If two regressions use different sets of observations, then we can tell how the R-squareds will compare, even if one regression uses a subset of regressors.

Question

If two regressions use different sets of observations, then we can tell how the R-squareds will compare, even if one regression uses a subset of regressors.​

Quizplus · Accepted Answer

It is not possible to compare the R-squareds of two regressions that use different sets of observations, as the overlap of observations is important for calculating the variance of the dependent variable. Additionally, the use of different subsets of regressors can also affect the R-squared. Therefore, without a common set of observations and regressors, we cannot compare the R-squareds of two regressions.

If Two Regressions Use Different Sets of Observations, Then We