## [1] "Visualize distribution of outcome variables"
print("Percentage of missing values by column and in DF- ")
## [1] "Percentage of missing values by column and in DF- "
100*(colSums(is.na(dfSample)) / nrow(dfSample))
## state year entered entryRt child
## 0.00 0.00 0.00 0.00 0.00
## agedout fcPop agedRt LessHS foodIns
## 0.00 0.00 0.00 0.00 0.00
## unempRt singPar chpovRt gspPc policy_updated
## 0.00 0.00 0.00 0.00 0.00
## crimeRt pctBlk pctHis tanf3fam mediPpl
## 0.00 0.00 0.00 0.00 0.00
## snapPpl tanfPpl welfarePc incarRt deathRt
## 0.00 0.00 0.25 0.00 0.25
## policePc
## 0.25
(sum(is.na(dfSample))/prod(dim(dfSample)))*100
## [1] 0.02884615
dfSample <- na.omit(dfSample)
scaled <- scale(dfSample[c(9:26)])
dfSample_scaled <- cbind(dfSample[c(1:8)],scaled)
dfSample_scaled$year_c <- dfSample_scaled$year - 2004
obsN=1:nrow(dfSample_scaled)
enterModel <- glmer(entered ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc + policy_updated + crimeRt + pctBlk + tanf3fam + snapPpl + mediPpl + tanfPpl*welfarePc + incarRt + deathRt + policePc + (1 | state) + (1 | year_c) + (1 | obsN), offset=log(child),data=dfSample_scaled,family=poisson)
summary(enterModel)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: poisson ( log )
## Formula: entered ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc +
## policy_updated + crimeRt + pctBlk + tanf3fam + snapPpl +
## mediPpl + tanfPpl * welfarePc + incarRt + deathRt + policePc +
## (1 | state) + (1 | year_c) + (1 | obsN)
## Data: dfSample_scaled
## Offset: log(child)
##
## AIC BIC logLik deviance df.resid
## 12547.7 12650.7 -6251.9 12503.7 774
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -0.86772 -0.07050 0.00174 0.05521 0.59608
##
## Random effects:
## Groups Name Variance Std.Dev.
## obsN (Intercept) 2.251e-02 0.150038
## state (Intercept) 1.005e-01 0.316957
## year_c (Intercept) 2.779e-05 0.005272
## Number of obs: 796, groups: obsN, 796; state, 50; year_c, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.516188 0.045295 -121.783 < 2e-16 ***
## unempRt -0.036678 0.013165 -2.786 0.005334 **
## singPar -0.002707 0.033728 -0.080 0.936040
## foodIns -0.010893 0.009614 -1.133 0.257221
## chpovRt 0.039929 0.022912 1.743 0.081390 .
## LessHS -0.053588 0.024207 -2.214 0.026845 *
## gspPc -0.065049 0.019317 -3.367 0.000759 ***
## policy_updated 0.218737 0.033182 6.592 4.34e-11 ***
## crimeRt 0.033664 0.016983 1.982 0.047460 *
## pctBlk -0.236345 0.048275 -4.896 9.79e-07 ***
## tanf3fam 0.035964 0.024327 1.478 0.139317
## snapPpl -0.058738 0.013627 -4.310 1.63e-05 ***
## mediPpl 0.074239 0.014351 5.173 2.30e-07 ***
## tanfPpl 0.023493 0.011340 2.072 0.038301 *
## welfarePc 0.016663 0.018311 0.910 0.362823
## incarRt 0.048840 0.023001 2.123 0.033718 *
## deathRt 0.023635 0.007701 3.069 0.002148 **
## policePc -0.005718 0.012742 -0.449 0.653638
## tanfPpl:welfarePc -0.000757 0.010063 -0.075 0.940030
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation matrix not shown by default, as p = 19 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need it
agedoutModel <- glmer(agedout ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc + policy_updated + crimeRt + pctBlk + tanf3fam + snapPpl + mediPpl + tanfPpl*welfarePc + incarRt + deathRt + policePc + (1 | state) + (1 | year_c) + (1 | obsN), offset=log(fcPop),data=dfSample_scaled,family=poisson)
summary(agedoutModel)
## Generalized linear mixed model fit by maximum likelihood (Laplace
## Approximation) [glmerMod]
## Family: poisson ( log )
## Formula: agedout ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc +
## policy_updated + crimeRt + pctBlk + tanf3fam + snapPpl +
## mediPpl + tanfPpl * welfarePc + incarRt + deathRt + policePc +
## (1 | state) + (1 | year_c) + (1 | obsN)
## Data: dfSample_scaled
## Offset: log(fcPop)
##
## AIC BIC logLik deviance df.resid
## 9642.4 9745.3 -4799.2 9598.4 774
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.53191 -0.08100 0.00824 0.06868 1.16593
