responsible conduct of research laurel a. beckett, ph.d. professor and chief, division of...

Responsible Conduct of ResearchResponsible Conduct of Research

Laurel A. Beckett, Ph.D.Laurel A. Beckett, Ph.D.Professor and Chief, Division of BiostatisticsProfessor and Chief, Division of Biostatistics

Department of Public Health SciencesDepartment of Public Health Sciences

School of MedicineSchool of Medicine

Part 1. Responsible data collection and Part 1. Responsible data collection and management management

Part 2. Responsible data analysis and Part 2. Responsible data analysis and reporting reporting

Part 1. Responsible collection and management Part 1. Responsible collection and management of the data. General principals. of the data. General principals.

• Ensuring accuracy of the dataEnsuring accuracy of the data

• Accurate reporting of your methodsAccurate reporting of your methods

• Preservation of records.Preservation of records.

• Clarity on ownership and responsibilityClarity on ownership and responsibility

• Adequate provision for sharingAdequate provision for sharing

1.1. Ensuring accuracy of the data is easier if Ensuring accuracy of the data is easier if you plan it that way.you plan it that way.

• Make it hard to do things wrong and easy Make it hard to do things wrong and easy to do them right.to do them right.

• You can do this at various steps in the You can do this at various steps in the process:process:

• Planning the study,Planning the study,• Carrying out the data collection,Carrying out the data collection,• Analyzing the data,Analyzing the data,• Preserving and sharing the data.Preserving and sharing the data.

• Start by making sure you have a complete list of Start by making sure you have a complete list of the information you need to collect. Check this the information you need to collect. Check this list. Then check your forms against the list as list. Then check your forms against the list as you develop them to make sure something didn’t you develop them to make sure something didn’t get inadvertently left out.get inadvertently left out.

• Simplify as much as possible; people do better Simplify as much as possible; people do better when there is less stuff to fill out.when there is less stuff to fill out.

• Some information is so important you might want Some information is so important you might want internal checks by asking a question than once internal checks by asking a question than once or in different ways. or in different ways.

Decide on format for data collection:Decide on format for data collection:

• Paper forms, scanning form of some sort, or direct Paper forms, scanning form of some sort, or direct entry into computer.entry into computer.

• Paper forms are simplest and cheapest. Best way to Paper forms are simplest and cheapest. Best way to go for a small study. More potential for errors. And go for a small study. More potential for errors. And you have to plan for data entry. More possibility for you have to plan for data entry. More possibility for delay.delay.

• Scanning is harder on the person doing the form but Scanning is harder on the person doing the form but faster to get into computer, at least in principle!faster to get into computer, at least in principle!

• Direct entry is fastest, can have error checking build Direct entry is fastest, can have error checking build in. Takes a in. Takes a LOTLOT of up-front effort, problems if of up-front effort, problems if computer goes down.computer goes down.

Tips common to all formats:Tips common to all formats:

1.1. Use version numbers or version dates.Use version numbers or version dates.

2.2. Use consistent coding, e.g., 1=yes, 2=no throughoutUse consistent coding, e.g., 1=yes, 2=no throughout

3.3. Use 4 digit code for year (Y2K is still relevant).Use 4 digit code for year (Y2K is still relevant).

4.4. Record date, time, and person who entered the data.Record date, time, and person who entered the data.

5.5. Distinguish types of non-response (don’t know may Distinguish types of non-response (don’t know may not mean same thing as refusal or not relevant).not mean same thing as refusal or not relevant).

6.6. Use common templates across studies if possible, Use common templates across studies if possible, and standard versions of questions.and standard versions of questions.

7.7. Pretest everything, multiple times!Pretest everything, multiple times!

Specific tips for paper forms:Specific tips for paper forms:1.1. Decide who fills out forms, and who helps if Decide who fills out forms, and who helps if

respondent is not English speaking, can’t write, respondent is not English speaking, can’t write, has vision problems.has vision problems.

2.2. Booklet formats often work better than stapled Booklet formats often work better than stapled sheets of loose sheets.sheets of loose sheets.

3.3. Pretest the data entry as well as filling out Pretest the data entry as well as filling out forms. It helps to set up the data structure for forms. It helps to set up the data structure for data entry in advance.data entry in advance.

