Read libraries

Read in NYTD data

Organize NYTD data (drop missing)

Covariates

Create needed covariates

nytd_all$foodIns = nytd_all$Food.Insecure / 100 # mean 0.133106
nytd_all$unempRt = nytd_all$unemp/(nytd_all$unemp + nytd_all$emp) # 0.05514365
nytd_all$singPar = nytd_all$kidsSingPar/nytd_all$child # 0.3282801
nytd_all$chpovRt = nytd_all$childpov/nytd_all$child # 0.1967591
nytd_all$povRt = nytd_all$pov/nytd_all$pop # 0.1392956
nytd_all$gspPc = (nytd_all$Gross.State.Product*1000000) / nytd_all$pop # 57150.41
nytd_all$crimeRt = ((nytd_all$violent_crime + nytd_all$property_crime) / nytd_all$pop)*1000 # 28.5098
nytd_all$pctBlk = nytd_all$blkpop / nytd_all$pop # 0.1036744
nytd_all$pctHis = nytd_all$hispop / nytd_all$pop # 0.1171681
nytd_all$mediPpl = nytd_all$Medicaid.beneficiaries / nytd_all$pov # 1.599911
nytd_all$snapPpl= nytd_all$Food.Stamp.SNAP.Recipients / nytd_all$pov # 0.9826695
nytd_all$tanfPpl = nytd_all$AFDC.TANF.Recipients / nytd_all$childpov # 0.2354464
nytd_all$welfarePc = (nytd_all$swTot / nytd_all$pop)*1000 # 1.594769
nytd_all$incarRt = (nytd_all$incarTot / nytd_all$adult)*1000 # 5.005433
nytd_all$deathRt = (nytd_all$deathSen / nytd_all$newIncar)*1000 # 0.05661189
nytd_all$policePc = (nytd_all$policeTot / nytd_all$pop)*1000 # 2.72597
nytd_all$wicPpl = nytd_all$WIC.participation / nytd_all$childpov # 0.496694
nytd_all$fc_homeRt = (nytd_all$homeless / nytd_all$basepop)*100 # 12.22256
nytd_all$fc_subRt = (nytd_all$subabuse / nytd_all$basepop)*100 # 11.06124
nytd_all$fc_incarRt = (nytd_all$incarc / nytd_all$basepop)*100 # 14.34807

Create sample

nytd_sample <- subset(nytd_all, select = c("state","wave","homeless","subabuse","incarc","basepop",
                                           "fc_homeRt","fc_subRt","fc_incarRt","LessHS","foodIns",
                                           "unempRt","singPar","chpovRt","gspPc","policy_updated",
                                           "crimeRt","pctBlk","pctHis","tanf3fam","mediPpl","snapPpl",
                                           "tanfPpl","welfarePc","incarRt","deathRt","policePc"))

nytd_scaled <- scale(nytd_sample[c(10:27)])
nytd_sampSc <- cbind(nytd_sample[c(1:9)],nytd_scaled)
obsN=1:nrow(nytd_sampSc)
nytd_sampSc$wave_c <- nytd_sampSc$wave - 1

# separate waves
nytd_sampSc_1 <- subset(nytd_sampSc,wave==1)
obsN_1=1:nrow(nytd_sampSc_1)

nytd_sampSc_2 <- subset(nytd_sampSc,wave==2)
obsN_2=1:nrow(nytd_sampSc_2)

nytd_sampSc_3 <- subset(nytd_sampSc,wave==3)
obsN_3=1:nrow(nytd_sampSc_3)

Models

Start testing outcomes

# wave 2: prevalence of homelessness
home_lm_w2 <- lm(fc_homeRt ~ unempRt + singPar + foodIns + chpovRt + LessHS + gspPc + policy_updated + crimeRt + pctBlk + tanf3fam + snapPpl + mediPpl + tanfPpl*welfarePc + incarRt + deathRt + policePc, data=nytd_sampSc_2)
summary(home_lm_w2)
## 
## Call:
## lm(formula = fc_homeRt ~ unempRt + singPar + foodIns + chpovRt + 
##     LessHS + gspPc + policy_updated + crimeRt + pctBlk + tanf3fam + 
##     snapPpl + mediPpl + tanfPpl * welfarePc + incarRt + deathRt + 
##     policePc, data = nytd_sampSc_2)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -10.6681  -2.6141   0.1958   1.3819  14.1350 
## 
## Coefficients:
##                   Estimate Std. Error t value Pr(>|t|)    
## (Intercept)        10.5903     1.1861   8.929 4.46e-10 ***
## unempRt             0.8887     2.0411   0.435   0.6663    
## singPar             0.1764     1.1735   0.150   0.8815    
## foodIns            -0.3719     1.4524  -0.256   0.7996    
## chpovRt            -2.1976     2.3176  -0.948   0.3504    
## LessHS              0.3390     2.0199   0.168   0.8678    
## gspPc              -4.7971     1.8342  -2.615   0.0136 *  
## policy_updated     -1.0081     2.5407  -0.397   0.6942    
## crimeRt            -0.2670     1.2300  -0.217   0.8296    
## pctBlk             -1.3836     1.5440  -0.896   0.3771    
## tanf3fam            3.6164     1.9732   1.833   0.0765 .  
## snapPpl             0.3447     1.5382   0.224   0.8242    
## mediPpl            -1.6295     1.8148  -0.898   0.3762    
## tanfPpl             1.0588     1.7200   0.616   0.5427    
## welfarePc           0.5396     1.2626   0.427   0.6721    
## incarRt             2.4906     1.3061   1.907   0.0658 .  
## deathRt            -1.3574     1.8098  -0.750   0.4589    
## policePc           -0.7330     1.1375  -0.644   0.5241    
## tanfPpl:welfarePc  -2.3775     1.1056  -2.150   0.0394 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 6.217 on 31 degrees of freedom
## Multiple R-squared:  0.5239, Adjusted R-squared:  0.2475 
## F-statistic: 1.895 on 18 and 31 DF,  p-value: 0.0573