Lab4_Curvilinear Regression

# Lab4_Curvilinear Regression - EXST 7015 Statistical...

This preview shows pages 1–2. Sign up to view the full content.

EXST 7015 - Statistical Inference II, Fall 2011 Lab 4: Curvilinear Regression--Log Transformation OBJECTIVES Simple linear regression (SLR) is a common analysis procedure used to describe the significant relationship between two variables in such a manner that one variable can be predicted or explained by using information on the other. By using PROC REG and PROC UNIVARIATE, we learned how to evaluate the SLR model comprehensively through interpreting ANOVA table, R^2, parameter estimates, residual plot, normality test and diagnostic statistics. However, many systems encountered in research are curvilinear relationships instead of simple linear relationships. Luckily, many curvilinear relationships may be expressed in linear relationships. During last a couple of labs, you might be aware that heterogeneity of variance is a common violation of one of the assumptions of linear regression, which assumes a constant variability about the regression line. If the variability increases as the values of the predicted value increases then certain transformations are applied. Among the choices are the log, square root, and reciprocal transformations. Usually the need for one of these transformations is determined by examining the residual plot. If the residual plot is fan shaped then heterogeneity of variance is assumed. Log transformation is the most commonly used to alleviate a problem with heterogeneity of variance. Using log transformation implies underlying relationship is

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 12/29/2011 for the course EXST 7015 taught by Professor Wang,j during the Fall '08 term at LSU.

### Page1 / 3

Lab4_Curvilinear Regression - EXST 7015 Statistical...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online