4. Run the same regression as in item 2 but do not include log GDP per capita. What do you find? (Is democracy statistically significant?) Why do you think the results change?

5. Now open the sheet called variability. Run the regression that includes the standard deviation of ladder by country-year but does not include social support. (see WHR 2017 https://worldhappiness.report/ed/2017/for discussion of this variable on page 34 in section called "how does inequality affects the social foundations of happiness"). What does this variable measure? Describe your results.

Table 2.1: Regressions to Explain Average Happiness across Countries (Pooled OLS) Dependent Variable Cantril Ladder Positive Affect Negative Affect Cantril Ladder Independent Variable (0-10) (01) (01) (0-10) Log GDP per capita 0.31 -.009 0.008 0.324 (0.066)*\" (0.01) (0.008) (0.065)m Social support 2.362 0.247 -.336 2.011 (0.363)m (0.048)m (0.052)m (0.389)m Healthy life expectancy at birth 0.036 0.001 0.002 0.033 (0.01)'\""' (0.001) (0.001) (0.009)\" Freedom to make life choices 1.199 0.367 -.084 0.522 (0.298)m (0.041)m (0.04)\" (0.287)\" Generosity 0.661 0.135 0.024 0.39 (0.275)\" (0.03)m (0.028) (0.273) Perceptions of corruption -.646 0.02 0.097 -.720 (0.297)\" (0.027) (0.024)"'""" (0.294)" Positive affect 1.944 (0.355)m Negative affect 0.379 (0.425) Year fixed effects Included Included Included Included Number of countries 156 156 156 156 Number of obs. 1627 1624 1626 1623 Adjusted R-squared 0.751 0.475 0.3 0.768 Notes: This is a pooled OLS regression for a tattered panel explaining annual national average Cantril ladder responses from all available surveys from 2005 to 2019. See Technical Box 1 for detailed information about each of the predictors. Coefficients are reported with robust standard errors clustered by country in parentheses. m, ". and * indicate significance at the 1, 5 and 10 percent levels respectively