# Thread: ANOVA with multiple imputed Data

1. ## Re: ANOVA with multiple imputed Data

Originally Posted by spunky
If this is any exam project, didn't they teach you in school how do to it then before they let you do it yourself? I'm just wondering if maybe you have something on your notes on how do to this stuff and then you won't need to switch software or anything.

Its for my master thesis but its not a "usual" thesis, its in a kind of free research project. We got told the basics but I faced some missing values and used MI which was not told in the courses...

2. ## Re: ANOVA with multiple imputed Data

Originally Posted by froop91
Its for my master thesis but its not a "usual" thesis, its in a kind of free research project. We got told the basics but I faced some missing values and used MI which was not told in the courses...
Well... to be honest, if you're not very familiar with a somewhat complex method like Multiple Imputation, I'd see more value as a professor in you (a) acknowledging that this is a limitation of your research question and (b) mentioning that you researched potential solutions. Running Multiple Imputation it's not just a point-and-click type of analysis. You need to check to see whether your MCMC chains or imputation algorithm converged properly and run some imputation diagnostics. You'll probably want to calculate and report the fraction of missing information statistic and comment on whether or not that could influence your results (i.e. if it is high then you're mostly modelling the imputation as opposed to the actual data). And that's just off the top of my memory of the things you'd need to check. I know there are more but it's a Saturday here and my brain doesn't want to work.

So...yeah. I guess the overall recommendation here is to proceed cautiously if you have never learned how to do this.

3. ## The Following User Says Thank You to spunky For This Useful Post:

ondansetron (09-09-2017)

4. ## Re: ANOVA with multiple imputed Data

If all else fails, you can run it as a General Linear Model using the original data then imputation is not needed.

5. ## Re: ANOVA with multiple imputed Data

Agreed Katxt, if they weren't so darn close to just doing it. They have the formula and everything!

I would wonder what the trade-off would be for "power". Using missing data, their sample size will be smaller, but if the use MI their SE will be larger. Though, it always seems statisticians like to say do the MI. But knowing the source of missingness always seems dubious like specifying a model close enough to work with the data generating process and its probability distribution.

6. ## Re: ANOVA with multiple imputed Data

Yes, you don't get anything for nothing. It's hard to see how you can get more accurate results just by making up more data that summarizes the data you already have. With imputation you need to reduce the error df anyway, so your sample size isn't really any smaller with the GLM (I think.)

7. ## Re: ANOVA with multiple imputed Data

I tried to get in depth knowledge of the topic. I also calculate with not imputet data (e.g. listewise deletion) to compare the findings...

8. ## Re: ANOVA with multiple imputed Data

Originally Posted by katxt
If all else fails, you can run it as a General Linear Model using the original data then imputation is not needed.
This is me being curious here. When you say "run it as a GLM" do you mean re-phrasing the problem as an unbalanced groups design (where the missingness implies factors with an unequal number of participants) or do you mean running a linear mixed effects model that can naturally handle unbalanced groups?

9. ## Re: ANOVA with multiple imputed Data

I mean an unbalanced two way anova with subject as a factor which you then ignore. You may need to be careful in the interpretation, but hopefully the missing data is random and not too many points.

10. ## Re: ANOVA with multiple imputed Data

Thanks for all your help, guys

I used a makro provided by van Ginkel (https://www.universiteitleiden.nl/en...n-ginkel#tab-1) to do the calculations.

Have a nice day everybody!