[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: missing value imputation in Fixed Effects GLS model
I have a cross-sectional time series data (country by year) for the time
span from 1965 to 1995, which is to be analyzed by Fixed Effects GLS model.
One of the independent variables I use is Gini Coefficients. Since Gini
coefficients are not available, I measured it focuing on two years, circa
1970 and circa 1985 and am useing them as time-invariant covariates (say,
the circa 1970 measure for the period 1965-1975, and the circa 1985 for the
period 1976-1995). Unfortunately, this variable still has a substantial
number of missing values, forcing me to drop them from analysis.
So, my question is whether it is possible to use "missing values imputation"
for the Fixed Effects GLS model, and if it is, how can I do it?
I'd appreciate any of your suggestions on this matter.
Assistant Professor of Sociology
University of Washington
202 Savery Hall, Box 353340
Seattle, WA 98195-3340
* For searches and help try: