to focus group studies should be
considered in two distinct phases; getting potential participants to contact
the researcher, and converting those contacts into attendance. The difficulty
of recruitment in primary care is underemphasised in the literature especially
where people do not regularly come together, typified by this case study of
patients with sleep problems. We recommend training GPs and nurses to recruit
patients during consultations. Multiple recruitment methods should be employed
from the outset and the need to build topic related non-financial incentives
into the group meeting should be considered. Recruitment should be monitored
regularly with barriers addressed iteratively as a study progresses.
Available at:
http://www.biomedcentral.com/1471-2288/9/65 [Accessed September 29, 2009].
McCandless L, Gustafson P, Austin P, Levy A. Covariate balance in a
Bayesian propensity score analysis of beta blocker therapy in heart failure
patients. Epidemiologic Perspectives & Innovations. 2009;6(1):5. Available
at:
http://www.epi-perspectives.com/content/6/1/5 [Accessed September 14,
2009]. Abstract: Regression adjustment for the propensity score is a
statistical method that reduces confounding from measured variables in
observational data. A Bayesian propensity score analysis extends this idea by
using simultaneous estimation of the propensity scores and the treatment
effect. In this article, we conduct an empirical investigation of the
performance of Bayesian propensity scores in the context of an observational
study of the effectiveness of beta-blocker therapy in heart failure patients.
We study the balancing properties of the estimated propensity scores.
Traditional Frequentist propensity scores focus attention on balancing
covariates that are strongly associated with treatment. In contrast, we
demonstrate that Bayesian propensity scores can be used to balance the
association between covariates and the outcome. This balancing property has
the effect of reducing confounding bias because it reduces the degree to which
covariates are outcome risk factors.
Straus S, Haynes RB. Managing evidence-based knowledge: the need for
reliable, relevant and readable resources. CMAJ. 2009;180(9):942-945.
Excerpt: One method for finding useful evidence is the "5S approach". This
framework provides a model for the organization of evidence-based information
services. Ideally, resources become more reliable, relevant and readable as
one moves up the pyramid. To optimize search efficiency, it is best to start
at the top of the pyramid and work down when trying to answer a clinical
question. Available at:
http://www.cmaj.ca/cgi/content/full/180/9/942 [Accessed September 9,
2009].
Mathieu S, Boutron I, Moher D, Altman DG, Ravaud P. Comparison of
Registered and Published Primary Outcomes in Randomized Controlled Trials.
JAMA. 2009;302(9):977-984. Comment: Only the abstract is freely available
today (September 3, 2009), but if the full article is consistent with the
abstract, this is a very shocking finding. Most registered trials are
ambiguous about the primary outcome measure, and many of the trials that are
not show a major discrepancy between the primary outcome as reported in the
publication versus the primary outcome specified in the registry.
Available at:
http://jama.ama-assn.org/cgi/content/abstract/302/9/977 [Accessed
September 3, 2009].
Poses R. A New Perspective on Evaluating the Effects of Financial
Conflict of Interest on Research. Excerpt: I just posted about an
article from the August issue of the Journal of Epidemiology and Community
Health (link here, requires subscription.) Health Care Renewal readers may
want to peruse this issue, which has some very interesting articles on
conflicts of interest and related issues in research. In particular, an
article by Prof Sander Greenland offers a fresh discussion based on
perspectives from epidemiology, statistics, and cognitive psychology of the
effects of financial conflicts of interest (COI) on (clinical,
epidemiological, and health services) research (Greenland S. Accounting for
uncertainty about investigator bias: disclosure is informative. J Epidemiol
Community Health 2009; 63: 593-598. Link here, requires subscription.) Since
only subscribers can easily get this article, and because of its importance,
let me summarize its main points and provide appropriate quotations.
Available at:
http://hcrenewal.blogspot.com/2009/09/new-perspective-on-evaluating-effects.html
[Accessed September 3, 2009].
Brody H. Fairness in Enforcing COI Regs by Journals, and Many Other
Things Also. Excerpt: Laurence J. Hirsch, MD used to manage the Medical
Communications Department for clinical research publications at Merck
(2001-2006). He now works for a device company. This post concerns a paper he
just published in the Mayo Clinic Proceedings. Available at:
http://brodyhooked.blogspot.com/2009/09/fairness-in-enforcing-coi-regs-by.html
[Accessed September 3, 2009].
Hirsch LJ. Conflicts of Interest, Authorship, and Disclosures in
Industry-Related Scientific Publications: The Tort Bar and Editorial Oversight
of Medical Journals. Mayo Clinic Proceedings. 2009;84(9):811-821. Excerpt:
In recent years, Mayo Clinic Proceedings has published a variety of
articles dealing with important, broad-reaching matters of societal interest
that impact medicine and patient care. Topics included ideal physician
behaviors, gender and medical career mentoring, advance directives and
end-of-life issues, physician involvement in capital punishment, and, germane
to this article, institutional conflicts of interest (COIs), as well as the
journal's approach to publication of industry-sponsored clinical research.