4.4. You may want to consider double entry.You may want to consider double entry.

Specific tips for computer-assisted data collection:Specific tips for computer-assisted data collection:

1.1. Allow way more time to develop program than you Allow way more time to develop program than you think necessary.think necessary.

2.2. Build in checks for range, logic, and branching.Build in checks for range, logic, and branching.

3.3. Remember that the “questionnaire” is not just a text Remember that the “questionnaire” is not just a text file, but rather a real computer program. This can be file, but rather a real computer program. This can be a big advantage.a big advantage.

4.4. Always allow for a paper form back-up in case of Always allow for a paper form back-up in case of computer problems.computer problems.

5.5. Allow a way to print out hard copy of records.Allow a way to print out hard copy of records.

6.6. Make sure to download and back up off site.Make sure to download and back up off site.

Anticipate possible sources of error and try to find Anticipate possible sources of error and try to find ways to prevent them:ways to prevent them:

1.1. Non-response, refusal and errors by respondent.Non-response, refusal and errors by respondent.

2.2. Recording error by interviewer (failure to enter value, Recording error by interviewer (failure to enter value, enter wrong value, misunderstand respondent).enter wrong value, misunderstand respondent).

3.3. Data entry errors when paper forms transcribed.Data entry errors when paper forms transcribed.

4.4. Error in data management (wrong data stored or Error in data management (wrong data stored or transmitted, or errors introduced).transmitted, or errors introduced).

5.5. Programming error (everyone enters something Programming error (everyone enters something correctly but summary score or other programmed correctly but summary score or other programmed value is wrong).value is wrong).

2. Accuracy in reporting includes all aspects:2. Accuracy in reporting includes all aspects:

• How you report the primary data,How you report the primary data,

• Reporting how you collected the primary data,Reporting how you collected the primary data,

• And how you compiled, stored and audited the data And how you compiled, stored and audited the data after collection.after collection.

This means keeping good records! For a small lab study This means keeping good records! For a small lab study this might just be a good lab notebook, but for a large this might just be a good lab notebook, but for a large clinical trial it will be many file cabinets and gigabytes of clinical trial it will be many file cabinets and gigabytes of computer memory. Include this in your planning. Worse computer memory. Include this in your planning. Worse yet, you have to keep records for a very long time.yet, you have to keep records for a very long time.

Reporting of primary data:Reporting of primary data:

• This means making sure that what the This means making sure that what the respondent said or what you measured in respondent said or what you measured in the lab is what shows up in your final the lab is what shows up in your final analysis and paper.analysis and paper.

• You need to check all the steps along the You need to check all the steps along the way from interview or instrument to way from interview or instrument to publication to make sure that the numbers publication to make sure that the numbers at the end reflect the data at the at the end reflect the data at the beginning.beginning.

Reporting of primary data: Reporting of primary data: ContinuedContinued

• Keep good records and report accurately how Keep good records and report accurately how you collected the primary data. This means you collected the primary data. This means having copies of paper forms, computer forms, having copies of paper forms, computer forms, data entry instructions, computer programs, data entry instructions, computer programs, and audit forms.and audit forms.

• This is one reason for having hard copies of This is one reason for having hard copies of computer data entry sessions. Most computer computer data entry sessions. Most computer data entry programs have a feature that allows data entry programs have a feature that allows you to do this.you to do this.

Reporting of primary data: Reporting of primary data: ContinuedContinued

• Another useful form of record: a code book for the data Another useful form of record: a code book for the data collected.collected.

• For each data item collected the code book tells the For each data item collected the code book tells the variable name, interpretation, allowable values, whether variable name, interpretation, allowable values, whether there are any branching considerations, labels of values there are any branching considerations, labels of values if appropriate.if appropriate.

• The code book should also have the name and contact The code book should also have the name and contact information for the person who compiled it, the date last information for the person who compiled it, the date last updated, and the version number to which it refers.updated, and the version number to which it refers.

Reporting of primary data:Reporting of primary data: ContinuedContinued

• Some FDA guidelines require such things as Some FDA guidelines require such things as double programming of data entry and data double programming of data entry and data management programs. Be sure you can management programs. Be sure you can document who programmed computers, when, document who programmed computers, when, and have those programs available in case of and have those programs available in case of audit.audit.

