2
$\begingroup$

Was the randomization successful in the table below? Why or why not? and How does one get to know this? enter image description here

$\endgroup$
5
  • 1
    $\begingroup$ What do you mean by "successful"? $\endgroup$ Jun 22 at 7:03
  • 3
    $\begingroup$ This is a perfectly reasonable question. I don't think it should be closed. My reaction was: You are not given the right information to judge this. This kind of baseline table with "tests of baseline homogeneity" on some pre-intervention covariates (we don't even know whether in this case they are prognostic for the outcome of interest) is known to be of no particular value (the linked paper is a useful one to study) for judging the randomization. Sure, it's useful for telling you what the type of students in the study was. $\endgroup$
    – Björn
    Jun 22 at 7:17
  • 2
    $\begingroup$ You would judge a randomization based on how it was implemented (e.g. some methods are better than others: envelopes that one can try to peak into to find out what comes next are more problematic than a computer system where you cannot know beforehand, alternating assignment would not be a proper method of randomization etc.) $\endgroup$
    – Björn
    Jun 22 at 7:17
  • 1
    $\begingroup$ and what you know on how it went (e.g. if we know that people violated the instructions that were to be followed and assigned a different intervention than the one the randomization said, a computer system assigning groups randomly may have malfunctioned, in a non-blinded study people may have withdrawn consent to participate after finding out what group they are in etc.). $\endgroup$
    – Björn
    Jun 22 at 7:17
  • $\begingroup$ @Björn More detail is of course possible, but I think your comments would make for a reasonable answer even with no additions. $\endgroup$
    – mkt
    Jun 22 at 19:35

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.