STAT 4444 Study Guide - Final Guide: Simple Linear Regression, Maximum Likelihood Estimation, Dependent And Independent Variables

71 views2 pages

Document Summary

Lecture 16: linear regression with the frequentist approach. Class business: homework iv is due on april 17 at 11:59 p. m. The population simple linear regression equation takes the form yi = 0 + 1xi + i. 1 assumptions: linearity (needed for proper tting, the errors follow a normal distribution with mean zero and variance 2. This is required for inference (e. g. , con dence intervals, hypothesis testing). In simple linear regression, we have three parameters that need to be estimated and make inference about: 0, 1, and 2. In some cases, the y-intercept, 0 does not make sense. For example, if y is the price of a house and x is the square footage of the house, 0 is the average house price when the square footage is zero. In such cases, a common practice is to center x before using sample data to estimate the regression coe cients and variance. The centered model take the form yi = .