• I like to have a set of “I like to have a set of “good programming good programming practicepractice” guidelines and use that as part of ” guidelines and use that as part of evaluation of programmers. It is also useful to evaluation of programmers. It is also useful to show your external reviewers.show your external reviewers.

Conduct regular audits and keep track of Conduct regular audits and keep track of your results.your results.

This includes audits of:This includes audits of:

1.1. Accuracy of the primary data and,Accuracy of the primary data and,

2.2. Accuracy of the process (consents, IRB annual Accuracy of the process (consents, IRB annual renewal, storage and back-up of data).renewal, storage and back-up of data).

Audits typically do a percentage of the primary data Audits typically do a percentage of the primary data and and ALLALL of the consents, IRB and so on. of the consents, IRB and so on.

Set a standard for accuracy, and if it is not met, do Set a standard for accuracy, and if it is not met, do diagnostics, audit more stuff, and get it fixed.diagnostics, audit more stuff, and get it fixed.

If errors are found, they need to be corrected. If errors are found, they need to be corrected.

Errors should be corrected on the “Errors should be corrected on the “primary data baseprimary data base,” ,” not on copies.not on copies.

There should be limited permission to change primary There should be limited permission to change primary data base and you should track who makes changes data base and you should track who makes changes and why. Best to preserve ability to restore an older and why. Best to preserve ability to restore an older version if needed.version if needed.

Also track queries about data and how they were Also track queries about data and how they were resolved.resolved.

Keep good records of the error finding and correction Keep good records of the error finding and correction process.process.

3. Preserve records – if not forever, at least as 3. Preserve records – if not forever, at least as long as the current NIH guidelines at the time long as the current NIH guidelines at the time you complete the study. you complete the study.

Keep your original data (paper forms or copies of Keep your original data (paper forms or copies of computer data entry) in a safe place, locked, and in computer data entry) in a safe place, locked, and in separate location from the primary computer.separate location from the primary computer.

Back up your computer regularly and keep those back-Back up your computer regularly and keep those back-ups off site. Update back-up media as needed. Tapes ups off site. Update back-up media as needed. Tapes and diskettes are now obsolete; CD’s could go that and diskettes are now obsolete; CD’s could go that way, too.way, too.

Check your back-ups occasionally and redo if Check your back-ups occasionally and redo if necessary or make copies to new media.necessary or make copies to new media.

4. Be clear on who ownership of the data. 4. Be clear on who ownership of the data.

The institution that received the grant typically “The institution that received the grant typically “ownsowns” ” the data.the data.

The PI has custody and is responsible for accuracy and The PI has custody and is responsible for accuracy and protection.protection.

NIH now expects a copy of the data to be made public NIH now expects a copy of the data to be made public at some point. There is an expectation of accuracy.at some point. There is an expectation of accuracy.

You need to decide which is the “You need to decide which is the “primaryprimary” copy. This ” copy. This should not live somewhere that it can vanish from PI’s should not live somewhere that it can vanish from PI’s control.control.

Note: Ownership does not necessarily Note: Ownership does not necessarily include permission to peek at the data. include permission to peek at the data.

Clinical trials that are masked typically restrict Clinical trials that are masked typically restrict that to the study statisticians and the Data and that to the study statisticians and the Data and Safety Monitoring Committee (DSMC).Safety Monitoring Committee (DSMC).

Who gets access for writing papers, and who Who gets access for writing papers, and who gets to write which papers? Best to set up a gets to write which papers? Best to set up a mechanism in advance.mechanism in advance.

The PI is responsible for confidentiality but The PI is responsible for confidentiality but collaborators have to behave themselves. collaborators have to behave themselves.

Collaborators, including trainees, have rights of access Collaborators, including trainees, have rights of access to the data.to the data.

Typically there is a process of approval of publications Typically there is a process of approval of publications (maybe a committee).(maybe a committee).

Publications are expected to come out in a timely Publications are expected to come out in a timely fashion.fashion.

You should be able to produce the data that were used You should be able to produce the data that were used for the publication if so requested.for the publication if so requested.

55. Researchers who want to replicate your . Researchers who want to replicate your results should be able to do so. results should be able to do so.

