-
Notifications
You must be signed in to change notification settings - Fork 2
/
4tmle.Rmd
507 lines (405 loc) · 17.1 KB
/
4tmle.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
# TMLE
```{r tmlesetup01t, include=FALSE}
require(knitr)
require(glmnet)
require(kableExtra)
require(dplyr)
require(xgboost)
require(SuperLearner)
require(Publish)
require(tableone)
options(knitr.kable.NA = '')
cachex=TRUE
```
## Doubly robust estimators
Now that we have covered
- outcome models (e.g., G-computation) and
- exposure models (e.g., propensity score models),
let us talk about doubly robust (DR) estimators. DR has several important properties:
* They use information from both
- the exposure and
- the outcome models.
* They provide a **consistent estimator** if either of the above mentioned models is correctly specified.
- consistent estimator means as the sample size increases, distribution of the estimates gets concentrated near the true parameter
* They provide an **efficient estimator** if both the exposure and the outcome model are correctly specified.
- efficient estimator means estimates approximates the true parameter in terms of a chosen loss function (e.g., could be RMSE).
## TMLE
Targeted Maximum Likelihood Estimation (TMLE) is a DR method, using
- an initial estimate from the outcome model (G-computation)
- the propensity score (exposure) model to improve.
In addition to being DR, TMLE has several other desirable properties:
* It allows the use of **data-adaptive algorithms** like machine learning without sacrificing interpretability.
* ML is only used in intermediary steps to develop the estimator, so the optimization and interpretation of the estimator as a whole remains intact.
* The use of machine learning can help mitigate model misspecification.
* It has been shown to outperform other methods, particularly in **sparse data settings**.
## TMLE Steps
According to @luque2018targeted, we need to the following steps (2-7) for obtaining point estimates when dealing with binary outcome. But as we are dealing with continuous outcome, we need an added transformation step at the beginning, and also at the end.
| | |
|-|-|
|Step 1| Transformation of continuous outcome variable |
|Step 2| Predict from initial outcome modelling: G-computation|
|Step 3| Predict from propensity score model|
|Step 4| Estimate clever covariate $H$ |
|Step 5| Estimate fluctuation parameter $\epsilon$|
|Step 6| Update the initial outcome model prediction based on targeted adjustment of the initial predictions using the PS model |
|Step 7| Find treatment effect estimate |
|Step 8| Transform back the treatment effect estimate in the original outcome scale |
|Step 9| Confidence interval estimation based on closed form formula|
- We will go through the steps of TMLE one-by-one, using the RHC dataset presented in previous chapters.
- As a reminder, the exposure we are considering is RHC (right heart catheterization) and the outcome of interest is length of stay in the hospital.
```{r dataload_02, cache=TRUE, echo = TRUE}
# Read the data saved at the last chapter
ObsData <- readRDS(file = "data/rhcAnalytic.RDS")
```
## Step 1: Transformation of Y
In our example, the outcome is continuous.
```{r transf1, cache=TRUE, echo = TRUE}
summary(ObsData$Y)
plot(density(ObsData$Y), main = "Observed Y")
```
```{block, type='rmdcomment'}
General recommendation is to **transform** continuous outcome to be within the range [0,1] [@gruber2010targeted].
```
<!--- However, it is recommended that even with continuous outcomes we use a log-likelihood loss function for the maximum likelihood estimation, as we would with a binary outcome. --->
```{r transf, cache=TRUE, echo = TRUE}
min.Y <- min(ObsData$Y)
max.Y <- max(ObsData$Y)
ObsData$Y.bounded <- (ObsData$Y-min.Y)/(max.Y-min.Y)
```
Check the range of our transformed outcome variable
```{r transf2, cache=TRUE, echo = TRUE}
summary(ObsData$Y.bounded)
```
## Step 2: Initial G-comp estimate
```{block, type='rmdcomment'}
We construct our outcome model, and make our initial predictions.
```
For this step, we will use **SuperLearner**. This requires no apriori assumptions about the structure of our outcome model.
