diff --git a/docs/articles/Family.html b/docs/articles/Family.html index 86dfb6a..917cbdf 100644 --- a/docs/articles/Family.html +++ b/docs/articles/Family.html @@ -33,7 +33,7 @@ RobinCar - 1.1.0 + 1.2.0 @@ -100,26 +100,21 @@

2026-01-19

paper.

 library(RobinCar)
-library(RobinCar2)
-
## 
-## Attaching package: 'RobinCar2'
-
## The following object is masked from 'package:base':
-## 
-##     table
-
-library(dplyr)
-
## 
-## Attaching package: 'dplyr'
-
## The following objects are masked from 'package:stats':
-## 
-##     filter, lag
-
## The following objects are masked from 'package:base':
-## 
-##     intersect, setdiff, setequal, union
+library(RobinCar2) +library(dplyr) +library(SuperLearner) +library(ranger) +library(xgboost) +library(glmnet) +
+

Case Study 1: ACTG175 Dataset +

Data Manipulation

-

Creates continuous and binary outcomes, and does simple data -manipulations.

-
+
We use data from the Juraska et al. (2022) R package, which comes
+from a study of nucleoside treatment regimens for individuals with HIV-1
+(Hammer et al. 1996) called the AIDS Clinical Trials Group Study 175.
+This trial had stratified permuted block randomization.

+
 # Data are from the speff2trial package
 data <- tibble(speff2trial::ACTG175)
 
@@ -142,7 +137,7 @@ 
2026-01-19

 covariates of weight, hemophilia status, and prior use of non-zidovudine
 antiretroviral therapy. These specifications ensure that the covariate
 adjustment has guaranteed efficiency gain (asymptotically).

-
+
 robin_lm(
   y_cont ~ arms * (strat + wtkg + hemo + oprior), 
   treatment = arms ~ pb(strat), 
@@ -162,36 +157,10 @@ 
2026-01-19

 ## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

 
Generalized Linear Models

 
For the binary outcome, we can use a logistic regression model
-instead.

-
-robin_glm(
-  y_bin ~ arms * (wtkg + hemo + oprior),
-  treatment = arms ~ pb(strat),
-  family = binomial(link = "logit"),
-  contrast = "risk_ratio",
-  data = data
-)

-
## Warning in robin_glm(y_bin ~ arms * (wtkg + hemo + oprior), treatment = arms ~
-## : Consider using the log transformation `log_odds_ratio` and `log_risk_ratio`
-## to replace `odds_ratio` and `risk_ratio` to improve the performance of normal
-## approximation.

-
## Model        :  y_bin ~ arms * (wtkg + hemo + oprior) 
-## Randomization:  arms ~ pb(strat)  ( Permuted-Block )
-## Variance Type:  vcovG 
-## Marginal Mean: 
-##    Estimate   Std.Err     2.5 % 97.5 %
-## 0 0.0496651 0.0092998 0.0314378 0.0679
-## 1 0.1828118 0.0168988 0.1496908 0.2159
-## 
-## Contrast     :  risk_ratio
-##          Estimate Std.Err Z Value  Pr(>|z|)    
-## 1 v.s. 0  3.68089 0.76609  3.4994 0.0004662 ***
-## ---
-## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

-
Rather than a linear contrast, we can instead estimate a risk ratio.
-This does not change the marginal mean estimates, but it changes the
-contrast estimates (and p-values).

-
+instead. Rather than a linear contrast, we could instead estimate a log
+risk ratio. This does not change the marginal mean estimates, but it
+changes the contrast estimates (and p-values).

+
 robin_glm(
   y_bin ~ arms * (strat + wtkg + hemo + oprior),
   treatment = arms ~ pb(strat),
@@ -223,7 +192,7 @@ 
2026-01-19

 calculation.

 
The MH function in RobinCar is only valid for simple
 randomization.

-
+
 data <- data %>% mutate(
   X=interaction(oprior, hemo)
 )
@@ -246,7 +215,7 @@ 
2026-01-19

 
For a survival outcome with right-censoring, we can use the RobinCar2
 function robin_surv to do a covariate-adjusted, stratified
 log-rank test.

-
+
 surv <- robin_surv(
   Surv(days, cens) ~ wtkg + oprior + hemo + strat,
   treatment = arms ~ pb(strat),
@@ -272,17 +241,134 @@ 
2026-01-19

 ## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

 
You can use the table function to see the number of
 events and number at-risk

-
+
 table(surv)

 
## Number of patients and events per treatment arm:
 ##   arms Patients Events
 ## 1    0      532    181
 ## 2    1      522    103

+

+

+
Case Study 2: RCT of Indomethacin for Post-ERCP Pancreatitis
+

+
Data Manipulation

+
This case study uses a different dataset,
+medicaldata::indo_rct, which was a randomized trial of
+rectal indomethacin to prevent post-ERCP pancreatitis (Elmunzer,
+Higgins, et al. 2012). This study used simple randomization stratified
+by study site (this is not the same as stratified permuted block
+randomization in the first example).