This may require access to the original data.This may require access to the original data.

It may also require access to programs.It may also require access to programs.

And accurate documentation should be And accurate documentation should be available. The code book is useful here.available. The code book is useful here.

Part 2Part 2. Responsible analysis of the data. . Responsible analysis of the data.

General principals:General principals:

1.1. Clearly stated scientific questions.Clearly stated scientific questions.

2.2. Study designed to address questions.Study designed to address questions.

3.3. High participation rates.High participation rates.

4.4. The key variables measured accurately.The key variables measured accurately.

5.5. Pre-planned analyses that match question and data.Pre-planned analyses that match question and data.

6.6. Assumptions of analysis are met.Assumptions of analysis are met.

7.7. Well chosen summaries (numbers, tables, graphics).Well chosen summaries (numbers, tables, graphics).

8.8. Awareness of limitations of the study.Awareness of limitations of the study.

22. Design your study to address your questions. . Design your study to address your questions.

Plan a sample size with adequate power for your Plan a sample size with adequate power for your hypotheses. Allow for multiple comparisons if hypotheses. Allow for multiple comparisons if needed. Use pilot data or previous literature to needed. Use pilot data or previous literature to give you a basis for computing sample size and give you a basis for computing sample size and power.power.

Make good use of ways to reduce variance and Make good use of ways to reduce variance and improve precision: clever sampling designs, improve precision: clever sampling designs, repeated measures, regression adjustment for repeated measures, regression adjustment for covariates, paired designs. The exact strategy will covariates, paired designs. The exact strategy will depend on your setting.depend on your setting.

33. Attaining and keeping the desired sample . Attaining and keeping the desired sample ssize is really important!ize is really important!

Try for a high participation rate, both to get Try for a high participation rate, both to get sample size and to avoid selection bias.sample size and to avoid selection bias.

Try to avoid drop-out and loss to follow-up.Try to avoid drop-out and loss to follow-up.

Try to get complete data on participants.Try to get complete data on participants.

If you do have some losses or incomplete If you do have some losses or incomplete data, make use of special techniques that data, make use of special techniques that use partial data, but then be careful to check use partial data, but then be careful to check the assumptions.the assumptions.

44. Make sure your key outcomes and predictors . Make sure your key outcomes and predictors are carefully measured. are carefully measured.

Check the precision of your measurements.Check the precision of your measurements.

If you are using trained raters, monitor and retrain If you are using trained raters, monitor and retrain as necessary. Check inter-rater reliability.as necessary. Check inter-rater reliability.

Validate new instruments before using in a study. Validate new instruments before using in a study. Think about face validity, within and between Think about face validity, within and between patient variation, within and between rater patient variation, within and between rater variation, bias, precision, reproducibility. Don’t just variation, bias, precision, reproducibility. Don’t just rely on r-square or kappa or phi or percent rely on r-square or kappa or phi or percent agreement. More detailed assessment can be very agreement. More detailed assessment can be very illuminating and help to improve the instrument.illuminating and help to improve the instrument.

I like to collect more detailed data and collapseI like to collect more detailed data and collapseinto categories later. For example, ask about yearsinto categories later. For example, ask about yearsof formal education rather than category, and of formal education rather than category, and measure SBP/DBP rather than just recording measure SBP/DBP rather than just recording whether someone is hypertensive, borderline orwhether someone is hypertensive, borderline ornormal.normal.

If the data are not normally distributed, consider If the data are not normally distributed, consider transformation or nonparametric approaches.transformation or nonparametric approaches.

Look at your data before analysis, to assess for Look at your data before analysis, to assess for problems (both with data quality and with the problems (both with data quality and with the statistical distribution assumptions).statistical distribution assumptions).

55. Pre-plan the analyses to match the. Pre-plan the analyses to match the questions questions..

If your specific aims are clear enough, it should be If your specific aims are clear enough, it should be possible to write down a very careful analytic plan.possible to write down a very careful analytic plan.

The question should drive the design and the design The question should drive the design and the design should drive the analysis.should drive the analysis.

If you will be doing interim analysis, plan for this by If you will be doing interim analysis, plan for this by adjusting your alpha and sample size as needed, e.g., adjusting your alpha and sample size as needed, e.g., the O’Brien-Fleming rule for alpha spending.the O’Brien-Fleming rule for alpha spending.