```{r SL_out0, cache=TRUE, message=FALSE, warning=FALSE}
library(SuperLearner)
set.seed(123)
ObsData.noY <- dplyr::select(ObsData, !c(Y,Y.bounded))
Y.fit.sl <- SuperLearner(Y=ObsData$Y.bounded,
X=ObsData.noY,
cvControl = list(V = 3),
SL.library=c("SL.glm",
"SL.glmnet",
"SL.xgboost"),
method="method.CC_nloglik",
family="gaussian")
```
```{r SL_out01x, cache=TRUE}
ObsData$init.Pred <- predict(Y.fit.sl, newdata = ObsData.noY,
type = "response")$pred
summary(ObsData$init.Pred)
# alternatively, we could write
# ObsData$init.Pred <- Y.fit.sl$SL.predict
```
- We will use these initial prediction values later.
```{block, type='rmdcomment'}
$Q^0(A,L)$ is often used to represent the predictions from initial G-comp model.
```
### Get predictions under both treatments $A = 0$ and $1$
- We could estimate the treatment effect from this initial model.
- We will need the $Q^0(A=1,L)$ and $Q^0(A=0,L)$ predictions later.
- $Q^0(A=1,L)$ predictions:
```{r SL_out01, cache=TRUE}
ObsData.noY$A <- 1
ObsData$Pred.Y1 <- predict(Y.fit.sl, newdata = ObsData.noY,
type = "response")$pred
summary(ObsData$Pred.Y1)
```
- $Q^0(A=0,L)$ predictions:
```{r SL_out02, cache=TRUE}
ObsData.noY$A <- 0
ObsData$Pred.Y0 <- predict(Y.fit.sl, newdata = ObsData.noY,
type = "response")$pred
summary(ObsData$Pred.Y0)
```
### Get initial treatment effect estimate
```{r SL_out03, cache=cachex, echo = TRUE}
ObsData$Pred.TE <- ObsData$Pred.Y1 - ObsData$Pred.Y0
```
```{r SL_out04, cache=cachex, echo = TRUE}
summary(ObsData$Pred.TE)
```
```{r SL_out, cache=TRUE, message=FALSE, warning=FALSE, include = FALSE}
# # specify the library of machine learning algorithms our SuperLearner should use
# # we will use the same set that is the default set in the tmle package
# Q.SL.library = c("SL.glm", "SL.xgboost", "SL.glmnet")
# # check number of missing values, and omit rows with missing values if there are not too many
# sapply(ObsData, function(x) sum(is.na(x)))
# ObsData <- na.omit(ObsData)
# # fit our SuperLearner
# X <- dplyr::select(ObsData, !Y)
# QbarSL <- SuperLearner(Y=ObsData$Y, X=X, SL.library=Q.SL.library, family="gaussian", method="method.CC_nloglik")
# # make predictions with our fitted model
# QbarAW <- QbarSL$SL.predict
#
# # predict the counterfactual outcomes under treatment/no treatment for each observation
# X1 <- X
# X1$A <- 1
# X0 <- X
# X0$A <- 0
# # predicted outcome under treatment
# Qbar1W<- SuperLearner(Y=ObsData$Y, X=X, SL.library=Q.SL.library, family="gaussian", method="method.CC_nloglik", newX=X1)$SL.predict
# # predicted outcome under no treatment
# Qbar0W<- SuperLearner(Y=ObsData$Y, X=X, SL.library=Q.SL.library, family="gaussian", method="method.CC_nloglik", newX=X0)$SL.predict
#
# # initial estimate of the effect of A on Y:
# PsiHat.SS <- mean(Qbar1W - Qbar0W)
# cat("/n Our initial estimate of the effect of RHC on length of stay is: ", PsiHat.SS)
```
## Step 3: PS model
At this point, we have our initial estimate and now want to perform our targeted improvement.
```{r SL_out0ps, cache=TRUE, message=FALSE, warning=FALSE}
library(SuperLearner)
set.seed(124)
ObsData.noYA <- dplyr::select(ObsData, !c(Y,Y.bounded,
A,init.Pred,
Pred.Y1,Pred.Y0,
Pred.TE))
PS.fit.SL <- SuperLearner(Y=ObsData$A,
X=ObsData.noYA,
cvControl = list(V = 3),
SL.library=c("SL.glm",
"SL.glmnet",
"SL.xgboost"),
method="method.CC_nloglik",
family="binomial")
```
```{r SL_out01ps2, cache=TRUE}
all.pred <- predict(PS.fit.SL, type = "response")
ObsData$PS.SL <- all.pred$pred
```
```{block, type='rmdcomment'}
These propensity score predictions (`PS.SL`) are represented as $g(A_i=1|L_i)$.
