8.25 Murders and poverty, Part I.
The following regression output is for predicting annual murders per million from percentage living in poverty in a random sample of 20 metropolitan areas. Estimate Std. Error t value Pr(>jtj) (Intercept) -29.901 7.789 -3.839 0.001 poverty% 2.559 0.390 6.562 0.000 s = 5.512 R2 = 70.52% R2adj = 68:89%
Solution
- Write out the linear model.
- Linear Model, \(AnnualMurders(perMillion) = 2.559\times poverty\% - 29.901\)
- Interpret the intercept.
- If There is no poverty, the Expected murders in the cites will be -29.901 This value does not make any sense. It just serves to ajust the height of the regression line.
- Interpret the slope.
- When there is an increase in poverty percentage of 1%, the expected number of murders per million increase of 2.556.
- Interpret R2.
- Poverty level explains 70.52% of the variability in murder rates in metropolitan areas.
- Calculate the correlation coefficient.
- correlation coefficient \(r=\sqrt{R^2}\)
sqrt(.7052)
## [1] 0.8397619
The correlation coefficient is 83.98%