Be Be VERYVERY wary of post-hoc hypotheses? If you write wary of post-hoc hypotheses? If you write down your plan up front, these should be easily down your plan up front, these should be easily recognized.recognized.

If the data violate the assumptions of your planned If the data violate the assumptions of your planned analysis, have a back-up plan such as transformation analysis, have a back-up plan such as transformation or more robust analysis. Don’t just throw out data until or more robust analysis. Don’t just throw out data until the data match the plan.the data match the plan.

Keep all analytic documents (the plan, univariate and Keep all analytic documents (the plan, univariate and bivariate looks at data, validation, programs). bivariate looks at data, validation, programs). Programs should say who wrote them and when. I like Programs should say who wrote them and when. I like lots of comments in programs.lots of comments in programs.

Cross reference programs, output and papers. I Iike to Cross reference programs, output and papers. I Iike to have output footnoted with the file name of the source have output footnoted with the file name of the source code.code.

Irresponsible conduct of research: potential pitfalls in Irresponsible conduct of research: potential pitfalls in statistical analysis and reporting.statistical analysis and reporting.

Post-hoc hypotheses.Post-hoc hypotheses.

Inappropriate analyses (method does not address Inappropriate analyses (method does not address question of interest or data violate assumptions).question of interest or data violate assumptions).

Fragmentary reports (incomplete summary of findings Fragmentary reports (incomplete summary of findings with results you don’t like suppressed).with results you don’t like suppressed).

Data or experiments suppressed or trimmed to give Data or experiments suppressed or trimmed to give desired results.desired results.

Selective reports of findings, including misleading Selective reports of findings, including misleading choice of summary statistics or graphics.choice of summary statistics or graphics.

66. Check the a. Check the assumptions and use analysis suited to ssumptions and use analysis suited to the data you havethe data you have..

Classical assumptions: linearity, normality,Classical assumptions: linearity, normality,homoscedasticity, independence, for example.homoscedasticity, independence, for example.

You can get spurious results if these are violated – You can get spurious results if these are violated – either Type I or Type II errors, too wide or too either Type I or Type II errors, too wide or too narrow confidence intervals.narrow confidence intervals.

Possible fixes: transform data, choose a different Possible fixes: transform data, choose a different statistical model and procedure, choose robust statistical model and procedure, choose robust procedures (non-parametric or other).procedures (non-parametric or other).

77. Choose summaries that rev. Choose summaries that reveal and clarify, not eal and clarify, not obscure, your key findingsobscure, your key findings..

Graphics: Used for emphasis. Carry a big impact. Ed Tuft’s Graphics: Used for emphasis. Carry a big impact. Ed Tuft’s books have lots of good ideas.books have lots of good ideas.

Tables: When people will want to have details available. Tables: When people will want to have details available. They tend to obscure the message.They tend to obscure the message.

Summary statistics: Measures of spread + center.Summary statistics: Measures of spread + center.

Inferences: Include P value, magnitude of effect, precision, Inferences: Include P value, magnitude of effect, precision, and some idea of how much variation there is left to and some idea of how much variation there is left to explain.explain.

Use units that make sense and are interpretable.Use units that make sense and are interpretable.

88. Consider and discuss the limit. Consider and discuss the limitations of your ations of your studystudy..

Try to assess impact of limitations.Try to assess impact of limitations.

For example, you might be able to do sensitivity analysis to For example, you might be able to do sensitivity analysis to get an idea of impact of non-response. You can use your get an idea of impact of non-response. You can use your sample size and power to determine whether your null sample size and power to determine whether your null finding is informative, and how much (how big an effect finding is informative, and how much (how big an effect might you have missed, with what probability). might you have missed, with what probability).

Note for Clinical Trials: Note for Clinical Trials:

The CONSORT document (available on line, The CONSORT document (available on line, revised version, through many journals) outlines revised version, through many journals) outlines what you need to report. This can be used as a what you need to report. This can be used as a guideline for other kinds of studies, too.guideline for other kinds of studies, too.