```
- We can estimate $g(A_i=0|L_i)$ as $1 - g(A_i=1|L_i)$ or `1 - PS.SL`.
```{r ipw2psx2btmle, cache=TRUE, echo = TRUE}
summary(ObsData$PS.SL)
tapply(ObsData$PS.SL, ObsData$A, summary)
plot(density(ObsData$PS.SL[ObsData$A==0]),
col = "red", main = "")
lines(density(ObsData$PS.SL[ObsData$A==1]),
col = "blue", lty = 2)
legend("topright", c("No RHC","RHC"),
col = c("red", "blue"), lty=1:2)
```
```{r SL_ps, cache=TRUE, message=FALSE, error = FALSE, warning=FALSE, include = FALSE}
# library(SuperLearner)
# set.seed(123)
#
# # specify the library of machine learning algorithms our SuperLearner should use
# # we will use the same set that is the default set in the tmle package
# G.SL.library = c("SL.glm", "SL.gam", "tmle.SL.dbarts.k.5")
# # construct the propensity score model using SuperLearner
# gHatSL <- SuperLearner(Y=ObsData$A, X=subset(ObsData, select= -c(A,Y)),
# SL.library=G.SL.library, family="binomial")
# # get the probability of receiving each treatment for each observation
# gHat1W <- gHatSL$SL.predict # predicted probabilities of A=1 given baseline chars
# gHat0W <- 1 - gHat1W
# # get the probability of receiving the treatment they did receive for each observation
# gHatAW <- rep(NA, nrow(ObsData))
# gHatAW[ObsData$A==1] <- gHat1W[ObsData$A==1]
# gHatAW[ObsData$A==0] <- gHat0W[ObsData$A==0]
```
## Step 4: Estimate $H$
```{block, type='rmdcomment'}
Clever covariate $H(A_i, L_i) = \frac{I(A_i=1)}{g(A_i=1|L_i)} - \frac{I(A_i=0)}{g(A_i=0|L_i)}$ [@luque2018targeted]
```
```{r hestimate2, cache=TRUE, warning=FALSE}
ObsData$H.A1L <- (ObsData$A) / ObsData$PS.SL
ObsData$H.A0L <- (1-ObsData$A) / (1- ObsData$PS.SL)
ObsData$H.AL <- ObsData$H.A1L - ObsData$H.A0L
summary(ObsData$H.AL)
tapply(ObsData$H.AL, ObsData$A, summary)
t(apply(cbind(-ObsData$H.A0L,ObsData$H.A1L),
2, summary))
```
Aggregated or individual clever covariate components show slight difference in their summaries.
## Step 5: Estimate $\epsilon$
```{block, type='rmdcomment'}
Fluctuation parameter $\epsilon$, representing **how large of an adjustment we will make** to the initial estimate.
```
- The fluctuation parameter $\hat\epsilon$ could be
- a scalar or
- a vector with 2 components $\hat\epsilon_0$ and $\hat\epsilon_1$.
- It is estimated through MLE, using a model with an offset based on the initial estimate, and clever covariates as independent variables [@gruber2009targeted]:
$E(Y|A,L)(\epsilon) = \frac{1}{1+\exp(-\log\frac{\bar Q^0(A,L)}{(1-\bar Q^0(A,L))}-\epsilon \times H(A,L))}$
### $\hat\epsilon$ = $\hat\epsilon_0$ and $\hat\epsilon_1$
This is closer to how `tmle` package has implement clever covariates
```{r eestimate, cache=TRUE, warning=FALSE}
eps_mod <- glm(Y.bounded ~ -1 + H.A1L + H.A0L +
offset(qlogis(init.Pred)),
family = "binomial",
data = ObsData)
epsilon <- coef(eps_mod)
epsilon["H.A1L"]
epsilon["H.A0L"]
```
Note that, if `init.Pred` includes negative values, `NaNs` would be produced after applying `qlogis()`.
