# Change in Length of Stay The function estimates the expected change in length of stay (LOS) associated with an intermediate event. ```r clos(x, aw, ratio, ...) ## S3 method for class 'etm' clos(x, aw = FALSE, ratio = FALSE, ...) ## S3 method for class 'msfit' clos(x, aw = FALSE, ratio = FALSE, cox_model, ...) ``` ## Arguments - `x`: An object of class `etm`. Argument `delta.na` in `etm` must be set to `TRUE` in order to use this function. - `aw`: Logical. Whether to compute the expected change of LOS using alternative weighting. Default is `FALSE`. - `ratio`: Logical. Compute the ratio of the expected length-of-stay given instermediate event status instead of a difference. Default value is `FALSE` - `cox_model`: TODO - `...`: Further arguments ## Details The approach for evaluating the impact of an intermediate event on the expected change in length of stay is based on Schulgen and Schumacher (1996). They suggested to consider the difference of the expected subsequent stay given infectious status at time s. Extensions to the methods of Schulgen and Schumacher and the earlier implementation in the `changeLOS` include the possibility to compute the extra length of stay both for competing endpoints and the more simple case of one absorbing state, as well as the possibility to compute this quantity for left-truncated data. ## Returns An object of class `clos.etm` with the following components: - **e.phi**: Change in length of stay - **phi.case**: Estimates of $E(LOS | X_s = intermediate event)$ for all observed transition times $s$, where $X_s$denotes the state by time $s$ - **phi.control**: Estimates of $E(LOS|X_s = initial state)$ for all observed transition times $s$. - **e.phi2**: Weighted average of the difference between `phi2.case` and `phi2.control`. - **phi2.case**: Estimates of c("$E(LOS \\strong{1}(X_LOS = discharge)|X_s =\n$", "$ intermediate event)$"), where $\strong{1}$ denotes the indicator function. - **phi2.control**: c("$E(LOS \\strong{1}(X_LOS = discharge)|X_s =\n$", "$ initial state)$"). - **e.phi3**: Weighted average of the difference between `phi3.case` and `phi3.control`. - **phi3.case**: Estimates of c("$E(LOS \\strong{1}(X_LOS = death)|X_s =\n$", "$ intermediate event)$"). - **phi3.control**: c("$E(LOS \\strong{1}(X_LOS = death)|X_s =\n$", "$ initial state)$"). - **weights**: Weights used to compute the weighted averages. - **w.time**: Times at which the weights are computed. - **time**: All transition times. - **e.phi.weights.1**: Expected change in LOS using `weights.1` - **e.phi.weights.other**: Expected change in LOS using `weights.other` - **weights.1**: Weights corresponding to the conditional waiting time in the intial state given one experiences the intermediate event. - **weights.other**: Weights corresponding to the conditional waiting time given one does not experience the intermediate event. ## References G Schulgen and M Schumacher (1996). Estimation of prolongation of hospital stay attributable to nosocomial infections. **Lifetime Data Analysis** 2, 219-240. J Beyersmann, P Gastmeier, H Grundmann, S Baerwolf, C Geffers, M Behnke, H Rueden, and M Schumacher (2006). Use of Multistate Models to Assess Prolongation of Intensive Care Unit Stay Due to Nosocomial Infection. **Infection Control and Hospital Epidemiology** 27, 493-499. Allignol A, Schumacher M, Beyersmann J: Estimating summary functionals in multistate models with an application to hospital infection data. **Computation Stat**, 2011; 26: 181-197. M Wrangler, J Beyersmann and M Schumacher (2006). changeLOS: An R-package for change in length of hospital stay based on the Aalen-Johansen estimator. **R News** 6(2), 31--35. ## Author(s) Arthur Allignol arthur.allignol@gmail.com , Matthias Wangler, Jan Beyersmann ## See Also `etm` ## Examples ```r data(los.data) ## putting los.data in the long format my.observ <- prepare.los.data(x=los.data) tra <- matrix(FALSE, 4, 4) tra[1, 2:4] <- TRUE tra[2, 3:4] <- TRUE tr.prob <- etm(my.observ, c("0","1","2","3"), tra, NULL, 0) cLOS <- etm::clos(tr.prob) plot(cLOS) ### Compute bootstrapped SE ## function that performs the bootstrap ## nboot: number of bootstrap samples. Other arguments are as in etm() boot.clos <- function(data, state.names, tra, cens.name, s = 0, nboot) { res <- double(nboot) for (i in seq_len(nboot)) { index <- sample(unique(data$id), replace = TRUE) inds <- new.id <- NULL for (j in seq_along(index)){ ind <- which(data$id == index[j]) new.id <- c(new.id, rep(j, length(ind))) inds <- c(inds, ind) } dboot <- cbind(data[inds, ], new.id) dboot[, which(names(dboot) == "id")] dboot$id <- dboot$new.id tr.prob <- etm(dboot, state.names, tra, cens.name, s, cova = FALSE) res[i] <- etm::clos(tr.prob)$e.phi } res } ## bootstrap se <- sqrt(var(boot.clos(my.observ, c("0","1","2","3"), tra, NULL, 0, nboot = 10))) ```

clos function