Week12-Hypothesis+testing+_+ChiSquare+_+Regression

# Week12-Hypothesis+testing+_+ChiSquare+_+Regression - Week...

This preview shows pages 1–8. Sign up to view the full content.

Week 12 (Chap. 15, 16) Review on Elaboration Model Hypothesis Testing Chi-Square and Regression GSS Lab 1

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

View Full Document
2 Preliminary Hypothesis Testing Bivariate analysis : assess the relationship between two variables. Attitude toward Capital Punishment Gender Men Women Favor 75.3% (865) 63.5% (899) Oppose 24.7% (284) 36.5% (517) Total 100% 100% N 1149 1416 Attitude toward capital punishment by Gender, 2000 GSS “Do you favor or oppose the death penalty for persons convicted of murder Independent variable: column (Top) Dependent variable: row (Side) Compute percentages in the direction of independent variable “Percentage down” N= Total sample size excluding missing cases = Valid cases
3 Attitude toward Capital Punishment Gender Men Women Favor 75.3% (865) 63.5% (899) Oppose 24.7% (284) 36.5% (517) Total 100% 100% N 1149 1416 Attitude toward capital punishment by Gender, 2000 GSS “Do you favor or oppose the death penalty for persons convicted of murder Independent variable: column > Gender Dependent variable: row > Attitude toward DP Q. Does gender influence attitude toward death penalty? A: We compare the 75.3% with the 63.5% and note that men are more likely than women to favor DP.

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

View Full Document
4 Men Women Weekly 25% 34% Less than often 75% 66% Total N 100% (901) 100% (1134) Church attendance reported by Men and Women in GSS(1996) Test whether gender (IV) affect the frequency of church attendance (DV) Reading 1) “Of the women, only 34 percent attended church weekly, and 66 percent said they attended less often; therefore, being a women makes you less likely to attend church frequently.” (INCORRECT!) Reading 2) “Compared to only 25 percent of men, 34% of women attended church weekly; women are more likely to attend church weekly than men.”(CORRECT!) Thus, GENDER appears to be one of the causes of church attendance.
5 Bivariate Relationship 1.Nominal or Ordinal: Cross-tabulation 2. Interval or ratio variable: Scatterplot > Correlation Subject # Experience in Years Income in Thousands 1 0 20 2 5 30 3 5 40 4 10 30 5 10 50 6 15 50 7 20 60 8 25 50 9 30 70 10 35 60 The correlation between years of work experience and yearly income

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

View Full Document
6 Elaboration paradigm Partial relationships compared with original Test (control) variable Antecedent Intervening Same relationship Replication None or Less Explanation Interpretation Split (one is same or greater, other is less or none) Specification Intervening Test Variable Independent variable → Test variable → Dependent variable Antecedent Test Variable Independent variable Test variable Dependent variable
7 Replication : The partial relationship are essentially the same as the original relationship The observed relationship persists across categories of the control variable Never Married Ever Married Very Happy 50% 80% Not too happy 50% 20% Total N 100% (100) 100% (100) Percent happiness by marital status (Bivariate) Young Old Never Married Ever Married Never Married

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 11/20/2011 for the course SOCIOLOGY 920:311 taught by Professor Phillips during the Fall '10 term at Rutgers.

### Page1 / 25

Week12-Hypothesis+testing+_+ChiSquare+_+Regression - Week...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online