Equally important to the well-being of patients and of medicine is the
legitimacy of interactions between industry sponsors of research and
investigator-authors who communicate the information and the journals/editors
who review and ultimately determine publication of the material. In this age
of transparency, disclosure of COIs has assumed great prominence in medical
journals. However, transparency is not always clear, disclosure policies are
varied, and their implementation (by journals and medical societies) is
asymmetric and biased. This commentary examines some prominent recent actions
by consultants to plaintiffs' attorneys and a series of publications in 3
top-tier general medical journals that illustrate selective and incomplete
disclosure of conflicts�both financial and otherwise. In my view, these events
call into question actions by a medical specialty society with one of the
consultants and, more broadly, the editorial practices at the journals
concerning COIs. Specific recommendations are offered to address the latter.
Available at:
http://www.mayoclinicproceedings.com/content/84/9/811.short [Accessed
September 3, 2009].
Lanier WL. Bidirectional Conflicts of Interest Involving Industry and
Medical Journals: Who Will Champion Integrity? Mayo Clinic Proceedings.
2009;84(9):771-775. Excerpt: In the current issue of the Proceedings, the
journal adds to its collection one more COI article that has passed the
journal's stringent peer-review standards. In his commentary, Dr Laurence
Hirsch, a part-time practicing endocrinologist, former employee of Merck & Co
and current employee of another biomedical company contributor to the
Pharmaceutical Manufacturers Association (PhRMA) guidelines on publication
standards, and former president of the International Society for Medical
Publishing Professionals (ISMPP), argues that journals and journal editors
have compromised their credibility as adjudicators of COI and, although likely
unintentionally, have abetted plaintiffs' lawyers to the detriment of the
pharmaceutical industry. Specifically, Hirsch argues that journal editors
sometimes use one set of COI standards for accepting or rejecting manuscripts
when it suits their purposes and another set of standards when it does not.
Available at:
http://www.mayoclinicproceedings.com/content/84/9/771.short [Accessed
September 3, 2009].
Wang R, Lagakos SW, Ware JH, Hunter DJ, Drazen JM. Statistics in
Medicine -- Reporting of Subgroup Analyses in Clinical Trials. N Engl J
Med. 2007;357(21):2189-2194. Excerpt: Medical research relies on clinical
trials to assess therapeutic benefits. Because of the effort and cost involved
in these studies, investigators frequently use analyses of subgroups of study
participants to extract as much information as possible. Such analyses, which
assess the heterogeneity of treatment effects in subgroups of patients, may
provide useful information for the care of patients and for future research.
However, subgroup analyses also introduce analytic challenges and can lead to
overstated and misleading results. This report outlines the challenges
associated with conducting and reporting subgroup analyses, and it sets forth
guidelines for their use in the Journal. Although this report focuses on the
reporting of clinical trials, many of the issues discussed also apply to
observational studies. Available at:
http://content.nejm.org/cgi/content/full/357/21/2189 [Accessed September
3, 2009].
August
Kolata G. Lack of Study Volunteers Hobbles Cancer Fight. The New
York Times. 2009. Excerpt: "There are more than 6,500 cancer clinical
trials seeking adult patients, according to clinicaltrials.gov, a trials
registry. But many will be abandoned along the way. More than one trial in
five sponsored by the National Cancer Institute failed to enroll a single
subject, and only half reached the minimum needed for a meaningful result, Dr.
Ramsey and his colleague John Scoggins reported in an editorial in the
September 2008 issue of The Oncologist." Available at:
www.nytimes.com/2009/08/03/health/research/03trials.html [Accessed August
29, 2009].
Pearson R, Liu X, Sanguinetti G, et al. puma: a Bioconductor package
for propagating uncertainty in microarray analysis. BMC Bioinformatics.
2009;10(1):211. Excerpt: Background Most analyses of microarray data are
based on point estimates of expression levels and ignore the uncertainty of
such estimates. By determining uncertainties from Affymetrix GeneChip data and
propagating these uncertainties to downstream analyses it has been shown that
we can improve results of differential expression detection, principal
component analysis and clustering. Previously, implementations of these
uncertainty propagation methods have only been available as separate packages,
written in different languages. Previous implementations have also suffered
from being very costly to compute, and in the case of differential expression
detection, have been limited in the experimental designs to which they can be
applied. Results puma is a Bioconductor package incorporating a suite of
analysis methods for use on Affymetrix GeneChip data. puma extends the
differential expression detection methods of previous work from the 2-class
case to the multi-factorial case. puma can be used to automatically create
design and contrast matrices for typical experimental designs, which can be
used both within the package itself but also in other Bioconductor packages.
