]> code.communitydata.science - ml_measurement_error_public.git/blob - simulations/irr_simulation_base.R
ee7112a233fcc9f72c185f991e320682891c62f1
[ml_measurement_error_public.git] / simulations / irr_simulation_base.R
1 library(matrixStats) # for numerically stable logsumexps
2
3 options(amelia.parallel="no",
4         amelia.ncpus=1)
5 library(Amelia)
6
7 source("measerr_methods.R") ## for my more generic function.
8
9 run_simulation <- function(df, result, outcome_formula = y ~ x + z, proxy_formula = w_pred ~ x, truth_formula = x ~ z){
10
11     accuracy <- df[,mean(w_pred==x)]
12     result <- append(result, list(accuracy=accuracy))
13
14     (model.true <- lm(y ~ x + z, data=df))
15     true.ci.Bxy <- confint(model.true)['x',]
16     true.ci.Bzy <- confint(model.true)['z',]
17
18     result <- append(result, list(Bxy.est.true=coef(model.true)['x'],
19                                   Bzy.est.true=coef(model.true)['z'],
20                                   Bxy.ci.upper.true = true.ci.Bxy[2],
21                                   Bxy.ci.lower.true = true.ci.Bxy[1],
22                                   Bzy.ci.upper.true = true.ci.Bzy[2],
23                                   Bzy.ci.lower.true = true.ci.Bzy[1]))
24
25
26
27     loa0.feasible <- lm(y ~ x.obs.0 + z, data = df[!(is.na(x.obs.1))])
28
29     loa0.ci.Bxy <- confint(loa0.feasible)['x.obs.0',]
30     loa0.ci.Bzy <- confint(loa0.feasible)['z',]
31
32     result <- append(result, list(Bxy.est.loa0.feasible=coef(loa0.feasible)['x.obs.0'],
33                                   Bzy.est.loa0.feasible=coef(loa0.feasible)['z'],
34                                   Bxy.ci.upper.loa0.feasible = loa0.ci.Bxy[2],
35                                   Bxy.ci.lower.loa0.feasible = loa0.ci.Bxy[1],
36                                   Bzy.ci.upper.loa0.feasible = loa0.ci.Bzy[2],
37                                   Bzy.ci.lower.loa0.feasible = loa0.ci.Bzy[1]))
38
39
40     df.loa0.mle <- copy(df)
41     df.loa0.mle[,x:=x.obs.0]
42     loa0.mle <- measerr_mle(df.loa0.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula, truth_formula=truth_formula)
43     fisher.info <- solve(loa0.mle$hessian)
44     coef <- loa0.mle$par
45     ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
46     ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
47
48     result <- append(result, list(Bxy.est.loa0.mle=coef['x'],
49                                   Bzy.est.loa0.mle=coef['z'],
50                                   Bxy.ci.upper.loa0.mle = ci.upper['x'],
51                                   Bxy.ci.lower.loa0.mle = ci.lower['x'],
52                                   Bzy.ci.upper.loa0.mle = ci.upper['z'],
53                                   Bzy.ci.lower.loa0.mle = ci.upper['z']))
54
55     loco.feasible <- lm(y ~ x.obs.1 + z, data = df[(!is.na(x.obs.1)) & (x.obs.1 == x.obs.0)])
56
57     loco.feasible.ci.Bxy <- confint(loco.feasible)['x.obs.1',]
58     loco.feasible.ci.Bzy <- confint(loco.feasible)['z',]
59
60     result <- append(result, list(Bxy.est.loco.feasible=coef(loco.feasible)['x.obs.1'],
61                                   Bzy.est.loco.feasible=coef(loco.feasible)['z'],
62                                   Bxy.ci.upper.loco.feasible = loco.feasible.ci.Bxy[2],
63                                   Bxy.ci.lower.loco.feasible = loco.feasible.ci.Bxy[1],
64                                   Bzy.ci.upper.loco.feasible = loco.feasible.ci.Bzy[2],
65                                   Bzy.ci.lower.loco.feasible = loco.feasible.ci.Bzy[1]))
66
67
68     df.loco.mle <- copy(df)
69     df.loco.mle[,x.obs:=NA]
70     df.loco.mle[(x.obs.0)==(x.obs.1),x.obs:=x.obs.0]
71     df.loco.mle[,x.true:=x]
72     df.loco.mle[,x:=x.obs]
73     print(df.loco.mle[!is.na(x.obs.1),mean(x.true==x,na.rm=TRUE)])
74     loco.mle <- measerr_mle(df.loco.mle, outcome_formula=outcome_formula, proxy_formula=proxy_formula, truth_formula=truth_formula)
75     fisher.info <- solve(loco.mle$hessian)
76     coef <- loco.mle$par
77     ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
78     ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
79
80     result <- append(result, list(Bxy.est.loco.mle=coef['x'],
81                                   Bzy.est.loco.mle=coef['z'],
82                                   Bxy.ci.upper.loco.mle = ci.upper['x'],
83                                   Bxy.ci.lower.loco.mle = ci.lower['x'],
84                                   Bzy.ci.upper.loco.mle = ci.upper['z'],
85                                   Bzy.ci.lower.loco.mle = ci.lower['z']))
86
87     ## print(rater_formula)
88     ## print(proxy_formula)
89     ## mle.irr <- measerr_irr_mle( df, outcome_formula = outcome_formula, rater_formula = rater_formula, proxy_formula=proxy_formula, truth_formula=truth_formula)
90
91     ## fisher.info <- solve(mle.irr$hessian)
92     ## coef <- mle.irr$par
93     ## ci.upper <- coef + sqrt(diag(fisher.info)) * 1.96
94     ## ci.lower <- coef - sqrt(diag(fisher.info)) * 1.96
95     
96     ## result <- append(result,
97     ##                  list(Bxy.est.mle = coef['x'],
98     ##                       Bxy.ci.upper.mle = ci.upper['x'],
99     ##                       Bxy.ci.lower.mle = ci.lower['x'],
100     ##                       Bzy.est.mle = coef['z'],
101     ##                       Bzy.ci.upper.mle = ci.upper['z'],
102     ##                       Bzy.ci.lower.mle = ci.lower['z']))
103
104     return(result)
105
106 }

Community Data Science Collective || Want to submit a patch?