Issue with missing data

[lucas111]

Hi all,

I am working on a dataset that include 12K+ firm-level data for 30+ countries. I have both firm-level variables (each firm within country has unique data) and country-level variables (each firm belonging to a given country gets the same value). For some country-level variables, the data for some countries are not available. Should I erase these countries from my dataset? (I use Stata)

Thanks in advance for your help!

 

[chiro]

Hey lucas111.

The answer to questions like these will depend on the data set and the nature of the analysis. Sometimes, missing values are not that important and sometimes they are: there is no one answer. This is the same as outliers: they need to be considered in relation to what you are trying to do and what you are trying to answer.

 

[lucas111]

Thanks Chiro. Much appreciated!

 

[Lazar]

Have you considered imputing the missing values? http://sites.stat.psu.edu/~jls/mifaq.html

 

[lucas111]

Great link Lazar ... many thanks!