Unstash work on misclassification models

[ml_measurement_error_public.git] / simulations / irr_dv_simulation_base.R

diff --git a/simulations/irr_dv_simulation_base.R b/simulations/irr_dv_simulation_base.R
index 059473c629e961de0a3d215002fb3e9e6c0c81ab..3263322cd8c0613279464cdb7c6420b06c6b3707 100644 (file)
--- a/simulations/irr_dv_simulation_base.R
+++ b/simulations/irr_dv_simulation_base.R
@@ -4,23 +4,47 @@ options(amelia.parallel="no",
         amelia.ncpus=1)
 library(Amelia)
 
         amelia.ncpus=1)
 library(Amelia)
 

-source("measerr_methods.R") ## for my more generic function.
+source("pl_methods.R")
+source("measerr_methods_2.R") ## for my more generic function.

 
 

-run_simulation_depvar <- function(df, result, outcome_formula = y ~ x + z, rater_formula = y.obs ~ x, proxy_formula = w_pred ~ y){
-
-    accuracy <- df[,mean(w_pred==y)]
+run_simulation_depvar <- function(df, result, outcome_formula = y ~ x + z, coder_formulas = list(y.obs.0 ~ 1, y.obs.1 ~ 1), proxy_formula = w_pred ~ y.obs.1+y.obs.0+y){
+    (accuracy <- df[,mean(w_pred==y)])

     result <- append(result, list(accuracy=accuracy))
     result <- append(result, list(accuracy=accuracy))

+    (error.cor.z <- cor(df$x, df$w_pred - df$z))
+    (error.cor.x <- cor(df$x, df$w_pred - df$y))
+    (error.cor.y <- cor(df$y, df$y - df$w_pred))
+    result <- append(result, list(error.cor.x = error.cor.x,
+                                  error.cor.z = error.cor.z,
+                                  error.cor.y = error.cor.y))
+
+    model.null <- glm(y~1, data=df,family=binomial(link='logit'))
+    (model.true <- glm(y ~ x + z, data=df,family=binomial(link='logit')))
+    (lik.ratio <- exp(logLik(model.true) - logLik(model.null)))

 
 

-    (model.true <- glm(y ~ x + z, data=df, family=binomial(link='logit')))

     true.ci.Bxy <- confint(model.true)['x',]
     true.ci.Bzy <- confint(model.true)['z',]
 
     true.ci.Bxy <- confint(model.true)['x',]
     true.ci.Bzy <- confint(model.true)['z',]
 

+
+    result <- append(result, list(lik.ratio=lik.ratio))
+

     result <- append(result, list(Bxy.est.true=coef(model.true)['x'],
                                   Bzy.est.true=coef(model.true)['z'],
                                   Bxy.ci.upper.true = true.ci.Bxy[2],
                                   Bxy.ci.lower.true = true.ci.Bxy[1],
                                   Bzy.ci.upper.true = true.ci.Bzy[2],
                                   Bzy.ci.lower.true = true.ci.Bzy[1]))
     result <- append(result, list(Bxy.est.true=coef(model.true)['x'],
                                   Bzy.est.true=coef(model.true)['z'],
                                   Bxy.ci.upper.true = true.ci.Bxy[2],
                                   Bxy.ci.lower.true = true.ci.Bxy[1],
                                   Bzy.ci.upper.true = true.ci.Bzy[2],
                                   Bzy.ci.lower.true = true.ci.Bzy[1]))

+                                  
+    (model.naive <- lm(y~w_pred+z, data=df))
+    
+    naive.ci.Bxy <- confint(model.naive)['w_pred',]
+    naive.ci.Bzy <- confint(model.naive)['z',]
+
+    result <- append(result, list(Bxy.est.naive=coef(model.naive)['w_pred'],
+                                  Bzy.est.naive=coef(model.naive)['z'],
+                                  Bxy.ci.upper.naive = naive.ci.Bxy[2],
+                                  Bxy.ci.lower.naive = naive.ci.Bxy[1],
+                                  Bzy.ci.upper.naive = naive.ci.Bzy[2],
+                                  Bzy.ci.lower.naive = naive.ci.Bzy[1]))

 
 
 
 
 
 


@@ -37,20 +61,20 @@ run_simulation_depvar <- function(df, result, outcome_formula = y ~ x + z, rater
                                   Bzy.ci.lower.loa0.feasible = loa0.ci.Bzy[1]))
 
 
                                   Bzy.ci.lower.loa0.feasible = loa0.ci.Bzy[1]))
 
 

