garym wrote: > I can't put my hands on the research right now, but I recall seeing > papers that suggest in testing using multiple choice questions, there > are group biases exhibited in choosing certain answer options (A, B, C, > D, etc.). He couldn't easily do this in this study, but had he been > doing this study in a context where he had some control over the subject > pools, he would have given half the subjects the test samples labled A, > B and the other half the labels would have been B,A. Then in his tests, > he could confirm that the order of the choices (A,B) did not interact > with the variable of interest (coding method).
Is this similar to that on test with tick boxes people want to tick somewhere in the middle , so you shuffle the position for questions and have variants of the tests ------------------------------------------------------------------------ Mnyb's Profile: http://forums.slimdevices.com/member.php?userid=4143 View this thread: http://forums.slimdevices.com/showthread.php?t=98010 _______________________________________________ audiophiles mailing list audiophiles@lists.slimdevices.com http://lists.slimdevices.com/mailman/listinfo/audiophiles