### Only 1 $\hat\epsilon$
For demonstration purposes
```{r eestimate2, cache=TRUE, warning=FALSE}
eps_mod1 <- glm(Y.bounded ~ -1 + H.AL +
offset(qlogis(init.Pred)),
family = "binomial",
data = ObsData)
epsilon1 <- coef(eps_mod1)
epsilon1
```
Alternative could be to use `H.AL` as weights (not shown here).
## Step 6: Update
### $\hat\epsilon$ = $\hat\epsilon_0$ and $\hat\epsilon_1$
We can use `epsilon["H.A1L"]` and `epsilon["H.A0L"]` to update
```{r teestimate, cache=TRUE, warning=FALSE}
ObsData$Pred.Y1.update <- plogis(qlogis(ObsData$Pred.Y1) +
epsilon["H.A1L"]*ObsData$H.A1L)
ObsData$Pred.Y0.update <- plogis(qlogis(ObsData$Pred.Y0) +
epsilon["H.A0L"]*ObsData$H.A0L)
summary(ObsData$Pred.Y1.update)
summary(ObsData$Pred.Y0.update)
```
### Only 1 $\hat\epsilon$
Alternatively, we could use `epsilon` to from `H.AL` to update
```{r teestimateb, cache=TRUE, warning=FALSE}
ObsData$Pred.Y1.update1 <- plogis(qlogis(ObsData$Pred.Y1) +
epsilon1*ObsData$H.AL)
ObsData$Pred.Y0.update1 <- plogis(qlogis(ObsData$Pred.Y0) +
epsilon1*ObsData$H.AL)
summary(ObsData$Pred.Y1.update1)
summary(ObsData$Pred.Y0.update1)
```
Note that, if `Pred.Y1` and `Pred.Y0` include negative values, `NaNs` would be produced after applying `qlogis()`.
```{r hestimate, cache=TRUE, warning=FALSE, include = FALSE}
# # clever covariates
# H1W <- ObsData$A / gHat1W
# H0W <- (1-ObsData$A) / gHat0W
#
# # fluctuation parameter
# eps_mod <- glm(ObsData$Y ~ -1 + H0W + H1W + offset(qlogis(QbarAW)), family = "binomial")
# epsilon <- coef(eps_mod)
# cat("Epsilon:", epsilon)
#
# # updated estimates
# Q0W_1 <- plogis(qlogis(Qbar0W) + epsilon[1]*H0W)
# Q1W_1 <- plogis(qlogis(Qbar1W) + epsilon[2]*H1W)
```
## Step 7: Effect estimate
Now that the updated predictions of our outcome models are calculated, we can calculate the ATE.
### $\hat\epsilon$ = $\hat\epsilon_0$ and $\hat\epsilon_1$
```{r teestimate2, cache=TRUE, warning=FALSE}
ATE.TMLE.bounded.vector <- ObsData$Pred.Y1.update -
ObsData$Pred.Y0.update
summary(ATE.TMLE.bounded.vector)
ATE.TMLE.bounded <- mean(ATE.TMLE.bounded.vector,
na.rm = TRUE)
ATE.TMLE.bounded
```
### Only 1 $\hat\epsilon$
Alternatively, using `H.AL`:
```{r teestimate2b, cache=TRUE, warning=FALSE}
ATE.TMLE.bounded.vector1 <- ObsData$Pred.Y1.update1 -
ObsData$Pred.Y0.update1
summary(ATE.TMLE.bounded.vector1)
ATE.TMLE.bounded1 <- mean(ATE.TMLE.bounded.vector1,
na.rm = TRUE)
ATE.TMLE.bounded1
```
## Step 8: Rescale effect estimate
We make sure to transform back to our original scale.
### $\hat\epsilon$ = $\hat\epsilon_0$ and $\hat\epsilon_1$
```{r meantmle, cache=TRUE}
ATE.TMLE <- (max.Y-min.Y)*ATE.TMLE.bounded
ATE.TMLE
```
### Only 1 $\hat\epsilon$
Alternatively, using `H.AL`:
```{r meantmle2, cache=TRUE}
ATE.TMLE1 <- (max.Y-min.Y)*ATE.TMLE.bounded1
ATE.TMLE1
```
## Step 9: Confidence interval estimation
- Since the machine learning algorithms were used only in intermediary steps, rather than estimating our parameter of interest directly, 95% confidence intervals can be calculated directly [@luque2018targeted].
