search

wikpur / Spacial-Econometrics-Project

Creative Commons Zero v1.0 Universal
0 stars 0 forks source link

Only avgsal is significant #24

Open MPaw18 opened 2 months ago

MPaw18 commented 2 months ago

https://github.com/wikpur/Spacial-Econometrics-Project/blob/f12e530994bb4025f811a1ba6b30d68c48c33c41/Spacial-Econometrics-Project.Rmd#L358

@rsbivand

rsbivand commented 2 months ago

Yes, but this is the same as:

> summary(lm_obj_pre)

Call:
lm(formula = form_pre, data = wpom3)

Residuals:
       Min         1Q     Median         3Q        Max 
-0.0025977 -0.0014165 -0.0001195  0.0007647  0.0048454 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)  
(Intercept)  -1.366e-02  8.178e-03  -1.670   0.1156  
log(density)  1.391e-03  7.328e-04   1.898   0.0771 .
avgsal        3.619e-06  1.501e-06   2.411   0.0292 *
unemp         1.041e-04  2.336e-04   0.446   0.6622  
ssusers      -2.252e-04  6.002e-04  -0.375   0.7128  
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.00222 on 15 degrees of freedom
Multiple R-squared:  0.785, Adjusted R-squared:  0.7276 
F-statistic: 13.69 on 4 and 15 DF,  p-value: 6.786e-05

Do you have an economic model expecting the crime rate to vary with the other explanatory variables? Maybe ssusers and unemp are irrelevant? Maybe creating the rate by population is misleading, as criminals do not necessarily commit crimes where they live?