(THREAD) this recent publication offers a teachable moment on data analysis of parallel-group RCT’s that include pre- and post-treatment measures of a continuous outcome variable:https://www.ncbi.nlm.nih.gov/pubmed/30864188
-
Show this thread
-
Full text here:https://onlinelibrary.wiley.com/doi/full/10.1002/ptr.6328 …
1 reply 0 retweets 0 likesShow this thread -
The authors randomly assigned participants with type 2 diabetes to receive either curcumin (n=23) or placebo (n=21) for 10 weeks.
1 reply 0 retweets 0 likesShow this thread -
Participants gave a baseline and end-of-trial blood sample from which the research team measured triglycerides, total cholesterol, LDL, HDL, hs-CRP, and adiponectin at both time points.
1 reply 0 retweets 0 likesShow this thread -
The study team did some things properly in carrying out this trial. Unfortunately, they did not use a very good approach for their data analysis and reporting of results.
1 reply 0 retweets 0 likesShow this thread -
For the moment, let’s put aside multiplicity considerations and focus on just one outcome: triglycerides, since a) it’s listed at the top of Table 4 and b) the authors chose to highlight triglyceride (TG) results in their abstract and conclusions.
2 replies 0 retweets 0 likesShow this thread -
Replying to @ADAlthousePhD
Let's also ignore a study of diabetes that took bloods but didn't include a measure of blood sugar????
2 replies 0 retweets 2 likes -
Replying to @GidMK
Yeah, I’m staying in “my lane” and commenting on the statistical issues here, but feel free to point out any other problems. I don’t think this trial should be taken very seriously, but it’s a good teaching vehicle to explain why NOT to do what they did for analysis.
2 replies 0 retweets 1 like
Yeh look if you're doing a diabetes study and not measuring HbA1c or fasting glucose even though you're taking bloods...that's very odd in a bad way
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.