EconometricanalysisLinearLeastSquares幻灯片.pptVIP

* * * * * * * * * * * * * * * * * * * * Partitioned Solution Method of solution (Why did FW care? In 1933, matrix computation was not trivial!) Direct manipulation of normal equations produces b2 = (X2?X2)-1X2?(y - X1b1) What is this? Regression of (y - X1b1) on X2 Important result (perhaps not fundamental). Note the result if X2?X1 = 0. Useful in theory: Probably Likely in practice? Not at all. Partitioned Inverse Use of the partitioned inverse result produces a fundamental result: What is the southeast element in the inverse of the moment matrix?