Test can also be used for other expected frequency

Info icon This preview shows pages 13–21. Sign up to view the full content.

View Full Document Right Arrow Icon
Test can also be used for other expected frequency distributions. i.e., not just normal distribution
Image of page 13

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

View Full Document Right Arrow Icon
Chapter 11: Goodness of Fit and Contingency Analysis Method to determine if a truly significant difference exists between observed and expected frequencies i.e., as per K-S Goodness-of-Fit Use: testing to see if a model produces frequency counts (i.e., a distribution) that reflects reality e.g., see textbook p. 160: spatial interaction models Know the purpose of the test Not responsible for solving (stick with Test #1) Test #2: CHI-Square Goodness-of-Fit
Image of page 14
Chapter 11: Goodness of Fit and Contingency Analysis Test # 3: Contingency Analysis
Image of page 15

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

View Full Document Right Arrow Icon
Chapter 11: Goodness of Fit and Contingency Analysis Different from tests 1 and 2 in Ch. 11 Tests 1 # 2: used for testing an observed against an expected frequency distribution i.e., single variable goodness-of-fit Contingency Analysis: testing two variables to see if their distributions are the same This answers the question: are two variables statistically independent? Variables are organized into nominal or ordinal categories and frequency counts used. Test #3: Contingency Analysis
Image of page 16