-    df.loa0.mle <- copy(df)
-    df.loa0.mle[,y:=y.obs.0]
-    loa0.mle <- measerr_mle_dv(df.loa0.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula)
-    fisher.info <- solve(loa0.mle$hessian)
-    coef <- loa0.mle$par
-    ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
-    ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
+    ## df.loa0.mle <- copy(df)
+    ## df.loa0.mle[,y:=y.obs.0]
+    ## loa0.mle <- measerr_mle_dv(df.loa0.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula)
+    ## fisher.info <- solve(loa0.mle$hessian)
+    ## coef <- loa0.mle$par
+    ## ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
+    ## ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96

 
 

-    result <- append(result, list(Bxy.est.loa0.mle=coef['x'],
-                                  Bzy.est.loa0.mle=coef['z'],
-                                  Bxy.ci.upper.loa0.mle = ci.upper['x'],
-                                  Bxy.ci.lower.loa0.mle = ci.lower['x'],
-                                  Bzy.ci.upper.loa0.mle = ci.upper['z'],
-                                  Bzy.ci.lower.loa0.mle = ci.upper['z']))
+    ## result <- append(result, list(Bxy.est.loa0.mle=coef['x'],
+    ##                               Bzy.est.loa0.mle=coef['z'],
+    ##                               Bxy.ci.upper.loa0.mle = ci.upper['x'],
+    ##                               Bxy.ci.lower.loa0.mle = ci.lower['x'],
+    ##                               Bzy.ci.upper.loa0.mle = ci.upper['z'],
+    ##                               Bzy.ci.lower.loa0.mle = ci.upper['z']))

 
     loco.feasible <- glm(y.obs.0 ~ x + z, data = df[(!is.na(y.obs.0)) & (y.obs.1 == y.obs.0)], family=binomial(link='logit'))
 
 
     loco.feasible <- glm(y.obs.0 ~ x + z, data = df[(!is.na(y.obs.0)) & (y.obs.1 == y.obs.0)], family=binomial(link='logit'))
 


@@ -64,29 +88,110 @@ run_simulation_depvar <- function(df, result, outcome_formula = y ~ x + z, rater
                                   Bzy.ci.upper.loco.feasible = loco.feasible.ci.Bzy[2],
                                   Bzy.ci.lower.loco.feasible = loco.feasible.ci.Bzy[1]))
 
                                   Bzy.ci.upper.loco.feasible = loco.feasible.ci.Bzy[2],
                                   Bzy.ci.lower.loco.feasible = loco.feasible.ci.Bzy[1]))
 

+    
+    ## df.double.proxy <- copy(df)
+    ## df.double.proxy <- df.double.proxy[,y.obs:=NA]
+    ## df.double.proxy <- df.double.proxy[,y:=NA]
+    
+    ## double.proxy.mle <- measerr_irr_mle_dv(df.double.proxy, outcome_formula=y~x+z, outcome_family=binomial(link='logit'), coder_formulas=list(y.obs.0 ~ y),  proxy_formula=w_pred ~ y.obs.0 + y, proxy_family=binomial(link='logit'))
+    ## print(double.proxy.mle$hessian)
+    ## fisher.info <- solve(double.proxy.mle$hessian)
+    ## coef <- double.proxy.mle$par
+    ## ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
+    ## ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
+
+    ## result <- append(result, list(Bxy.est.double.proxy=coef['x'],
+    ##                               Bzy.est.double.proxy=coef['z'],
+    ##                               Bxy.ci.upper.double.proxy = ci.upper['x'],
+    ##                               Bxy.ci.lower.double.proxy = ci.lower['x'],
+    ##                               Bzy.ci.upper.double.proxy = ci.upper['z'],
+    ##                               Bzy.ci.lower.double.proxy = ci.lower['z']))
+

 
 

-    df.loco.mle <- copy(df)
-    df.loco.mle[,y.obs:=NA]
-    df.loco.mle[(y.obs.0)==(y.obs.1),y.obs:=y.obs.0]
-    df.loco.mle[,y.true:=y]
-    df.loco.mle[,y:=y.obs]
-    print(df.loco.mle[!is.na(y.obs.1),mean(y.true==y,na.rm=TRUE)])
-    loco.mle <- measerr_mle_dv(df.loco.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula)
-    fisher.info <- solve(loco.mle$hessian)
-    coef <- loco.mle$par
+    df.triple.proxy <- copy(df)
+    df.triple.proxy <- df.triple.proxy[,y.obs:=NA]
+    df.triple.proxy <- df.triple.proxy[,y:=NA]
+    
+    triple.proxy.mle <- measerr_irr_mle_dv(df.triple.proxy, outcome_formula=outcome_formula, outcome_family=binomial(link='logit'), coder_formulas=coder_formulas, proxy_formula=proxy_formula, proxy_family=binomial(link='logit'))
+    print(triple.proxy.mle$hessian)
+    fisher.info <- solve(triple.proxy.mle$hessian)
+    print(fisher.info)
+    coef <- triple.proxy.mle$par

     ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
     ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
 
     ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
     ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
 

-    result <- append(result, list(Bxy.est.loco.mle=coef['x'],
-                                  Bzy.est.loco.mle=coef['z'],
-                                  Bxy.ci.upper.loco.mle = ci.upper['x'],
-                                  Bxy.ci.lower.loco.mle = ci.lower['x'],
-                                  Bzy.ci.upper.loco.mle = ci.upper['z'],
-                                  Bzy.ci.lower.loco.mle = ci.lower['z']))
+    result <- append(result, list(Bxy.est.triple.proxy=coef['x'],
+                                  Bzy.est.triple.proxy=coef['z'],
+                                  Bxy.ci.upper.triple.proxy = ci.upper['x'],
+                                  Bxy.ci.lower.triple.proxy = ci.lower['x'],
+                                  Bzy.ci.upper.triple.proxy = ci.upper['z'],
+                                  Bzy.ci.lower.triple.proxy = ci.lower['z']))
+
+    ## df.loco.mle <- copy(df)
+    ## df.loco.mle[,y.obs:=NA]
+    ## df.loco.mle[(y.obs.0)==(y.obs.1),y.obs:=y.obs.0]
+    ## df.loco.mle[,y.true:=y]
+    ## df.loco.mle[,y:=y.obs]
+    ## print(df.loco.mle[!is.na(y.obs.1),mean(y.true==y,na.rm=TRUE)])
+    ## loco.mle <- measerr_mle_dv(df.loco.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula)
+    ## fisher.info <- solve(loco.mle$hessian)
+    ## coef <- loco.mle$par
+    ## ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
+    ## ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
+
+    ## result <- append(result, list(Bxy.est.loco.mle=coef['x'],
+    ##                               Bzy.est.loco.mle=coef['z'],
+    ##                               Bxy.ci.upper.loco.mle = ci.upper['x'],
+    ##                               Bxy.ci.lower.loco.mle = ci.lower['x'],
+    ##                               Bzy.ci.upper.loco.mle = ci.upper['z'],
+    ##                               Bzy.ci.lower.loco.mle = ci.lower['z']))
+
+

 
 

-    print(rater_formula)
-    print(proxy_formula)
+    ## my implementatoin of liklihood based correction
+    mod.zhang <- zhang.mle.dv(df.loco.mle)
+    coef <- coef(mod.zhang)
+    ci <- confint(mod.zhang,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 %']))
+
+    

 
 

+    print(df.loco.mle)
+
+    # amelia says use normal distribution for binary variables.
+    tryCatch({
+        amelia.out.k <- amelia(df.loco.mle, m=200, p2s=0, idvars=c('y','ystar','w','y.obs.1','y.obs.0','y.true'))
+        mod.amelia.k <- zelig(y.obs~x+z, model='ls', data=amelia.out.k$imputations, cite=FALSE)
+        (coefse <- combine_coef_se(mod.amelia.k, messages=FALSE))
+        est.x.mi <- coefse['x','Estimate']
+        est.x.se <- coefse['x','Std.Error']
+        result <- append(result,
+                         list(Bxy.est.amelia.full = est.x.mi,
+                              Bxy.ci.upper.amelia.full = est.x.mi + 1.96 * est.x.se,
+                              Bxy.ci.lower.amelia.full = est.x.mi - 1.96 * est.x.se
+                              ))
+
+        est.z.mi <- coefse['z','Estimate']
+        est.z.se <- coefse['z','Std.Error']
+
+        result <- append(result,
+                         list(Bzy.est.amelia.full = est.z.mi,
+                              Bzy.ci.upper.amelia.full = est.z.mi + 1.96 * est.z.se,
+                              Bzy.ci.lower.amelia.full = est.z.mi - 1.96 * est.z.se
+                              ))
+
+    },
+    error = function(e){
+        message("An error occurred:\n",e)
+        result$error <- paste0(result$error,'\n', e)
+    })

     ## mle.irr <- measerr_irr_mle( df, outcome_formula = outcome_formula, rater_formula = rater_formula, proxy_formula=proxy_formula, truth_formula=truth_formula)
 
     ## fisher.info <- solve(mle.irr$hessian)
     ## mle.irr <- measerr_irr_mle( df, outcome_formula = outcome_formula, rater_formula = rater_formula, proxy_formula=proxy_formula, truth_formula=truth_formula)
 
     ## fisher.info <- solve(mle.irr$hessian)