Dear all, I have a question about estimation in two phases sampling. I' have a first sample of household from a complex sampling S1, a second sample is drawned from S2. from S2, I compute an estimator y2, for households of S1 not in S2 I set y2=0. I have an estimator y1 on S1 My indicator is y=y1+y2. So the variance of y is v(y)=v(y1)+v(y2)+cov(y1,y2). Sampling theory indicate how to compute v(y1) and v(y2) but how can I compute cov(y1,y2) ? Can the survey package help me for that ? Justin BEM BP 1917 Yaoundé Tél (237) 76043774 [[alternative HTML version deleted]]