DiscoverBlood & CancerReader beware: Interpreting post hoc analyses
Reader beware: Interpreting post hoc analyses

Reader beware: Interpreting post hoc analyses

Update: 2019-10-31
Share

Description

David L. Streiner, PhD, of McMaster University, Hamilton, Ont., and the University of Toronto, joins Blood & Cancer host David Henry, MD, of Pennsylvania Hospital, Philadelphia, to explain what a post hoc analysis is and why it should be interpreted with caution.

Plus, in Clinical Correlation, Ilana Yurkiewicz, MD, of Stanford (Calif.) University, explores what to tell patients when it comes to prognostic scoring system results.

* * * 

Help us make this podcast better! Please take our short listener survey: https://www.surveymonkey.com/r/podcastsurveyOct2019

* * * 

This week in Oncology:

In rectal cancer, fragmented care linked to lower survival
by Jim Kling, reporting from Clinical Congress 2019.

Post hoc analyses

What is a post hoc analysis? Analyzing data after a study has already had conclusions made and looking for patterns that were not prespecified.

Dr. Streiner’s advice for researchers: Pick a small number of primary outcomes and develop a narrow hypothesis. Then use post hoc analysis as a means of assessing future questions that can be investigated in a subsequent study.

Dr. Streiner’s advice for clinicians: Treat a post hoc analysis as a hypothesis that requires further study. It should be viewed with some degree of suspicion because it may have been significant only by chance.

Show notes by Ronak Mistry, DO, resident in the department of internal medicine, University of Pennsylvania, Philadelphia.

 

References

Marcus R et al. Obinutuzumab for the first-line treatment of follicular lymphoma. N Engl J Med. 2017;377:13 31-44.

Crawford ED et al. Comorbidity and mortality results from a randomized prostate cancer screening trial. J Clin Oncol. 2011;29:35 5-61.

Streiner DL et al. Size, follow-up, data analysis – good; post hoc analysis, interpretation – not so good. Commun Oncol. 2011;8:37 9-80.

 

For more MDedge Podcasts, go to mdedge.com/podcasts

Email the show: podcasts@mdedge.com

Interact with us on Twitter: @MDedgehemonc

David Henry on Twitter: @davidhenrymd

Ilana Yurkiewicz on Twitter: @ilanayurkiewicz

 

Comments 
loading
00:00
00:00
1.0x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

Reader beware: Interpreting post hoc analyses

Reader beware: Interpreting post hoc analyses

MDedge