# Trained-on-Observed-Studies Ensemble (Study-Specific Ensemble) for Multi-Study Learning: fits one or more models on each study and ensembles models. ```r sse(formula = Y ~ ., data, target.study = NA, sim.covs = NA, ssl.method = list("lm"), ssl.tuneGrid = list(c()), sim.mets = FALSE, model = FALSE, customFNs = list(), stack.standardize = FALSE) ``` ## Arguments - `formula`: Model formula - `data`: A dataframe with all the studies has the following columns in this order: "Study", "Y", "V1", ...., "Vp" - `target.study`: Dataframe of the design matrix (just covariates) of study one aims to make predictions on - `sim.covs`: Is a vector of names of covariates or the column numbers of the covariates to be used for the similarity measure. Default is to use all covariates. - `ssl.method`: A list of strings indicating which modeling methods to use. - `ssl.tuneGrid`: A list of the tuning parameters in the format of the caret package. Each element must be a dataframe (as required by caret). If no tuning parameters are required then NA is indicated. - `sim.mets`: Boolean indicating whether to calculate default covariate profile similarity measures. - `model`: Indicates whether to attach training data to model object. - `customFNs`: Optional list of functions that can be used to add custom covaraite profile similarity measures. - `stack.standardize`: Boolean determining whether stacking weights are standardized to sum to 1. Default is FALSE ## Returns A model object of studyStrap class "ss" that can be used to make predictions. ## Examples ```r ########################## ##### Simulate Data ###### ########################## set.seed(1) # create half of training dataset from 1 distribution X1 <- matrix(rnorm(2000), ncol = 2) # design matrix - 2 covariates B1 <- c(5, 10, 15) # true beta coefficients y1 <- cbind(1, X1) %*% B1 # create 2nd half of training dataset from another distribution X2 <- matrix(rnorm(2000, 1,2), ncol = 2) # design matrix - 2 covariates B2 <- c(10, 5, 0) # true beta coefficients y2 <- cbind(1, X2) %*% B2 X <- rbind(X1, X2) y <- c(y1, y2) study <- sample.int(10, 2000, replace = TRUE) # 10 studies data <- data.frame( Study = study, Y = y, V1 = X[,1], V2 = X[,2] ) # create target study design matrix for covariate profile similarity weighting and # accept/reject algorithm (covaraite-matched study strap) target <- matrix(rnorm(1000, 3, 5), ncol = 2) # design matrix colnames(target) <- c("V1", "V2") ########################## ##### Model Fitting ##### ########################## sseMod <- sse(formula = Y ~., data = data, ssl.method = list("pcr"), ssl.tuneGrid = list(data.frame("ncomp" = 1)), model = FALSE, customFNs = list() ) ## Fit models with Target Study Specified ## # Fit model with 1 Single-Study Learner (SSL): Linear Regression sseMod1 <- sse(formula = Y ~., data = data, target.study = target, ssl.method = list("lm"), ssl.tuneGrid = list(NA), sim.mets = FALSE, model = FALSE, customFNs = list() ) # Fit model with 2 SSLs: Linear Regression and PCA Regression sseMod2 <- sse(formula = Y ~., data = data, target.study = target, ssl.method = list("lm", "pcr"), ssl.tuneGrid = list(NA, data.frame("ncomp" = 1)), sim.mets = TRUE, model = FALSE, customFNs = list() ) # Fit model with custom similarity function for # covaraite profile similarity weighting fn1 <- function(x1,x2){ return( abs( cor( colMeans(x1), colMeans(x2) )) ) } sseMod3 <- sse(formula = Y ~., data = data, target.study = target, ssl.method = list("lm", "pcr"), ssl.tuneGrid = list(NA, data.frame("ncomp" = 1)), sim.mets = TRUE, model = FALSE, customFNs = list(fn1) ) ######################### ##### Predictions ###### ######################### preds <- studyStrap.predict(sseMod1, target) ```

sse function