X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/fa05dbab6bd2c5db6ed4eccf38cff03bb4fd6683..69948cae1e691191fc86e6abdaa485bc98f38f1f:/simulations/simulation_base.R?ds=inline

diff --git a/simulations/simulation_base.R b/simulations/simulation_base.R
index e715edf..73544e9 100644
--- a/simulations/simulation_base.R
+++ b/simulations/simulation_base.R
@@ -280,79 +280,83 @@ run_simulation <-  function(df, result, outcome_formula=y~x+z, proxy_formula=NUL
                                   Bxy.ci.lower.naive = naive.ci.Bxy[1],
                                   Bzy.ci.upper.naive = naive.ci.Bzy[2],
                                   Bzy.ci.lower.naive = naive.ci.Bzy[1]))
-                                  
 
+    amelia_result <- list(
+        Bxy.est.amelia.full = NULL,
+        Bxy.ci.upper.amelia.full = NULL,
+        Bxy.ci.lower.amelia.full = NULL,
+        Bzy.est.amelia.full = NULL,
+        Bzy.ci.upper.amelia.full = NULL,
+        Bzy.ci.lower.amelia.full = NULL
+        )
 
-    amelia.out.k <- amelia(df, m=200, p2s=0, idvars=c('x','w'))
-    mod.amelia.k <- zelig(y~x.obs+z, model='ls', data=amelia.out.k$imputations, cite=FALSE)
-    (coefse <- combine_coef_se(mod.amelia.k, messages=FALSE))
+    tryCatch({
+        amelia.out.k <- amelia(df, m=200, p2s=0, idvars=c('x','w'))
+        mod.amelia.k <- zelig(y~x.obs+z, model='ls', data=amelia.out.k$imputations, cite=FALSE)
+        (coefse <- combine_coef_se(mod.amelia.k))
 
-    est.x.mi <- coefse['x.obs','Estimate']
-    est.x.se <- coefse['x.obs','Std.Error']
-    result <- append(result,
-                     list(Bxy.est.amelia.full = est.x.mi,
-                          Bxy.ci.upper.amelia.full = est.x.mi + 1.96 * est.x.se,
-                          Bxy.ci.lower.amelia.full = est.x.mi - 1.96 * est.x.se
-                          ))
+        est.x.mi <- coefse['x.obs','Estimate']
+        est.x.se <- coefse['x.obs','Std.Error']
+        est.z.mi <- coefse['z','Estimate']
+        est.z.se <- coefse['z','Std.Error']
 
-    est.z.mi <- coefse['z','Estimate']
-    est.z.se <- coefse['z','Std.Error']
+        amelia_result <- list(Bxy.est.amelia.full = est.x.mi,
+                              Bxy.ci.upper.amelia.full = est.x.mi + 1.96 * est.x.se,
+                              Bxy.ci.lower.amelia.full = est.x.mi - 1.96 * est.x.se,
+                              Bzy.est.amelia.full = est.z.mi,
+                              Bzy.ci.upper.amelia.full = est.z.mi + 1.96 * est.z.se,
+                              Bzy.ci.lower.amelia.full = est.z.mi - 1.96 * est.z.se
+                              )
 
-    result <- append(result,
-                     list(Bzy.est.amelia.full = est.z.mi,
-                          Bzy.ci.upper.amelia.full = est.z.mi + 1.96 * est.z.se,
-                          Bzy.ci.lower.amelia.full = est.z.mi - 1.96 * est.z.se
-                          ))
+    },
 
+    error = function(e){
+        result[['error']] <- e}
+    )
 
-        temp.df <- copy(df)
-        temp.df <- temp.df[,x:=x.obs]
-        mod.caroll.lik <- measerr_mle(temp.df, outcome_formula=outcome_formula, proxy_formula=proxy_formula, truth_formula=truth_formula)
-
-    ## tryCatch({
-    ## mod.calibrated.mle <- mecor(y ~ MeasError(w_pred, reference = x.obs) + z, df, B=400, method='efficient')
-    ## (mod.calibrated.mle)
-    ## (mecor.ci <- summary(mod.calibrated.mle)$c$ci['x.obs',])
-    ## result <- append(result, list(
-    ##                              Bxy.est.mecor = mecor.ci['Estimate'],
-    ##                              Bxy.ci.upper.mecor = mecor.ci['UCI'],
-    ##                              Bxy.ci.lower.mecor = mecor.ci['LCI'])
-    ##                  )
 