```{block, type='rmdcomment'}
Based on semi-parametric theory, closed form variance formula is already derived [@van2012targeted].
```
- Time-consuming bootstrap procedure is not necessary.
```{r tmleinf2, cache=TRUE}
ci.estimate <- function(data = ObsData, H.AL.components = 1){
min.Y <- min(data$Y)
max.Y <- max(data$Y)
# transform predicted outcomes back to original scale
if (H.AL.components == 2){
data$Pred.Y1.update.rescaled <-
(max.Y- min.Y)*data$Pred.Y1.update + min.Y
data$Pred.Y0.update.rescaled <-
(max.Y- min.Y)*data$Pred.Y0.update + min.Y
}
if (H.AL.components == 1) {
data$Pred.Y1.update.rescaled <-
(max.Y- min.Y)*data$Pred.Y1.update1 + min.Y
data$Pred.Y0.update.rescaled <-
(max.Y- min.Y)*data$Pred.Y0.update1 + min.Y
}
EY1_TMLE1 <- mean(data$Pred.Y1.update.rescaled,
na.rm = TRUE)
EY0_TMLE1 <- mean(data$Pred.Y0.update.rescaled,
na.rm = TRUE)
# ATE efficient influence curve
D1 <- data$A/data$PS.SL*
(data$Y - data$Pred.Y1.update.rescaled) +
data$Pred.Y1.update.rescaled - EY1_TMLE1
D0 <- (1 - data$A)/(1 - data$PS.SL)*
(data$Y - data$Pred.Y0.update.rescaled) +
data$Pred.Y0.update.rescaled - EY0_TMLE1
EIC <- D1 - D0
# ATE variance
n <- nrow(data)
varHat.IC <- var(EIC, na.rm = TRUE)/n
# ATE 95% CI
if (H.AL.components == 2) {
ATE.TMLE.CI <- c(ATE.TMLE - 1.96*sqrt(varHat.IC),
ATE.TMLE + 1.96*sqrt(varHat.IC))
}
if (H.AL.components == 1) {
ATE.TMLE.CI <- c(ATE.TMLE1 - 1.96*sqrt(varHat.IC),
ATE.TMLE1 + 1.96*sqrt(varHat.IC))
}
return(ATE.TMLE.CI)
}
```
### $\hat\epsilon$ = $\hat\epsilon_0$ and $\hat\epsilon_1$
```{r tmleinf2b, cache=TRUE}
CI2 <- ci.estimate(data = ObsData, H.AL.components = 2)
CI2
```
### Only 1 $\hat\epsilon$
```{r tmleinf2c, cache=TRUE}
CI1 <- ci.estimate(data = ObsData, H.AL.components = 1)
CI1
```
```{r tmleinf, cache=TRUE, include = FALSE}
# # transform predicted outcomes back to original scale
# Q1W_1_sc <- (b-a)*Q1W_1+a
# Q0W_1_sc <- (b-a)*Q0W_1+a
#
# EY1_TMLE1 <- mean(Q1W_1_sc)
# EY0_TMLE1 <- mean(Q0W_1_sc)
#
# # ATE efficient influence curve
# D1 <- ObsData$A/gHat1W*(ObsData$Y - Q1W_1_sc) + Q1W_1_sc - EY1_TMLE1
# D0 <- (1 - ObsData$A)/(1 - gHat1W)*(ObsData$Y - Q0W_1_sc) + Q0W_1_sc - EY0_TMLE1
# EIC <- D1 - D0
# #ATE variance
# n <- nrow(ObsData)
# varHat.IC <- var(EIC)/n
# #ATE 95% CI
# ATE_TMLE1_CI <- c(ATE_TMLE1 - 1.96*sqrt(varHat.IC), ATE_TMLE1 + 1.96*sqrt(varHat.IC))
# cat("ATE: ", ATE_TMLE1, " (", ATE_TMLE1_CI[1], ", ", ATE_TMLE1_CI[2], ")", sep = "")
```
```{r, cache=TRUE, echo = TRUE}
saveRDS(ATE.TMLE, file = "data/tmlepointh.RDS")
saveRDS(CI2, file = "data/tmlecih.RDS")
```