The implementation of differential expression detection methods has been
parallelised leading to significant decreases in processing time on a range of
computer architectures. puma incorporates the first R implementation of an
uncertainty propagation version of principal component analysis, and an
implementation of a clustering method based on uncertainty propagation. All of
these techniques are brought together in a single, easy-to-use package with
clear, task-based documentation. Available at:
www.biomedcentral.com/1471-2105/10/211 [Accessed August 19, 2009].
Harrell FE. Statistical Graphics Course. Available at:
biostat.mc.vanderbilt.edu/wiki/Main/StatGraphCourse
[Accessed August 18, 2009]. Excerpt: Graphical methods are being
increasingly used for exploratory data analysis. Some of the many graphical
tools that are useful in this setting are scatterplot matrices, nonparametric
smoothers, and tree diagrams. Statistical graphics for presenting information
have been used much longer, but most of the commonly used graphics used in
papers, presentations, and the popular media, such as bar charts and pie
charts, are either poor or misleading in communicating information to the
reader. This short course begins with a series of graphical horror stories
from the scientific and lay press. Then elements of graphical perception and
good graph construction, many from the writings of Bill Cleveland, are
covered. Practical suggestions for choosing the best chart or graph type,
making good and clear graphics, and formatting are covered. Techniques for
simultaneous presentation of multiple variables are described.
Burns P. Spreadsheet Addiction. Available at:
www.burns-stat.com/pages/Tutor/spreadsheet_addiction.html [Accessed August
18, 2009]. Excerpt: The goal of computing is not to get an answer, but to
get the correct answer. Often a wrong answer is much worse than no answer at
all. There are a number of features of spreadsheets that present a challenge
to error-free computing.
Deffeyes J, Harbourne R, Dejong S, et al. Use of information entropy
measures of sitting postural sway to quantify developmental delay in infants.
Journal of NeuroEngineering and Rehabilitation. 2009;6(1):34. Available at:
www.jneuroengrehab.com/content/6/1/34 [Accessed August 18, 2009].
Herber O, Schnepp W, Rieger M. Recruitment rates and reasons for
community physicians' non-participation in an interdisciplinary intervention
study on leg ulceration. BMC Medical Research Methodology. 2009;9(1):61.
Available at:
www.biomedcentral.com/1471-2288/9/61 [Accessed August 18, 2009].
Excerpt: Despite great efforts to recruit physicians, the recruitment rate
reached only 26 out of 1549 contacted practices (1.7%) and 12 out of 273
(4.4%) practices during the first and second recruitment phase respectively.
The overall recruitment rate over the 16-month recruitment period was 2%. With
a target recruitment rate of n=300, only 45 patients were enrolled in the
study, not meeting study projections.
Moreno SG, Sutton AJ, Turner EH, et al. Novel methods to deal with
publication biases: secondary analysis of antidepressant trials in the FDA
trial registry database and related journal publications. BMJ.
2009;339(aug07_1):b2981. Available at:
www.bmj.com/cgi/content/abstract/339/aug07_1/b2981 [Accessed August 8,
2009]. Excerpt: Methods Publication biases were identified using novel
contour enhanced funnel plots, a regression based adjustment method, Egger�s
test, and the trim and fill method. Results were compared with a meta-analysis
of the gold standard data submitted to the FDA. Results Severe asymmetry was
observed in the contour enhanced funnel plot that appeared to be heavily
influenced by the statistical significance of results, suggesting publication
biases as the cause of the asymmetry. Applying the regression based adjustment
method to the journal data produced a similar pooled effect to that observed
by a meta-analysis of the FDA data. Contrasting journal and FDA results
suggested that, in addition to other deviations from study protocol, switching
from an intention to treat analysis to a per protocol one would contribute to
the observed discrepancies between the journal and FDA results.
July
Osborne JW, Holland A. What is authorship, and what should it be? A
survey of prominent guidelines for determining authorship in scientific
publications. Practical Assessment, Research & Evaluation. 2009;14(15).
Available at pareonline.net/pdf/v14n15.pdf. Excerpt: The goal of this paper
is to review prominent and diverse guidelines concerning scientific
authorship and to attempt to synthesize existing guidelines into
recommendations that represent ethical practices for ensuring credit where
(and only where) credit is due.
Redelmeier DA. The Cognitive Psychology of Missed Diagnoses. Ann Intern
Med. 2005;142(2):115-120. Available at:
www.annals.org/cgi/content/abstract/142/2/115 [Accessed July 8,
2009]. Description: this paper presents a case study and discusses many
of the psychological issues that come into play during the process of
establishing a diagnosis.
