ISDS 2000 Chapter : Chapter 14 Outline Section 1 Updated 0810
Document Summary
Chapter 14: multiple linear regression: introduction, in chapter 13, we considered simple linear regression. In particular, we had one explanatory/independent variable (x) for purposes of predicting one response/dependent variable (y): in real life, we are usually faced with a situation where one response variable can be explained by more than one predictor. In this case, we use multiple regression analysis: examples, we will also stress that the purpose of regression is prediction; correlation is for measuring the strength of the relationship between y and multiple x"s. Developing the multiple regression model: multiple linear regression model. K = population slope for xki , sometimes called partial regression coefficients. Y = bo + b1x1i + b2x2i + + bkxki i i. Y = predicted value of y bo = sample intercept bk are the sample slopes where for obs i: least squares criteria for estimating o and k"s, goal is to get one best equation that fits the data.