home   author    contact   web site dedication



Specific guide to this web site for:

 1.  Medical School
      in Statistics

 2.  Medical Students

 3.  Science media writers

 4.  High School & College
     Statistic Teachers


1. Harvard led MI study

2. JACC study 

   (J. of Amer. Coll.

3. NEJM cath study

4. Amer. J. of Cardio.
    review of literature


Oat bran study

Pregnancy & Alcohol

Are Geminis really
9. Columbia 'Miracle' Study  

Additional Topics:


Limitations of Meta-Analyses

Large Randomized Clinical Trials

Tale of Two Large

Advocate meta-analyses

Network meta-analyses





Improving Medical Statistics and the Interpretation of Medical Studies

    There is considerable variability in the information that the public and physicians receive regarding the results of medical trials. One contributing factor is the incorrect application of statistics in the medical literature. A more common source of error is that the conclusions of a study are not always a reasonable reflection of the data presented.
    The following includes examples of the misuse of statistics and inappropriate conclusions in the medical literature. Some suggestions for improvement are included.        


1. Death of the oat bran fad  How an improperly interpreted study led to the death of the oat bran fad.

2. Are Geminis really different? -The Pratfalls of Subgroup Analysis. Excessive subgroup analysis can lead to the invalid conclusion that treatment outcome is determined by an astrological sign.

3. Biased meta-analysis conclusions  Can you really bias the conclusions of a meta-analysis? You decide which slanted version of these conclusions you would pick. 

4. The ALLHAT hypertension trial controversy that occurred immediately following publication was a marker for conclusions that extended beyond a reasonable and conservative interpretation of the data. What are the problems with the ALLHAT trial conclusions that a diuretic is the preferred initial therapy for hypertension?      download (pdf)

5. NEW  Another meta-analysis mishap. This Harvard associated meta-analysis creates information that does not exist in the study: monounsaturated fatty acids replacing saturated fatty acids. Seemingly sophisticated statistical manipulation leads to unreliable information.

6. The Columbia University 'Miracle' Study
The unfortunate saga of possible fraud in a medical study with a medical journal and a medical school failing to respond appropriately.
Including:  "Lessons to be Learned" by Dr. Bruce Flamm 

7. Limitations of meta-analysis  What are some of the pitfalls that can occur in the summation of clinical trials (meta-analysis) that can lead to invalid conclusions?

8. Celebrex  How the initial article that admirably and beneficially raised public awareness of the potential risks of Vioxx and Celebrex was right about Celebrex for the wrong reason. What was invalid in the statistical analysis of the initial article in regards to the assessment of Celebrex?

9. Self-correcting nature of science. Comments on the self-correcting nature of science.

10, List of questions to consider routinely asking when a medical trial is published. 

11. Low level alcohol ingestion during pregnancy  An alternative look at some of the studies analyzing low level alcohol ingestion during pregnancy.

Several topics are available as downloadable files:   click here

Misadventures in Medical Statistics & the Interpretation of Clinical Trials:

1.  A trial led by Harvard Medical School faculty with a protocol so biased (unintentionally) that the trial was inherently invalid. details
*See comments by cardiology leaders.  (O'Neil, Sleight, Swan, Topol) 

2.  A statistical analysis in a major medical journal JACC (Journal of American College of Cardiology) which was so bad, that it may have led to a subsequent improvement in the review process of JACC.   details
*See comments by one of the JACC editors

3.  An example of a study in the New England Journal of Medicine where the conclusions run exactly the opposite of what the data suggests. details
In this one study, the authors unintentionally miscounted their trial's primary endpoints, included patients that did not belong in the trial, then incorrectly analyzed the data with a potential for a Type II statistical error, and finally failed to appreciate the implications of their miscounted data. (A grand slam for a poorly conducted and interpreted trial). 

 4.  How an incorrect review of the literature in in a single article in the medical literature could potentially adversely affect patient care.  details 

 5. The ALLHAT trial.  How conclusions that extend beyond the data can provoke controversy.   details 

6. Death of the oat bran fad. (Murdered by a poorly conceived study.)  details

7. Pregnancy and alcohol, what do some of the studies really suggest? details

8. The Hazards of Subgroup Analysis  (Are Geminis really different?) 

9. The Columbia University 'Miracle' Study-  The unfortunate saga of possible fraud in a medical study with a medical journal and a medical school failing to respond appropriately. 
    Including:  "Lessons to be Learned" by Dr. Bruce Flamm   .

10.  Perspectives:

         Limitations of Meta-Analyses

The Very Large Randomized Clinical Trial  (Strengths and Limitations) 

A Tale of Two Large Trials

Beware of Meta-analyses Bearing False Gifts

        Network meta-analyses, a problem with reliability

11. How science has reparative processes that limit problems resulting from poor statistics or inappropriate conclusions ( How these particular issues might look   "10 years later".

12. Effect on p Values when the difference in outcome events remains constant as the number of background events increases for a constant sample size                    _

    To return to prior web page position: click here       .

Topics available in a download file: 

    Lessons from an unusual saga of possible fraud in the literature                     __
            The Columbia Miracle Study:      pdf download 

    The hazards of subgroup analysis. Are Geminis really different?
                                                                pdf download   

    Can a meta-analysis be biased?
     You decide in 60 seconds:                        pdf download  
            Limitations of Meta-analysis: overview:   pdf download  

    Tale of Two Trials-  A superbly conducted trial contrasted to a suboptimally interpreted trial:            pdf download    

    Miscounted and Misinterpreted.  How not to conduct a study.
             The NEJM cath study        pdf download  

    A detailed critique of the ALLHAT trial and subsequent meta-analysis
                                              pdf download  

This web site is dedicated to the principle of the conservative interpretation of clinical trials where the conclusions of a study are limited to those directly derived from the experimental data. 


    2005-2024   ImprovingMedicalStatistics.com

















Submit here:
Nominations for Medical Statistics Misadventures 


The Reparative Power of Science:
Revisit these controversies
"10 years later"


List of Questions to Consider for a Clinical Trial