June
Ward A. The role of causal criteria in causal inferences: Bradford
Hill's "aspects of association". Epidemiologic Perspectives &
Innovations. 2009;6(1):2. Available at: www.epi-perspectives.com/content/6/1/2
[Accessed June 24, 2009]. Abstract: As noted by Wesley Salmon and many
others, causal concepts are ubiquitous in every branch of theoretical
science, in the practical disciplines and in everyday life. In the
theoretical and practical sciences especially, people often base claims
about causal relations on applications of statistical methods to data.
However, the source and type of data place important constraints on the
choice of statistical methods as well as on the warrant attributed to the
causal claims based on the use of such methods. For example, much of the
data used by people interested in making causal claims come from
non-experimental, observational studies in which random allocations to
treatment and control groups are not present. Thus, one of the most
important problems in the social and health sciences concerns making
justified causal inferences using non-experimental, observational data. In
this paper, I examine one method of justifying such inferences that is
especially widespread in epidemiology and the health sciences generally -
the use of causal criteria. I argue that while the use of causal criteria is
not appropriate for either deductive or inductive inferences, they do have
an important role to play in inferences to the best explanation. As such,
causal criteria, exemplified by what Bradford Hill referred to as "aspects
of [statistical] associations", have an indispensible part to play in the
goal of making justified causal claims.
May
Lazic S, Mason S, Michell A, Barker R. Visualising disease
progression on multiple variables with vector plots and path plots. BMC
Medical Research Methodology. 2009;9(1):32. Available at:
www.biomedcentral.com/1471-2288/9/32 [Accessed May 29, 2009].
Description: This paper shows how to use vector plots to display
longitudinal changes in individual patients.
SAS Institute. Ten Great Reasons Why A Statistician Should Update to
SAS 9.2. Available at:
support.sas.com/rnd/app/da/stat_top10.html [Accessed May
26, 2009]. Description: I have not used SAS in ten years, but it helps to
know what I am missing. The latest version of SAS has generalized linear
mixed models, quantile regression, and Markov Chain Monte Carlo solutions
for several procedures. SAS has also implemented certain model selection
approaches like LAR and LASSO.
American Statistical Association. Making Sense of Statistical Studies.
Available at:
http://www.amstat.org/education/msss/?nl=0509 [Accessed May 20,
2009]. Excerpt: Are hot dogs unhealthy? What percent of people wear their
seat belts when driving? Which works better-a low-fat diet or a
low-carbohydrate diet? Would most teenagers return an extra $10 they
received in incorrect change at a store? Does listening to music hurt
students' concentration and ability to study? How are peoples' heights and
foot lengths related? These are just a few examples of the types of
questions students will explore in Making Sense of Statistical Studies (MSSS).
The module consists of 15 hands-on investigations that provide students with
valuable experience in designing and analyzing statistical studies. It is
written for an upper middle-school or high-school audience having some
background in exploratory data analysis and basic probability.
Gunnes N, Seierstad T, Aamdal S, et al. Assessing quality of life in
a randomized clinical trial: Correcting for missing data. BMC Medical
Research Methodology. 2009;9(1):28. Available at:
www.biomedcentral.com/1471-2288/9/28 [Accessed May 20, 2009].
Excerpt: Use of proper methodology developed for analysing data subject
to missingness is necessary to reduce potential estimation bias. The quality
of life of patients receiving radiation therapy with concurrent chemotherapy
(docetaxel) appears somewhat worse than that of patients receiving radiation
therapy alone in the period during which treatment is given. The conclusions
are robust for the choice of statistical methods.
Mills E, Chan A, Wu P, et al. Design, analysis, and presentation of
crossover trials. Trials. 2009;10(1):27. Available at:
www.trialsjournal.com/content/10/1/27 [Accessed May 20, 2009].
Excerpt: Reports of crossover trials frequently omit important
methodological issues in design, analysis, and presentation. Guidelines for
the conduct and reporting of crossover trials might improve the conduct and
reporting of studies using this important trial design.
Coory M, Wills R, Barnett A. Bayesian versus frequentist statistical
inference for investigating a one-off cancer cluster reported to a health
depart- ment. BMC Medical Research Methodology. 2009;9(1):30. Available at:
www.biomedcentral.com/1471-2288/9/30 [Accessed May 19, 2009].
Elhai JD, Calhoun PS, Ford JD. Statistical procedures for analyzing mental
health services data. Psychiatry Research. 2008;160(2):129-136. Available at:
www.ncbi.nlm.nih.gov/pubmed/18585790 [Accessed May 19, 2009].
April
Flom PL, Cassell DL. Stopping stepwise: Why stepwise and similar
selection methods are bad, and what you should use. Available at:
www.nesug.org/proceedings/nesug07/sa/sa07.pdf [Accessed April 24,
2009].