##
## Random effects:
## Groups Name Variance Std.Dev.
## obsN (Intercept) 0.14194 0.3767
## state (Intercept) 0.30739 0.5544
## year_c (Intercept) 0.03999 0.2000
## Number of obs: 796, groups: obsN, 796; state, 50; year_c, 16
##
## Fixed effects:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.708859 0.094409 -39.285 < 2e-16 ***
## unempRt -0.043093 0.045528 -0.947 0.34389
## singPar -0.124493 0.074171 -1.678 0.09326 .
## foodIns -0.003214 0.025801 -0.125 0.90086
## chpovRt 0.157094 0.064580 2.433 0.01499 *
## LessHS -0.096027 0.071896 -1.336 0.18166
## gspPc 0.051015 0.060157 0.848 0.39642
## policy_updated -0.009419 0.086410 -0.109 0.91320
## crimeRt 0.062766 0.045502 1.379 0.16777
## pctBlk 0.030263 0.095750 0.316 0.75195
## tanf3fam -0.082325 0.062092 -1.326 0.18489
## snapPpl 0.063881 0.038824 1.645 0.09989 .
## mediPpl -0.002817 0.042226 -0.067 0.94682
## tanfPpl 0.027445 0.028891 0.950 0.34214
## welfarePc -0.092340 0.045323 -2.037 0.04161 *
## incarRt -0.109581 0.055460 -1.976 0.04817 *
## deathRt -0.074309 0.019765 -3.760 0.00017 ***
## policePc 0.077915 0.043429 1.794 0.07280 .
## tanfPpl:welfarePc 0.060973 0.025795 2.364 0.01809 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation matrix not shown by default, as p = 19 > 12.
## Use print(x, correlation=TRUE) or
## vcov(x) if you need it
dfSample_scaled %>% is.pbalanced()
## [1] FALSE
twfe_entryRt <- plm(log(entryRt) ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc + policy_updated + crimeRt + pctBlk + tanf3fam + snapPpl + mediPpl + tanfPpl*welfarePc + incarRt + deathRt + policePc, data=dfSample_scaled, effect="twoway", model="within", index=c("state","year_c"))
# summary(twfe_entryRt)
par(mfrow=c(1,2))
qqnorm(residuals(twfe_entryRt), ylab = 'Residuals')
qqline(residuals(twfe_entryRt))
hist(residuals(twfe_entryRt), xlab = 'Residuals')
bptest(twfe_entryRt, studentize = F)
##
## Breusch-Pagan test
##
## data: twfe_entryRt
## BP = 117.67, df = 18, p-value < 2.2e-16
pbgtest(twfe_entryRt)
##
## Breusch-Godfrey/Wooldridge test for serial correlation in panel models
##
## data: log(entryRt) ~ unempRt + singPar + foodIns + chpovRt + LessHS + ...
## chisq = 343.55, df = 15, p-value < 2.2e-16
## alternative hypothesis: serial correlation in idiosyncratic errors
coeftest(twfe_entryRt, vcov = vcovHC(twfe_entryRt, method = "arellano", type = "HC0", cluster = "group"))
