X-Git-Url: https://code.communitydata.science/ml_measurement_error_public.git/blobdiff_plain/5c931a7198452ff3ce0ace5b1f68046bfb33d352..214551f74cc94ef1fa2f24aa317265c25bb03757:/simulations/summarize_estimator.R

diff --git a/simulations/summarize_estimator.R b/simulations/summarize_estimator.R
index 3e4209f..8ddeb7c 100644
--- a/simulations/summarize_estimator.R
+++ b/simulations/summarize_estimator.R
@@ -1,18 +1,23 @@
+library(ggdist)
 
-summarize.estimator <- function(df, suffix='naive', coefname='x'){
+summarize.estimator <- function(sims.df, suffix='naive', coefname='x'){
 
-    part <- df[,c('N',
-                  'm',
-                  'Bxy',
-                  paste0('B',coefname,'y.est.',suffix),
-                  paste0('B',coefname,'y.ci.lower.',suffix),
-                  paste0('B',coefname,'y.ci.upper.',suffix),
-                  'y_explained_variance',
-                  'Bzx',
-                  'Bzy',
-                  'accuracy_imbalance_difference'
-                  ),
-               with=FALSE]
+    reported_vars <- c(
+                       'Bxy',
+                       paste0('B',coefname,'y.est.',suffix),
+                       paste0('B',coefname,'y.ci.lower.',suffix),
+                       paste0('B',coefname,'y.ci.upper.',suffix)
+                       )
+
+    
+    grouping_vars <- c('N','m','B0', 'Bxy', 'Bzy', 'Bzx', 'Px', 'Py','y_explained_variance', 'prediction_accuracy','outcome_formula','proxy_formula','truth_formula','z_bias','y_bias')
+
+    grouping_vars <- grouping_vars[grouping_vars %in% names(df)]
+
+    part <- sims.df[,
+                    unique(c(reported_vars,
+                             grouping_vars)),
+                    with=FALSE]
 
 
     true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
@@ -25,14 +30,17 @@ summarize.estimator <- function(df, suffix='naive', coefname='x'){
                        bias=bias,
                        sign.correct =sign.correct)]
 
+
     part.plot <- part[, .(p.true.in.ci = mean(true.in.ci),
                           mean.bias = mean(bias),
-                          mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
-                          var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
+                          mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]],na.rm=T),
+                          var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]],na.rm=T),
                           est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.975,na.rm=T),
                           est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.025,na.rm=T),
                           mean.ci.upper = mean(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],na.rm=T),
                           mean.ci.lower = mean(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],na.rm=T),
+                          median.ci.upper = median(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],na.rm=T),
+                          median.ci.lower = median(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],na.rm=T),
                           ci.upper.975 = quantile(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],0.975,na.rm=T),
                           ci.upper.025 = quantile(.SD[[paste0('B',coefname,'y.ci.upper.',suffix)]],0.025,na.rm=T),
                           ci.lower.975 = quantile(.SD[[paste0('B',coefname,'y.ci.lower.',suffix)]],0.975,na.rm=T),
@@ -43,7 +51,7 @@ summarize.estimator <- function(df, suffix='naive', coefname='x'){
                           variable=coefname,
                           method=suffix
                           ),
-                      by=c("N","m",'y_explained_variance','Bzx', 'Bzy', 'accuracy_imbalance_difference')
+                      by=grouping_vars,
                       ]
     
     return(part.plot)