+    result <- append(result, amelia_result)
 
 
-    fischer.info <- NA
-    ci.upper <- NA
-    ci.lower <- NA
+   mle_result <- list(Bxy.est.mle = NULL,
+                      Bxy.ci.upper.mle = NULL,
+                      Bxy.ci.lower.mle = NULL,
+                      Bzy.est.mle = NULL,
+                      Bzy.ci.upper.mle = NULL,
+                      Bzy.ci.lower.mle = NULL)
 
-    tryCatch({fischer.info <- solve(mod.caroll.lik$hessian)
+    tryCatch({
+        temp.df <- copy(df)
+        temp.df <- temp.df[,x:=x.obs]
+        mod.caroll.lik <- measerr_mle(temp.df, outcome_formula=outcome_formula, proxy_formula=proxy_formula, truth_formula=truth_formula)
+        fischer.info <- solve(mod.caroll.lik$hessian)
+        coef <- mod.caroll.lik$par
         ci.upper <- coef + sqrt(diag(fischer.info)) * 1.96
         ci.lower <- coef - sqrt(diag(fischer.info)) * 1.96
+        mle_result <- list(Bxy.est.mle = coef['x'],
+                           Bxy.ci.upper.mle = ci.upper['x'],
+                           Bxy.ci.lower.mle = ci.lower['x'],
+                           Bzy.est.mle = coef['z'],
+                           Bzy.ci.upper.mle = ci.upper['z'],
+                           Bzy.ci.lower.mle = ci.lower['z'])
     },
 
     error=function(e) {result[['error']] <- as.character(e)
     })
 
-    coef <- mod.caroll.lik$par
         
-        result <- append(result,
-                         list(Bxy.est.mle = coef['x'],
-                              Bxy.ci.upper.mle = ci.upper['x'],
-                              Bxy.ci.lower.mle = ci.lower['x'],
-                              Bzy.est.mle = coef['z'],
-                              Bzy.ci.upper.mle = ci.upper['z'],
-                              Bzy.ci.lower.mle = ci.lower['z']))
-
-        mod.zhang.lik <- zhang.mle.iv(df)
-        coef <- coef(mod.zhang.lik)
-        ci <- confint(mod.zhang.lik,method='quad')
-        result <- append(result,
-                         list(Bxy.est.zhang = coef['Bxy'],
-                              Bxy.ci.upper.zhang = ci['Bxy','97.5 %'],
-                              Bxy.ci.lower.zhang = ci['Bxy','2.5 %'],
-                              Bzy.est.zhang = coef['Bzy'],
-                              Bzy.ci.upper.zhang = ci['Bzy','97.5 %'],
-                              Bzy.ci.lower.zhang = ci['Bzy','2.5 %']))
+    result <- append(result, mle_result)
+
+    mod.zhang.lik <- zhang.mle.iv(df)
+    coef <- coef(mod.zhang.lik)
+    ci <- confint(mod.zhang.lik,method='quad')
+    result <- append(result,
+                     list(Bxy.est.zhang = coef['Bxy'],
+                          Bxy.ci.upper.zhang = ci['Bxy','97.5 %'],
+                          Bxy.ci.lower.zhang = ci['Bxy','2.5 %'],
+                          Bzy.est.zhang = coef['Bzy'],
+                          Bzy.ci.upper.zhang = ci['Bzy','97.5 %'],
+                          Bzy.ci.lower.zhang = ci['Bzy','2.5 %']))
 
     ## What if we can't observe k -- most realistic scenario. We can't include all the ML features in a model.
     ## amelia.out.nok <- amelia(df, m=200, p2s=0, idvars=c("x","w_pred"), noms=noms)