Timeline for Multilevel MIXED Linear Regression with pseudo-repeats: Why designate "Repeated' variables, while "Subject ID" already identifies all repeats?
Current License: CC BY-SA 4.0
23 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 22, 2024 at 11:06 | answer | added | BenP | timeline score: 1 | |
| S Jan 21, 2024 at 23:06 | history | bounty ended | CommunityBot | ||
| S Jan 21, 2024 at 23:06 | history | notice removed | CommunityBot | ||
| Jan 21, 2024 at 13:37 | answer | added | BenP | timeline score: 3 | |
| Jan 19, 2024 at 19:25 | answer | added | Sointu | timeline score: 2 | |
| Jan 19, 2024 at 11:07 | history | edited | Vic | CC BY-SA 4.0 | clarified my concerns regarding the complexities and intricacies of handling REPEATED variables in a multilevel mixed regression. Mostly moved the content from the end of my post to the top of it. |
| Jan 17, 2024 at 9:56 | answer | added | PBulls | timeline score: 6 | |
| Jan 13, 2024 at 21:34 | history | edited | Vic | CC BY-SA 4.0 | added 382 characters in body |
| S Jan 13, 2024 at 21:33 | history | bounty started | Vic | ||
| S Jan 13, 2024 at 21:33 | history | notice added | Vic | Canonical answer required | |
| Jan 11, 2024 at 8:17 | comment | added | Sointu | Just a practical comment as a former SPSS user who has moved to R: in my experience, these things are only confusing when you try to use SPSS. SPSS "repeated" box is among the most confusing things I've ever encountered. | |
| Jan 10, 2024 at 23:11 | answer | added | AdamO | timeline score: 4 | |
| Jan 10, 2024 at 21:05 | history | edited | Vic | CC BY-SA 4.0 | added 6 characters in body |
| Jan 10, 2024 at 20:55 | history | edited | Vic | CC BY-SA 4.0 | added 5 characters in body |
| Jan 10, 2024 at 20:47 | history | edited | Vic | CC BY-SA 4.0 | added 5 characters in body |
| Jan 10, 2024 at 20:40 | comment | added | Vic | @AdamO the main reason I enter left/right as Repeated is not that I even care about the difference between left and right sides in hands, feet, etc. That might be a very weak reason too, but not the main reason. The main reason to model laterality is to 1) just account for the dependence pf the left/right observations and avoid pseudocorrelation and inflated type I error, while 2) at the same time not averaging the left/right sides and thus not losing precious data. The end of your comment was very good. So mixed models ARE bewildering and vague, at times. BTW, I edited my post. | |
| Jan 10, 2024 at 20:28 | history | edited | Vic | CC BY-SA 4.0 | added 1045 characters in body; edited title |
| Jan 10, 2024 at 20:26 | comment | added | AdamO | If you truly believed left/right were replications, then they don't need any effect at all. This is, of course, not true. The point of specifying left/right effects is because you might believe that if subject A's left arm is longer than their right, their left leg would be longer too. The number of possible permutations of random effects specifications is just too high to deal with. So much so that many analyses fit a variety of models and just pick the one with the best AIC and call it done. | |
| Jan 10, 2024 at 20:03 | comment | added | Vic | The scenario was totally imaginary. I made it up to serve my needs regarding understanding 'what to consider repeated' in mixed models. So yes, my question is not really about SPSS. I am bewildered by mixed-models, especially multilevel ones. I have difficulty understanding which variables should be considered REPEATED within a mixed model context, and Why. In a classical sense, where repeated measurements are literally repeated, it is easy. But in a left/right laterality example, this becomes convoluted. You know. left and right are NOT real repetitions of each other; yet, sort of are. | |
| Jan 10, 2024 at 19:58 | comment | added | Vic | @AdamO if you double-check, I did talk about nesting ["... and nest them within the SUBJECT variable..."]. Regarding duplication, this is not a duplicated question, given its various aspects, questions, etc. Regarding your answer, thanks that helps, though I would love to receive complete answers to my exact questions. BTW, amputees would be consider missing data in this example. | |
| Jan 10, 2024 at 19:56 | comment | added | AdamO | your question then is not about SPSS, but rather the correct random effect structure to facilitate inspection of morphological differences in a sample of people of a variety of races? | |
| Jan 10, 2024 at 19:48 | comment | added | AdamO | Not a lot of SPSS users on this site, but if we ignore the software, this question is a duplicate of: stats.stackexchange.com/questions/228800/…. In other words, it's possibly not enough to just say that Subject and Laterality are random effects. These are nested effects, and you need to tell SPSS this so it estimates Subject level variation and then estimates variation due to laterality after. Having a balanced design helps (but amputees in the dataset could imply large differences). | |
| Jan 10, 2024 at 19:13 | history | asked | Vic | CC BY-SA 4.0 |