Dear professors,
I am a Phd student at the University of Paris VIII and I am working on financial issue in a panel data. I've come to use the multiple imputation for my
missing data and I've been very interested in your method.
Since I was working with R, I installed your Amelia II Package which has perfectly worked for my case. However, when I started to look closely to the values imputated I realised
that the method has replaced the missing values with negative ones which in my case was non significant and non relevant. Beside the negative issue,
I have some problem with variable ranging between 0 and 1. Indeed, I have a variable wich representes a percentage but when imputated, the missing values exceed the number 1 which is wierd.
Could you have the kindness to enlighten me of a possible solution to these two problems, knowing that by adding in the
command ( ords ="X5", p2s = 0), the
negative value disappear and the imputed data for X5 are numeric
a.out<- amelia(Mydata, m = 5, ts = "year", cs = "id", ords ="X5", p2s = 0).
This constraint (ords ="X5", p2s = 0) in the command is correct!! Thank you in advance for your answer.
Best regards
Mouna kessentini