Moerman C, Deurenberg R, Haafkens J. Locating sex-specific evidence on
clinical questions in MEDLINE: a search filter for use on OvidSPTM. BMC
Medical Research Methodology. 2009;9(1):25. Available at:
www.biomedcentral.com/1471-2288/9/25 [Accessed April 16, 2009].
Abstract: Background Many recently published clinical studies report
sex-specific data. This information may help to improve clinical
decision-making for both sexes, but it is not easily accessible in MEDLINE.
The aim of this project was to develop and validate a search filter that would
facilitate the retrieval of studies reporting high quality sex-specific data
on clinical questions. Methods A filter was developed by screening titles,
abstracts and Medical Subject Headings (MeSH) in a set of 80 high quality and
relevant papers, 75 of which were identified through a review of clinical
guidelines and five through other means. The filter, for use on OvidSPTM,
consists of nine command lines for searching free text words in the title,
abstract and MeSH of a paper. It was able to identify 74/80 (92.5%) of the
articles from which it was derived. The filter was evaluated in a set of 622
recently published original studies on Alzheimer's disease and on asthma. It
was validated against a reference of 98 studies from this set, which provided
high quality, clinically relevant, sex-specific evidence. Recall and precision
were used as performance measures. Results The filter demonstrated 81/98 (83%)
recall and 81/125 (65%) precision in retrieving relevant articles on
Alzheimer's disease and on asthma. In comparison, only 30/98 (31%) recall
would have been achieved if sex-specific MeSH terms only had been used.
Conclusion This sex-specific search filter performs well in retrieving
relevant papers, while its precision rate is good. It performs better than a
search with sex-specific MeSH. The filter can be useful to anyone seeking
sex-specific clinical evidence (e.g., guideline organizations, researchers,
medical educators, clinicians)
Ethgen M, Boutron I, Steg PG, Roy C, Ravaud P. Quality of reporting
internal and external validity data from randomized controlled trials
evaluating stents for percutaneous coronary intervention. BMC Medical
Research Methodology. 2009;9(1):24. Available at:
www.biomedcentral.com/1471-2288/9/24 [Accessed April 16, 2009].
Abstract: Background Stents are commonly used to treat patients with coronary
artery disease. However, the quality of reporting internal and external
validity data in published reports of randomised controlled trials (RCTs) of
stents has never been assessed. The objective of our study was to evaluate the
quality of reporting internal and external validity data in published reports
of RCTs assessing the stents for percutaneous coronary interventions. Methods
A systematic literature review was conducted. Reports of RCTs assessing stents
for percutaneous coronary interventions indexed in MEDLINE and the Cochrane
Central Register of Controlled Trials and published between January 2003 and
September 2008 were selected. A standardized abstraction form was used to
extract data. All analyses were adjusted for the effect of clustering articles
by journal. Results 132 articles were analyzed. The generation of the
allocation sequence was adequate in 58.3% of the reports; treatment allocation
was concealed in 34.8%. Adequate blinding was reported in one-fifth of the
reports. An intention-to-treat analysis was described in 79.5%. The main
outcome was a surrogate angiographic endpoint in 47.0%. The volume of
interventions per center was described in two reports. Operator expertise was
described in five (3.8%) reports. The quality of reporting was better in
journals with high impact factors and in journals endorsing the CONSORT
statement. Conclusions The current reporting of results of RCTs testing stents
needs to be improved to allow readers to appraise the risk of bias and the
applicability of the results.
Wuensch K. Stepwise Regression = Voodoo Regression. Available at:
core.ecu.edu/psyc/wuenschk/StatHelp/Stepwise-Voodoo.htm [Accessed
April 16, 2009]. Excerpt: It is pretty cool, but not necessarily very
useful, and just plain dangerous in the hands of somebody not well educated in
the multiple regression techniques, including effects of collinearity,
redundancy, and suppression. Here are some quotes from others I have collected
from the now departed STAT-L.
Shahen B. Orwik : The Open Science Platform. Available at: orwik.blogspot.com/
[Accessed April 16, 2009].
March
Jefferson T, Di Pietrantonj C, Debalini MG, Rivetti A, Demicheli V.
Relation of study quality, concordance, take home message, funding, and impact
in studies of influenza vaccines: systematic review. BMJ.
2009;338(feb12_2):b354. Available at:
www.bmj.com/cgi/content/abstract/338/feb12_2/b354 [Accessed March
31, 2009].
Pogue D. Should You Worry About Data Rot? The New York Times.
2009. Available at: www.nytimes.com/2009/03/26/technology/personaltech/26pogue-email.html
[Accessed March 30, 2009]. Description: There are some physical aspects
to the data that you store. these can affect whether your data is readable
10 or 20 years later. David Pogue interviews Dag Spicer, an expert on the
durability (or lack thereof) of various storage media.
