Merge branch 'master' of https://github.com/scunning1975/mixtape

Do/bail.do

@@ -28,6 +28,9 @@ ivregress 2sls guilt (jail3= $judge_pre) $control2, robust first
 ivregress 2sls guilt (jail3= $judge_pre) possess robbery DUI1st drugSell aggAss $demo $prior $off $control2 , robust first
 
 * JIVE main results
+* jive can be installed using: net from https://www.stata-journal.com/software/sj6-3/
+* net install st0108
+
 * minimum controls
 jive guilt (jail3= $judge_pre) $control2, robust
 * maximum controls

R/castle_3.R

@@ -23,7 +23,7 @@ leadslags_plot %>%
   ggplot(aes(x = label, y = mean,
              ymin = mean-1.96*sd, 
              ymax = mean+1.96*sd)) +
-  geom_hline(yintercept = 0.035169444, color = "red") +
+  geom_hline(yintercept = 0.0769, color = "red") +
   geom_pointrange() +
   theme_minimal() +
   xlab("Years before and after castle doctrine expansion") +
@@ -34,4 +34,23 @@ leadslags_plot %>%
              linetype = "dashed")
 
 
+# This version includes
+# an interval that traces the confidence intervals
+# of your coefficients
+leadslags_plot %>%
+  ggplot(aes(x = label, y = mean,
+             ymin = mean-1.96*sd, 
+             ymax = mean+1.96*sd)) +
+  # this creates a red horizontal line
+  geom_hline(yintercept = 0.0769, color = "red") +
+  geom_line() + 
+  geom_point() +
+  geom_ribbon(alpha = 0.2) +
+  theme_minimal() +
+  # Important to have informative axes labels!
+  xlab("Years before and after castle doctrine expansion") +
+  ylab("log(Homicide Rate)") +
+  geom_hline(yintercept = 0) +
+  geom_vline(xintercept = 0)
+
 

R/castle_4.R

@@ -7,7 +7,7 @@ leadslags_plot %>%
              ymin = mean-1.96*sd, 
              ymax = mean+1.96*sd)) +
   # this creates a red horizontal line
-  geom_hline(yintercept = 0.035169444, color = "red") +
+  geom_hline(yintercept = 0.0769, color = "red") +
   geom_line() + 
   geom_point() +
   geom_ribbon(alpha = 0.2) +

R/sasp.R

@@ -49,7 +49,7 @@ balanced_sasp <- balanced_sasp %>% mutate(
   demean_asian_cl = asian_cl - ave(asian_cl, id),
   demean_black_cl = black_cl - ave(black_cl, id),
   demean_hispanic_cl = hispanic_cl - ave(hispanic_cl, id),
-  demean_othrace_cl = othrace_cl - ave(lnw, id),
+  demean_othrace_cl = othrace_cl - ave(othrace_cl, id),
   demean_hot = hot - ave(hot, id),
   demean_massage_cl = massage_cl - ave(massage_cl, id)
   )

R/thornton_ri.R

@@ -18,13 +18,14 @@ tb <- NULL
 
 permuteHIV <- function(df, random = TRUE){
   tb <- df
-  first_half <- ceiling(nrow(tb)/2)
-  second_half <- nrow(tb) - first_half
+  # Number of treated in dataset
+  n_treated <- 2222
+  n_control <- nrow(tb) - n_treated
 
   if(random == TRUE){
     tb <- tb %>%
       sample_frac(1) %>%
-      mutate(any = c(rep(1, first_half), rep(0, second_half)))
+      mutate(any = c(rep(1, n_treated), rep(0, n_control)))
   }
 
   te1 <- tb %>%

python/castle_3.py

@@ -48,14 +48,12 @@ def read_data(file):
 leadslags_plot['lb'] = leadslags_plot['mean'] - leadslags_plot['sd']*1.96
 leadslags_plot['ub'] = leadslags_plot['mean'] + leadslags_plot['sd']*1.96
 
-# This version has a point-range at each
-# estimated lead or lag
-# comes down to stylistic preference at the
-# end of the day!
+# This version has a point-range at each estimated lead or lag
+# comes down to stylistic preference at the end of the day!
 p.ggplot(leadslags_plot, p.aes(x = 'label', y = 'mean',
              ymin = 'lb', 
              ymax = 'ub')) +\
-    p.geom_hline(yintercept = 0.035169444, color = "red") +\
+    p.geom_hline(yintercept = 0.0769, color = "red") +\
     p.geom_pointrange() +\
     p.theme_minimal() +\
     p.xlab("Years before and after castle doctrine expansion") +\

python/castle_4.py

@@ -1 +1,16 @@
-# Missing python script
+# This version has a point-range at each estimated lead or lag
+# comes down to stylistic preference at the end of the day!
+p.ggplot(leadslags_plot, p.aes(x = 'label', y = 'mean',
+             ymin = 'lb', 
+             ymax = 'ub')) +\
+    p.geom_hline(yintercept = 0.0769, color = "red") +\
+    p.geom_line() +\
+    p.geom_point() +\
+    p.geom_ribbon(alpha = 0.2) +\
+    p.theme_minimal() +\
+    p.xlab("Years before and after castle doctrine expansion") +\
+    p.ylab("log(Homicide Rate)") +\
+    p.geom_hline(yintercept = 0,
+             linetype = "dashed") +\
+    p.geom_vline(xintercept = 0,
+             linetype = "dashed")

python/nsw_pscore.py

@@ -16,11 +16,11 @@ def read_data(file):
 nsw_dw_cpscontrol = read_data('cps_mixtape.dta')
 
 nsw_dw_cpscontrol = pd.concat((nsw_dw_cpscontrol, nsw_dw))
-nsw_dw_cpscontrol[['u74', 'u75']] = 0
+nsw_dw_cpscontrol['u74'], nsw_dw_cpscontrol['u75'] = 0, 0
 nsw_dw_cpscontrol.loc[nsw_dw_cpscontrol.re74==0, 'u74'] = 1
 nsw_dw_cpscontrol.loc[nsw_dw_cpscontrol.re75==0, 'u75'] = 1
 # estimating propensity score
-logit_nsw = smf.glm(formula="""treat ~ age + age**2 + age**3 + educ + educ**2 + 
+logit_nsw = smf.glm(formula="""treat ~ age + I(age**2) + I(age**3) + educ + I(educ**2) + 
                     marr + nodegree + black + hisp + re74 + re75 + u74 + u75 + educ*re74""", 
                     family=sm.families.Binomial(),
                    data=nsw_dw_cpscontrol).fit()

python/thornton_ri.py

@@ -17,11 +17,11 @@ def read_data(file):
 
 def permuteHIV(df, random = True):
     tb = df.copy()
-    first_half = np.ceil(tb.shape[0] / 2)
-    second_half = tb.shape[0] - first_half
+    n_treated = 2222
+    n_control = tb.shape[0] - n_treated
     if random:
         tb = tb.sample(frac=1)
-        tb['any'] = np.concatenate((np.repeat(1, first_half), np.repeat(0, second_half)))
+        tb['any'] = np.concatenate((np.repeat(1, n_treated), np.repeat(0, n_control)))
 
     te1 = tb[tb['any']==1]['got'].mean()
     te0 = tb[tb['any']==0]['got'].mean()