spring2013stat202-lecture10 - Lecture 10 Wed Feb 6 36-202...

Info icon This preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 10 36-202 Wed, Feb. 6 Spring 2013 This document is available on: http://www.cmu.edu/blackboard (under ‘course content’) Including Categorical Variables in the Regression Model [Reserve Material Reference: Section 13.5, “How Can Regression Include Categorical Predictors,” of Statistics by Agresti and Franklin)] Up to this point, we have seen how to build, test, and use regression models involving several predictor variables; but all those variables were quantitative. But often, there are also categorical variables that we want to include in the prediction model. Example 1 (including a categorical variable with just 2 levels) . Salary data was available on from around 100 executives from Towers, Perrin, Foster, & Crosby (an international management consulting firm). We want to explain the variability in the executives’ salary. Salary ($) Experience (yrs) Gender Gender(c) 1 93300 12 M 1 2 130000 25 M 1 3 88200 20 F 0 4 74400 3 M 1 5 115300 19 M 1 6 70400 14 F 0 7 114200 18 M 1 8 72600 2 M 1 9 108600 14 M 1 10 68600 4 M 1 11 102000 8 M 1 12 101400 19 M 1 13 149400 23 M 1 14 57100 5 F 0 15 87400 3 M 1 16 131000 22 M 1 17 90300 24 F 0 18 115600 22 M 1 19 102800 13 M 1 20 141900 21 M 1 Questions: 1. Is there a significant linear relationship between Salary and Experience? 2. How can we determine if there’s a gender effect?
Image of page 1

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

View Full Document Right Arrow Icon