Timeline for Is excluding cases with missing data fine for a predictive (not explanatory/descriptive) model?
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 2, 2018 at 15:57 | comment | added | AdamO | @user86895 MCAR/MAR doesn't matter: multiply impute or weight the data or exclude to complete cases if you have adequate power. NMAR means your data are critically flawed and no fancy schmancy methods can save you from that. | |
| Mar 2, 2018 at 15:53 | comment | added | ReneBt | Thanks for the suggestions @AdamO, user86895 and JWH2006. I think they strengthen the answer quite a bit. If its still unclear which solutions work with which type of missingness I'll try and put something clearer together. | |
| Mar 2, 2018 at 15:51 | history | edited | ReneBt | CC BY-SA 3.0 |
In response to initial comments, I have updated the answer to provide more examples of situations that may cause the types of missingness and also to give some opinion on the implications of the different solutions depending on the presence or absence of bias
|
| Mar 2, 2018 at 15:41 | history | edited | ReneBt | CC BY-SA 3.0 |
In response to initial comments, I have updated the answer to provide more examples of situations that may cause the types of missingness and also to give some opinion on the implications of the different solutions depending on the presence or absence of bias
|
| Mar 1, 2018 at 21:12 | vote | accept | Sam Weisenthal | ||
| Mar 1, 2018 at 21:12 | |||||
| Mar 1, 2018 at 20:45 | comment | added | JWH2006 | The above is a very nice explanation. I will also add that another way to deal with missing data is to mean code missing values. This preserves power compared to listwise deletion. That being said, if you are facing a large portion of your data having missing values, its probably time to bring out the big guns: multiple imputation and maximum likelihood estimation. | |
| Mar 1, 2018 at 20:40 | comment | added | Sam Weisenthal | Thank you--still confused. Can you give a scenario where you are bulding a predictive model and data are mcar and what you might do, mar and what you might do, and mnar and what you might do, and for each case explain why simply removing cases with missing x is not preferable? | |
| Mar 1, 2018 at 15:42 | comment | added | AdamO | (+1) Really nice discussion. It's worth pointing out that imputation does not confer much practical advantage over complete case analysis in most settings, except for boosting the power and effective sample size slightly. | |
| Mar 1, 2018 at 15:17 | history | answered | ReneBt | CC BY-SA 3.0 |