Partial Correlations with Missing Data

[student1234]

I have a dataset with incomplete/missing data and want to perform partial correlations in R. I realise that pcor.test does not allow missing data and partial.r does not show p-values of correlation coefficients. Is there any other command for partial correlations that
a) allows missing data AND
b) provides p-values?

Thanks a lot!

 

[hlsmith]

Does partial.r just perform listwise deletion of you the row that the missing value is in. I would imagine this may be the scenario. You can always delete out those row and test if this is what happens.

How much missing data do you have? Imputation may be any option as well.

 

[student1234]

Thank you for your reply! I think I do have a considerable amount of missing data. Both the solutions you mentioned sound good and I'll definitely try it out again. Thank you!

 

[hlsmith]

Depending on the source of missingness - imputation may be a possibility as well.