We pre-plan our study reports and give part of We pre-plan our study reports and give part of DSMC reports in outline form following this DSMC reports in outline form following this document. For example, the study flow charts are document. For example, the study flow charts are really helpful for tracking participation and loss to really helpful for tracking participation and loss to follow-up.follow-up.

Responsible collaboration: guidelines Responsible collaboration: guidelines for working with a statistician:for working with a statistician:

1.1. Consult the statistician early if possible! We can’t Consult the statistician early if possible! We can’t save a study that was designed wrong.save a study that was designed wrong.

2.2. Agree up front on who will have responsibility for Agree up front on who will have responsibility for data accuracy, data management, back up, quality data accuracy, data management, back up, quality control. This might be the researcher; the control. This might be the researcher; the statistical group, or a separate data management statistical group, or a separate data management group. group.

3.3. Agree on goals of study and on a draft analytic Agree on goals of study and on a draft analytic plan early in the process. Try to understand what plan early in the process. Try to understand what the statistician is proposing, and why.the statistician is proposing, and why.

4.4. Discuss whether statistician will provide just analytic Discuss whether statistician will provide just analytic results, or also draft tables, graphics, methods results, or also draft tables, graphics, methods sections, and other components.sections, and other components.

5.5. Discuss the possibility of regular meetings or Discuss the possibility of regular meetings or statistician attending some research group meetings. statistician attending some research group meetings.

6.6. Plan to credit work appropriately.Plan to credit work appropriately.

7.7. Discuss who will keep the records of analysis and Discuss who will keep the records of analysis and programs, and how any transition might be handled if it programs, and how any transition might be handled if it looks like that might occur (for example, if a grad looks like that might occur (for example, if a grad student is doing analyses but is expected to graduate).student is doing analyses but is expected to graduate).

8.8. If there’s something you don’t understand, If there’s something you don’t understand, ASKASK!!

Responsible Conduct of Research: Objective ReportingResponsible Conduct of Research: Objective ReportingReferences:References:

• Moher D, Schultz KF, Altman D. The CONSORT Moher D, Schultz KF, Altman D. The CONSORT statement: revised recommendations for improving the statement: revised recommendations for improving the quality of reports of parallel-group randomized trials. quality of reports of parallel-group randomized trials. JAMA JAMA 2001; 285:1997-1991.2001; 285:1997-1991.– This statement has been accepted in and published by a number This statement has been accepted in and published by a number

of top-tier medical journals. It includes a 22-item checklist of of top-tier medical journals. It includes a 22-item checklist of items that should be included in a report of a clinical trial and a items that should be included in a report of a clinical trial and a diagram of patient flow that can serve as a useful template. diagram of patient flow that can serve as a useful template. Many items apply not just to clinical trials, but to any clinical Many items apply not just to clinical trials, but to any clinical research.research.

• The CONSORT statement has been used as a starting The CONSORT statement has been used as a starting point for publication guidelines for other kinds of studies, point for publication guidelines for other kinds of studies, too.too.

• Stone SP, Cooper BS, Kibbler CC, Cookson BD, Roberts Stone SP, Cooper BS, Kibbler CC, Cookson BD, Roberts JA, Medley GF, Duckworth G, Lai R, Ebrahim S, Brown JA, Medley GF, Duckworth G, Lai R, Ebrahim S, Brown EM, Wiffen PJ, Davey PG. The ORION statement: EM, Wiffen PJ, Davey PG. The ORION statement: guidelines for transparent reporting of outbreak reports guidelines for transparent reporting of outbreak reports and intervention studies of nosocomial infection. and intervention studies of nosocomial infection. Lancet Lancet Infect Dis. Infect Dis. 2007 Apr;7(4):282-8.2007 Apr;7(4):282-8.– This paper extends the guidelines to infectious disease study This paper extends the guidelines to infectious disease study

reports.reports.

• McShane LM, Altman DG, Sauerbrei W, Taube SE, Gion McShane LM, Altman DG, Sauerbrei W, Taube SE, Gion M, Clark GM; Statistics Subcommittee of the NCI-M, Clark GM; Statistics Subcommittee of the NCI-EORTC Working Group on Cancer Diagnostics. EORTC Working Group on Cancer Diagnostics. Reporting recommendations for tumor marker prognostic Reporting recommendations for tumor marker prognostic studies (REMARK). studies (REMARK). J Natl Cancer InstJ Natl Cancer Inst. 2005 Aug . 2005 Aug 17;97(16):1180-4.17;97(16):1180-4.– This version addresses the reporting guidelines for tumor This version addresses the reporting guidelines for tumor

biomarker studies.biomarker studies.