Broeze K, Opmeer B, Bachmann L, et al. Individual patient data
meta-analysis of diagnostic and prognostic studies in obstetrics,
gynaecology and reproductive medicine. BMC Medical Research Methodology.
2009;9(1):22. Available at:
www.biomedcentral.com/1471-2288/9/22 [Accessed March 30, 2009].
Abstract: Background In clinical practice a diagnosis is based on a
combination of clinical history, physical examination and additional
diagnostic tests. At present, studies on diagnostic research often report
the accuracy of tests without taking into account the information already
known from history and examination. Due to this lack of information,
together with variations in design and quality of studies, conventional
meta-analyses based on these studies will not show the accuracy of the tests
in real practice. By using individual patient data (IPD) to perform
meta-analyses, the accuracy of tests can be assessed in relation to other
patient characteristics and allows the development or evaluation of
diagnostic algorithms for individual patients. In this study we will examine
these potential benefits in four clinical diagnostic problems in the field
of gynaecology, obstetrics and reproductive medicine. Methods Based on
earlier systematic reviews for each of the four clinical problems, studies
are considered for inclusion. The first authors of the included studies will
be invited to participate and share their original data. After assessment of
validity and completeness, the acquired datasets are merged. Based on these
data, a series of analyses will be performed, including a systematic
comparison of the results of the IPD meta-analysis with those of a
conventional meta-analysis, development of multivariable models for clinical
history alone and for the combination of history, physical examination and
relevant diagnostic tests, and development of clinical prediction rules for
individual patients. These will be made accessible for clinicians.
Discussion The use of IPD meta-analysis will allow evaluating accuracy of
diagnostic tests in relation to other relevant information. Ultimately, this
could increase the efficiency of the diagnostic work-up, e.g. by reducing
the need for invasive tests and/or improving the accuracy of the diagnostic
workup. This study will assess whether these benefits of IPD meta-analysis
over conventional meta-analysis can be exploited and will provide a
framework for future IPD meta-analyses in diagnostic research.
Smith D. Revolutions. News about R, statistics and the world of open
source from the staff of REvolution Computing. Available at:
blog.revolution-computing.com/ [Accessed March 13, 2009].
Xie Y. Keep on Fighting! - Yihui XIE: A Blog Site for Statistics.
Available at:
www.yihui.name/en/index.php [Accessed March 13, 2009].
Goozner M. GoozNews: States Say Medscape CME Part of Off-Label
Promotion Scheme. Available at:
www.gooznews.com/archives/001345.html [Accessed March 9, 2009].
Eurich D, Tsuyuki R, Majumdar S, et al. Metformin treatment in
diabetes and heart failure: when academic equipoise meets clinical reality.
Trials. 2009;10(1):12. Available at:
www.trialsjournal.com/content/10/1/12 [Accessed March 9, 2009].
Rico-Villademoros F, Hernando T, Sanz J, et al. The role of the clinical
research coordinator - data manager - in oncology clinical trials. BMC
Medical Research Methodology. 2004;4(1):6. Available at:
www.biomedcentral.com/1471-2288/4/6
[Accessed March 3, 2009].
Tierney J, Stewart L, Ghersi D, Burdett S, Sydes M. Practical methods
for incorporating summary time-to-event data into meta-analysis. Trials.
2007;8(1):16. Available at:
www.trialsjournal.com/content/8/1/16 [Accessed March 3, 2009].
February
Holland K. Smoothing the Way to Self-Employment. The New York
Times. 2009. Available at: www.nytimes.com/2009/02/22/jobs/22mgmt.html
[Accessed February 26, 2009].
Chan A, Hrobjartsson A, Haahr MT, Gotzsche PC, Altman DG. Empirical
Evidence for Selective Reporting of Outcomes in Randomized Trials:
Comparison of Protocols to Published Articles. JAMA. 2004;291(20):2457-2465.
Available at: jama.ama-assn.org/cgi/content/abstract/291/20/2457
[Accessed February 25, 2009].
Chan A, Altman DG. Identifying outcome reporting bias in randomised
trials on PubMed: review of publications and survey of authors. BMJ.
2005;330(7494):753. Available at: www.bmj.com/cgi/content/abstract/330/7494/753
[Accessed February 25, 2009].
Chan A, Krleza-Jeric K, Schmid I, Altman DG. Outcome reporting bias in
randomized trials funded by the Canadian Institutes of Health Research. CMAJ.
2004;171(7):735-740. Available at: www.cmaj.ca/cgi/content/abstract/171/7/735
[Accessed February 25, 2009].
Feinman R. Intention-to-treat. What is the question? Nutrition &
Metabolism. 2009;6(1):1. Available at: www.nutritionandmetabolism.com/content/6/1/1
[Accessed February 24, 2009].
