In: Statistics and Probability
Use this regression model I created to answer this question:
1. Interpret the slope estimates in this model, interpret the impact of Income on U5MR, and interpret the R2[square].
Regression Statistics | ||||||||
Multiple R | 0.443 | |||||||
R Square | 0.197 | |||||||
Adjusted R Square | 0.190 | |||||||
Standard Error | 35.125 | |||||||
Observations | 132 | |||||||
ANOVA | ||||||||
df | SS | MS | F | Significance F | ||||
Regression | 1 | 39247.449 | 39247.449 | 31.811 | 1.013E-07 | |||
Residual | 130 | 160390.937 | 1233.776 | |||||
Total | 131 | 199638.386 | ||||||
Coefficients | Standard Error | t Stat | P-value | Lower 95% | Upper 95% | Lower 90.0% | Upper 90.0% | |
Intercept | 53.509 | 3.733 | 14.336 | 1.5E-28 | 46.124 | 60.893 | 47.325 | 59.692 |
4090 | -0.002 | 0.000 | -5.640 | 1E-07 | -0.002 | -0.001 | -0.002 | -0.001 |
Use this regression model I created to answer this question:
## 1. Interpret the slope estimates in this model, interpret the impact of Income on U5MR, and interpret the R2[square].
Answer : slope estimates is - 0.002
it is negative as 4090 (or x ) value increases by 1 unit y value decreases as - 0.002 units .
it is affect to the predict y value , but as it is very small it will impact but not much .
# R square = coefficient of determintion : = 0.197
variation explained by model is 0.197 that is 19.7 %
If R squared value is < 0.3 ie 30 % this value is generally considered a None or very weak effect size
our R square value is < 0.3 hence it is consider as very weak effect size .