Responsible Conduct of Research: Objective ReportingResponsible Conduct of Research: Objective ReportingReferences continued:References continued:

• Campbell MK, Elbourne DR, Altman DG; CONSORT group. CONSORT statement: extension to cluster randomised trials. BMJ. 2004 Mar 20;328(7441):702-8.– The CONSORT guidelines have also been extended to cluster

randomized designs.

• Squires K, Pozniak AL, Pierone G, et al. Tenofovir disoproxil fumarate in nucleosideresistant HIV-1 infection: a randomized trial. Ann Intern Med 2003; 139:313-20.– This paper, in a journal that subscribes to the CONSORT

principles, illustrates how to use the guidelines in reporting a clinical trial. Note the nice flow chart based on CONSORT.



• Devereaux PJ, Manns BJ, Ghali WA, et al. The reporting of methodologic factors in randomized clinical trials and the association with a journal policy to promote adherence to the Consolidated Standards of Reporting Trials (CONSORT) checklist. Controlled Clinical Trials 2002; 23:380-388.– This paper studied 105 RCT’s in 29 medical journals and found that of

the 11 methodological factors, the average was 6 reported in CONSORT-standard journals and 5 in non-CONSORT. There is still room for improvement in reporting.

• Tufte, ER. The Visual Display of Quantitative Information. Graphics Press, Cheshire, CT: 1983. (Also Visual Explanations and Envisioning Information)– These three books provide a beautifully illustrated and thoughtful tutorial

into how good graphics can inform readers, and bad graphics can mislead them. For a particularly dramatic example, read Tufte’s section on the Challenger explosion: the data were trying to warn people but were hidden in abysmal displays.

• Lang TA, Secic M. Lang TA, Secic M. How to report statistics in medicine: How to report statistics in medicine: annotated guidelines for authors, editors, and reviewers. annotated guidelines for authors, editors, and reviewers. American College of Physicians, 1997.American College of Physicians, 1997.– This book is available in paperback and gives a good This book is available in paperback and gives a good

overview for the practicing physician of what to overview for the practicing physician of what to include and how to say or show it.include and how to say or show it.


http://onlineethics.org/reseth/mod/data.html

This web site is very nice, has a lot of references and links.

If you do biomedical research, it is useful to read the following brief sections of the International Committee of Medical Journal Editors' "Uniform Requirements for Manuscripts Submitted to Biomedical Journals." This statement was published in 1997 in the New England Journal of Medicine 335: 309-315, and was updated May 2000.

* Corrections, Retractions, and" Expressions of Concern" about Research Findings* Medical Journals and the Popular Media,* Human subjects protection,* Publication of industry-sponsored research.

The UNC web site you can link to from this web site has an excellent “text” on statistical ethics and responsible analysis.

NIH recently instituted a policy that requires that all proposals for contracts and grants for research involving human subjects submitted after October 1, 2000 certify that all key personnel have received education on the protection of human research subjects. This requirement applies to all applications for grants or proposals for contracts submitted to NIH after October 1st and to all new and all non-competing grants for which an award is issued after October 1st. NIH has posted a web series of "frequently-asked questions" regarding these new requirements. The frequently asked questions can be accessed at: http://grants.nih.gov/grants/policy/hs_educ_faq.htm.Here is one NIH certificate web site:http://cme.cancer.gov/clinicaltrials/learning/humanparticipant-protections.asp

A terrific web site for statistical practice in medicine is Jerry Dallal’s “Little Handbook of Statistical Practice”:http://www.tufts.edu/~gdallal/LHSP.HTMJerry also has links to all the articles in the BMJ series on statistical practice in medicine, a superb series, very well written.

Responsible Conduct of Research: Objective ReportingResponsible Conduct of Research: Objective ReportingSome web sites that may be helpful:Some web sites that may be helpful:

responsible conduct of research laurel a. beckett, ph.d. professor and chief, division of...

Documents