Happiness study

This study investigates urban-rural difference in (global) happiness. Data for the analysis

came from the 2008 China’s General Social Survey (CGSS), conducted by the Survey Research

Center at the Renmin University of China. The 2008 CGSS is a national survey of Chinese

adults, including a nationally representative sample of 6,000 people. For the purpose of

this assignment, the study sample is limited to respondents who were aged 20-59 (N =

4,718). The data, assignment1.dta, are posted on the class email server.

The Exercise.

1. Fit a logistic regression model using “d3” (1 = happy or very happy,

0 otherwise) as the dependent variable and place of residence (with rural

residence as the reference category) as the independent variable, and interpret

the residence coefficient in terms of odds ratios.

2. In model 2, add controls for age, sex, marital status, education, family

income, and self-reported health. Construct a 95% confidence interval for the odds

ratio comparing urban and rural residents.

3. In model 3, test the hypothesis that the effect of place of residence varies

depending upon education.