+
+
## Loading required package: medicaldata

+
+data2 <- medicaldata::indo_rct %>%
+  mutate(
+    outcome2=as.numeric(outcome)-1
+  ) %>%
+  select(
+    -c(outcome, status, type, bleed)
+  )

+
First fit a really simple logistic regression working model only
+adjusting for site, and a risk difference as our contrast of
+interest.

+
+robin_glm(
+  outcome2 ~ rx * site, 
+  treatment = rx ~ sr(1), 
+  data=data2,
+  family=binomial(link="logit"),
+  contrast = "difference"
+)

+
## Model        :  outcome2 ~ rx * site 
+## Randomization:  rx ~ sr(1)  ( Simple )
+## Variance Type:  vcovG 
+## Marginal Mean: 
+##                Estimate  Std.Err    2.5 % 97.5 %
+## 0_placebo      0.167499 0.021227 0.125894 0.2091
+## 1_indomethacin 0.092527 0.016766 0.059666 0.1254
+## 
+## Contrast     :  difference
+##                                Estimate   Std.Err Z Value Pr(>|z|)   
+## 1_indomethacin v.s. 0_placebo -0.074971  0.026910  -2.786 0.005337 **
+## ---
+## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

+
There are 27 baseline covariates included in this dataset and 602
+patients. If we include all of the covariates in a logistic regression
+working model, the model fails to converge and returns NA.

+
+# Create formula with all baseline covariates included in dataset
+covariates <- setdiff(colnames(data2), c("id", "outcome2", "rx"))
+formula <- as.formula(
+  sprintf("outcome2 ~ rx * (%s)", paste0(covariates, collapse=" + "))
+)

+
+robin_glm(
+  as.formula(formula), 
+  treatment = rx ~ sr(1), 
+  data=data2,
+  family=binomial(link="logit"),
+  contrast = "difference"
+)

+
## Model        :  outcome2 ~ rx * (site + age + risk + gender + sod + pep + recpanc +      psphinc + precut + difcan + pneudil + amp + paninj + acinar +      brush + asa81 + asa325 + asa + prophystent + therastent +      pdstent + sodsom + bsphinc + bstent + chole + pbmal + train) 
+## Randomization:  rx ~ sr(1)  ( Simple )
+## Variance Type:  vcovG 
+## Marginal Mean: 
+##                Estimate Std.Err 2.5 % 97.5 %
+## 0_placebo            NA      NA    NA     NA
+## 1_indomethacin       NA      NA    NA     NA
+## 
+## Contrast     :  difference
+##                               Estimate Std.Err Z Value Pr(>|z|)
+## 1_indomethacin v.s. 0_placebo       NA      NA      NA       NA

+
If you do want to include all of the baseline covariates because you
+aren’t sure which ones are the most prognostic, this is a use-case for
+the SuperLearner approach. We’ll test an ensemble of random forest
+(SL.ranger), elastic net regression (Sl.glmnet), and XGboost
+(SL.xgboost). SuperLearner will figure out the optimal combination of
+these approaches. See this
+link for documentation on the SuperLearner.

+
RobinCar includes SuperLearner working models with cross-fitting to
+ensure we aren’t over-fitting to the data. We will use 5 folds for
+cross-fitting. Since cross-fitting is a random process, we’ll also set a
+seed for reproducibility.

+
+set.seed(1989)
+
+sl <- robincar_SL(
+  df=data2,
+  response_col="outcome2",
+  treat_col="rx",
+  covariate_cols=covariates,
+  SL_libraries=c("SL.xgboost", "SL.glmnet", "SL.ranger"),
+  car_scheme="simple",
+  k_split=5
+)

+
## Done!

+
## Warning in func(): Prediction unbiasedness does not hold.

+
+# Make a linear contrast
+contrast <- robincar_contrast(sl, contrast_h="diff")
+contrast

+
## Treatment group contrasts using linear contrast
+## 
+## Contrasts:
+## # A tibble: 1 × 4
+##   contrast                         estimate     se `pval (2-sided)`
+##   <chr>                               <dbl>  <dbl>            <dbl>
+## 1 treat 1_indomethacin - 0_placebo  -0.0812 0.0269          0.00256
+## 
+## Variance-Covariance Matrix for Contrasts:
+##              [,1]
+## [1,] 0.0007245833

+

   

 
   
+        
+

 
 

 
diff --git a/docs/articles/index.html b/docs/articles/index.html
index e3d59bf..e11f0cc 100644
--- a/docs/articles/index.html
+++ b/docs/articles/index.html
@@ -17,7 +17,7 @@
       
       
         RobinCar
-        1.1.0
+        1.2.0
       
     

 
diff --git a/vignettes/articles/Family.Rmd b/vignettes/articles/Family.Rmd
index 1f5cb38..5354c9c 100644
--- a/vignettes/articles/Family.Rmd
+++ b/vignettes/articles/Family.Rmd
@@ -13,7 +13,7 @@ This vignette accompanies the Results section of the RobinCar Family paper.
 knitr::opts_chunk$set(echo = TRUE)
 ```
 
-```{r}
+```{r, results='hide', message=FALSE, warning=FALSE}
 library(RobinCar)
 library(RobinCar2)
 library(dplyr)