12Май
10 4: The Least Squares Regression Line Statistics LibreTexts
In other words, \(A\hat x\) is the vector whose entries are the values of \(f\) evaluated on the points \((x,y)\) we specified in our data table, and \(b\) is the vector whose entries are the desired values of \(f\) evaluated at those points. The difference \(b-A\hat x\) is the vertical distance of the graph from the data points, as indicated in the above picture. The best-fit linear function minimizes the sum of these vertical distances. The least squares method is...