##
## t test of coefficients:
##
## Estimate Std. Error t value Pr(>|t|)
## unempRt -0.0048323 0.0277689 -0.1740 0.861901
## singPar -0.0379966 0.0576229 -0.6594 0.509852
## foodIns -0.0069413 0.0137136 -0.5062 0.612899
## chpovRt 0.0091827 0.0387251 0.2371 0.812628
## LessHS -0.0653270 0.0715153 -0.9135 0.361305
## gspPc -0.0509728 0.0431756 -1.1806 0.238158
## policy_updated 0.2205517 0.0873422 2.5251 0.011781 *
## crimeRt 0.0229072 0.0412958 0.5547 0.579267
## pctBlk -0.0845178 0.2731381 -0.3094 0.757083
## tanf3fam 0.0368083 0.0897076 0.4103 0.681699
## snapPpl -0.0695715 0.0248446 -2.8003 0.005244 **
## mediPpl 0.0735174 0.0414290 1.7745 0.076400 .
## tanfPpl 0.0156208 0.0260254 0.6002 0.548554
## welfarePc 0.0055500 0.0454819 0.1220 0.902912
## incarRt 0.0477526 0.0583352 0.8186 0.413294
## deathRt 0.0259446 0.0118415 2.1910 0.028776 *
## policePc 0.0245910 0.0380665 0.6460 0.518488
## tanfPpl:welfarePc 0.0037847 0.0245461 0.1542 0.877507
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
twfe_agedRt <- plm(agedRt ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc + policy_updated + crimeRt + pctBlk + tanf3fam + snapPpl + mediPpl + tanfPpl*welfarePc + incarRt + deathRt + policePc, data=dfSample_scaled, effect="twoway", model="within", index=c("state","year_c"))
# summary(twfe_agedRt)
par(mfrow=c(1,2))
qqnorm(residuals(twfe_agedRt), ylab = 'Residuals')
qqline(residuals(twfe_agedRt))
hist(residuals(twfe_agedRt), xlab = 'Residuals')
bptest(twfe_agedRt, studentize = F)
##
## Breusch-Pagan test
##
## data: twfe_agedRt
## BP = 179.94, df = 18, p-value < 2.2e-16
pbgtest(twfe_agedRt)
##
## Breusch-Godfrey/Wooldridge test for serial correlation in panel models
##
## data: agedRt ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc + ...
## chisq = 372.94, df = 15, p-value < 2.2e-16
## alternative hypothesis: serial correlation in idiosyncratic errors
coeftest(twfe_agedRt, vcov = vcovHC(twfe_agedRt, method = "arellano", type = "HC0", cluster = "group"))
##
## t test of coefficients:
##
## Estimate Std. Error t value Pr(>|t|)
## unempRt -0.039305 0.243098 -0.1617 0.871601
## singPar -0.294525 0.353998 -0.8320 0.405690
## foodIns 0.032311 0.077900 0.4148 0.678436
## chpovRt 0.526947 0.177279 2.9724 0.003054 **
## LessHS -0.473083 0.416189 -1.1367 0.256045
## gspPc 0.408244 0.388116 1.0519 0.293220
## policy_updated 0.196969 0.423345 0.4653 0.641882
## crimeRt 0.160232 0.188329 0.8508 0.395159
## pctBlk 1.210939 1.687056 0.7178 0.473127
## tanf3fam -0.019518 0.232787 -0.0838 0.933202
## snapPpl 0.356863 0.211416 1.6880 0.091855 .
## mediPpl 0.073061 0.146890 0.4974 0.619073
## tanfPpl -0.037108 0.216578 -0.1713 0.864007
## welfarePc -0.286048 0.190328 -1.5029 0.133303
## incarRt -0.298342 0.282325 -1.0567 0.290992
## deathRt -0.156446 0.084368 -1.8543 0.064104 .
## policePc 0.060124 0.199692 0.3011 0.763438
## tanfPpl:welfarePc 0.180619 0.108440 1.6656 0.096229 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
r2(enterModel)
## Warning: mu of 0.0 is too close to zero, estimate of random effect variances may
## be unreliable.
## # R2 for Mixed Models
##
## Conditional R2: 0.033
## Marginal R2: 0.016
icc(enterModel)
## Warning: mu of 0.0 is too close to zero, estimate of random effect variances may
## be unreliable.
## # Intraclass Correlation Coefficient
##
## Adjusted ICC: 0.018
## Unadjusted ICC: 0.018
# check for multicollinearity
x <- check_collinearity(enterModel)
plot(x)
## Variable `Component` is not in your data frame :/
# check for singularity
tt <- getME(enterModel,"theta")
ll <- getME(enterModel,"lower")
min(tt[ll==0])
## [1] 0.00527183
# check for overdispersion
check_overdispersion(enterModel)
## # Overdispersion test
##
## dispersion ratio = 0.023
## Pearson's Chi-Squared = 17.867
## p-value = 1
## No overdispersion detected.
# check residuals
par(mfrow=c(1,2))
plot(residuals(enterModel) ~ fitted(enterModel), main = "residuals v.s. fitted")
qqnorm(residuals(enterModel))
# random effects
plot(ranef(enterModel))
## $obsN
##
## $state
##
## $year_c