Skip to main content
23 events
when toggle format what by license comment
S Dec 15, 2018 at 12:03 history bounty ended Tilen
S Dec 15, 2018 at 12:03 history notice removed Tilen
Dec 15, 2018 at 11:51 comment added Tilen @Björn, are you saying that to determine which predictors are likely drivers of the response, one would either A) fit a pre-specified full model and judge "importance" (yes or no) of predictors based on p-values, or B) use something like AIC to determine which of these predictors of the full model should stay in, but not C) both? Did I get that right? If that is the case, would you opt for A or B to assess which variables seem "important" for the response?
Dec 11, 2018 at 14:53 comment added Tilen @whuber, yes, and that is where my confusion comes from. I was surprised by this choice of "If normal, let's do a GLM, if non-normal, let's do the Wilcoxon instead", which is why I'm asking this question. Chris, I considered that, but I did not wish to publicly call out the authors (also because I know some of them), but rather inquired about the approach itself.
Dec 10, 2018 at 10:15 comment added Björn In addition to the good answers: doing different tests based on outcome of normality tests or naively doing a test on a model buildt using some model selection procedure (e.g. AIC based) invalidates p-values. Using a single pre-specified full model is by far the easiest way to get valid p-values assuming that your model assumptions are correct. If some model selection (whether normality testing, deciding what variables to include etc.) was done, the procedure for getting p-values needs to take that into account. It's possible to do, but requires extra contortions.
Dec 8, 2018 at 14:30 answer added Frank Harrell timeline score: 5
Dec 8, 2018 at 0:15 answer added overdisperse timeline score: 4
Dec 7, 2018 at 21:01 comment added Chris Can you provide a link to the paper?
Dec 7, 2018 at 20:27 comment added whuber I have a hard time seeing how these approaches even address the same problem. A GLM is a regression model (of a conditional response) whereas the Wilcoxon test is a particular hypothesis test of a difference in location and Spearman rank correlation is a descriptive statistic of co-variation! It's a little like asking whether riding a bike or going to the beach are valid alternatives to eating an apple.
Dec 7, 2018 at 20:17 answer added Heteroskedastic Jim timeline score: 9
S Dec 7, 2018 at 18:21 history bounty started Tilen
S Dec 7, 2018 at 18:21 history notice added Tilen Draw attention
Jul 25, 2017 at 22:43 history tweeted twitter.com/StackStats/status/889979447025299456
Mar 27, 2017 at 12:18 history edited Tilen CC BY-SA 3.0
edited title
Mar 27, 2017 at 12:05 history edited Tilen CC BY-SA 3.0
Edited the title, to make it clearer
Mar 17, 2017 at 11:00 review Suggested edits
Mar 17, 2017 at 11:59
Mar 17, 2017 at 10:24 history edited Tilen CC BY-SA 3.0
deleted 4 characters in body
Mar 17, 2017 at 9:44 history edited Tilen
edited tags
Mar 17, 2017 at 9:32 history edited Tilen CC BY-SA 3.0
Corrected minor inconsistencies, clarified the questions.
S Mar 17, 2017 at 9:04 history edited F. Tusell CC BY-SA 3.0
deleted unrelated questions etc. in the bodytext . changed tags
S Mar 17, 2017 at 9:04 history suggested user10619 CC BY-SA 3.0
deleted unrelated questions etc. in the bodytext . changed tags
Mar 17, 2017 at 7:11 review Suggested edits
S Mar 17, 2017 at 9:04
Mar 16, 2017 at 18:43 history asked Tilen CC BY-SA 3.0