Johnston M, Hays R, Hui K. Evidence-based effect size estimation: An
illustration using the case of acupuncture for cancer-related fatigue. BMC
Complementary and Alternative Medicine. 2009;9(1):1. Available at: www.biomedcentral.com/1472-6882/9/1
[Accessed February 24, 2009].
Rancoita P, Hutter M, Bertoni F, Kwee I. Bayesian DNA copy number
analysis. BMC Bioinformatics. 2009;10(1):10. Available at: www.biomedcentral.com/1471-2105/10/10
[Accessed February 24, 2009].
Martin-Requena V, Munoz-Merida A, Claros M, Trelles O. PreP+07:
improvements of a user friendly tool to pre-process and analyse microarray
data. BMC Bioinformatics. 2009;10(1):16. Available at: www.biomedcentral.com/1471-2105/10/16
[Accessed February 24, 2009].
Moreno S, Sutton A, Ades A, et al. Assessment of regression-based methods
to adjust for publication bias through a comprehensive simulation study. BMC
Medical Research Methodology. 2009;9(1):2. Available at: www.biomedcentral.com/1471-2288/9/2
[Accessed February 24, 2009].
Haynes AB, Weiser TG, Berry WR, et al. A Surgical Safety Checklist to
Reduce Morbidity and Mortality in a Global Population. N Engl J Med.
2009;360(5):491-499. Available at: content.nejm.org/cgi/content/abstract/360/5/491
[Accessed February 24, 2009].
Gaye P, Nelson D. Effective scale-up: avoiding the same old traps. Human
Resources for Health. 2009;7(1):2. Available at: www.human-resources-health.com/content/7/1/2
[Accessed February 24, 2009].
Yu H, Agarwal S, Johnston M, Cohen A. Are figure legends sufficient?
Evaluating the contribution of associated text to biomedical figure
comprehension. Journal of Biomedical Discovery and Collaboration. 2009;4(1):1.
Available at: www.j-biomed-discovery.com/content/4/1/1 [Accessed
February 23, 2009].
Hirji K. No short-cut in assessing trial quality: a case study. Trials.
2009;10(1):1. Available at: www.trialsjournal.com/content/10/1/1
[Accessed February 23, 2009].
Lund I, Naslund J, Lundeberg T. Minimal acupuncture is not a valid placebo
control in randomised controlled trials of acupuncture: a physiologist's
perspective. Chinese Medicine. 2009;4(1):1. Available at: www.cmjournal.org/content/4/1/1
[Accessed February 10, 2009].
Cao J, Xie X, Zhang S, Whitehurst A, White M. Bayesian optimal discovery
procedure for simultaneous significance testing. BMC Bioinformatics.
2009;10(1):5. Available at: www.biomedcentral.com/1471-2105/10/5
[Accessed February 23, 2009].
Vittinghoff E, McCulloch CE. Relaxing the Rule of Ten Events per Variable
in Logistic and Cox Regression. Am. J. Epidemiol. 2007;165(6):710-718.
Available at: aje.oxfordjournals.org/cgi/content/abstract/165/6/710
[Accessed February 18, 2009]. Description: This article examines the rule
that you need 10 events per independent variable. Some sources cite 15 events
and other 20 events per independent variable. The authors argue that in the
context of adjusting for confounders, this rule might be relaxed a bit.
SAS Institute. 30333 - FASTats: Frequently Asked-For Statistics. Usage
Note 30333: FASTats: Frequently Asked-For Statistics. Available at: support.sas.com/kb/30/333.html
[Accessed February 11, 2009]. Description: This webpage lists hundreds of
specialized statistics and explains how to compute them using SAS software.
January
Mills E, Rachlis B, O'Regan C, Thabane L, Perri D. Metastatic renal cell
cancer treatments: An indirect comparison meta-analysis. BMC Cancer.
2009;9(1):34. Available at: www.biomedcentral.com/1471-2407/9/34
[Accessed January 30, 2009]. Description: This paper is an illustrative
example of the use of meta-analysis to compare two interventions when the
interventions are not compared directly to one another in any study, but
instead are compared to a third intervention common to all the studies.
Schluter P. A multivariate hierarchical Bayesian approach to measuring
agreement in repeated measurement method comparison studies. BMC Medical
Research Methodology. 2009;9(1):6. Available at: www.biomedcentral.com/1471-2288/9/6
[Accessed January 30, 2009]. Description: This paper considers a Bayesian
extension to the Bland-Altman chart to incorporate repeatability assessment as
well as agreement among three or more methods.
Koelch M, Singer H, Prestel A, et al. "...because I am something special"
or "I think I will be something like a guinea pig": information and assent of
legal minors in clinical trials - assessment of understanding, appreciation
and reasoning. Child and Adolescent Psychiatry and Mental Health. 2009;3(1):2.
Available at: www.capmh.com/content/3/1/2 [Accessed January 30, 2009].
Description: Children do not have the legal capacity to formally consent to
participate in research. Respect for the individual, however, still requires
us to seek assent from a child before they participate. How much can a child
truly understand about the research hypothesis? This study examined a group of
children between the ages of 7 and 15 diagnosed with attention
deficit/hyperactivity disorder (ADHD) or ADHD combined with oppositional
defiant disorder. Children understood the general procedures being conducted
in the research but had more difficulty with abstract concepts such as the
need for a placebo and their individual chance of receiving a placebo.
Abrahamowicz M, du Berger R, Krewski D, et al. Bias due to Aggregation
of Individual Covariates in the Cox Regression Model. Am. J. Epidemiol.
2004;160(7):696-706. Available at:
aje.oxfordjournals.org/cgi/content/abstract/160/7/696 [Accessed
January 19, 2009]. Description: Aggregated covariates represent covariates
measured at a group level such as an average income for all patients with a
certain zip code. Aggregated covariates are convenient, inexpensive, and often
can help protect patient confidentiality, but they have their limitations.
This article discusses problems associated with aggregated covariates in the
cox regression model.
Harrell FE. The Role of Covariable Adjustment in the Analysis of
Clinical Trials. Available at:
biostat.mc.vanderbilt.edu/twiki/pub/Main/FHHandouts/covadj.pdf
[Accessed January 19, 2009]. Presented at the Statistics of Multi-center
Trials, Henry Stewart Conference Studies, Washington DC, September 14, 2001.
Note that this is a PDF of some Powerpoint slides, which I usually do not like
to include, but the reputation of Dr. Harrell and the quality of the
bibliograpy more than compensate.
Trevor Sheldon. Managing uncertainty in healthcare. Report of a
meeting organised by NICE and AHRQ. 2008. Available at: www.nice.org.uk/media/A1A/E6/NICEAHRQWorkshopReportFINAL.pdf
[Accessed January 15, 2009]. Excerpt: There are certain challenges that
confront virtually all health systems, irrespective of the means by which they
are funded and administered. One such is the management of uncertainty:
specifically, knowing what to do when data on the effectiveness or the
cost-effectiveness of new medicines or procedures is incomplete or inadequate,
but decisions have nonetheless to be taken on whether to purchase and supply
them to patients. A similar issue arises when there is suspicion that a
procedure or medicine already in use may be relatively ineffective or
represent poor value for money.
R. Kabacoff. Quick-R: Home Page.
Accessed on 2009-01-07. Excerpt: R is an elegant and comprehensive
statistical and graphical programming language. Unfortunately, it can also
have a steep learning curve. I created this website for experienced users of
popular statistical packages such as SAS, SPSS, Stata, and Systat (although
current R users should also find it useful). My goal is to help you quickly
access this language in your work. URL: www.statmethods.net
Vance A. Data Analysts Captivated by R�s Power. The New York Times.
2009. Available at: www.nytimes.com/2009/01/07/technology/business-computing/07program.html
[Accessed January 7, 2009]. Excerpt: To some people R is just the 18th
letter of the alphabet. To others, it�s the rating on racy movies, a measure
of an attic�s insulation or what pirates in movies say. R is also the name of
a popular programming language used by a growing number of data analysts
inside corporations and academia. It is becoming their lingua franca partly
because data mining has entered a golden age, whether being used to set ad
prices, find new drugs more quickly or fine-tune financial models. Companies
as diverse as Google, Pfizer, Merck, Bank of America, the InterContinental
Hotels Group and Shell use it.
Mioplanet, Pixel Ruler:
Your free virtual screen ruler. Accessed on 2009-01-05.
Description: I try to keep my graphic images on my website to about 400 pixels
in width. This free utility places a ruler on the screen so I can size my
graphic images appropriately before exporting them to my website. URL:
www.mioplanet.com/products/pixelruler
Wolfe R, Hanley J. If we're so different, why do we keep overlapping? When
1 plus 1 doesn't make 2. CMAJ. 2002;166(1):65-66. Available at: www.cmaj.ca/cgi/content/full/166/1/65
[Accessed January 5, 2009]. Description: This
article provides a simple explanation why two overlapping confidence intervals
is not the same as showing that the two means are not statistically different
from one another.
Rucker G, Schwarzer G, Carpenter J, Schumacher M. Undue reliance on I^2 in
assessing heterogeneity may mislead. BMC Medical Research Methodology.
2008;8(1):79. Available at: www.biomedcentral.com/1471-2288/8/79
[Accessed January 2, 2009]. This article describes several quantitative
measures of heterogeneity, and argues that most of these measures, including
I^2, are dependent on the sample sizes of the original studies. Instead of
I^2, the authors recommend the use of tau^2.