analyse {rbmi}

Analyse Multiple Imputed Datasets

Description

This function takes multiple imputed datasets (as generated by the impute() function) and runs an analysis function on each of them.

Usage

analyse(imputations, fun = ancova, delta = NULL, ...)

Arguments

imputations

An imputations object as created by impute().

fun

An analysis function to be applied to each imputed dataset. See details.

delta

A data.frame containing the delta transformation to be applied to the imputed datasets prior to running fun. See details.

...

Additional arguments passed onto fun.

Details

This function works by performing the following steps:

1. Extract a dataset from the imputations object.

2. Apply any delta adjustments as specified by the delta argument.

3. Run the analysis function fun on the dataset.

4. Repeat steps 1-3 across all of the datasets inside the imputations object.

5. Collect and return all of the analysis results.

The analysis function fun must take a data.frame as its first argument. All other options to analyse() are passed onto fun via .... fun must return a named list with each element itself being a list containing a single numeric element called est (or additionally se and df if you had originally specified method_bayes() or method_approxbayes()) i.e.:

myfun <- function(dat, ...) {
    mod_1 <- lm(data = dat, outcome ~ group)
    mod_2 <- lm(data = dat, outcome ~ group + covar)
    x <- list(
        trt_1 = list(
            est = coef(mod_1)[[group]],
            se = sqrt(vcov(mod_1)[group, group]),
            df = df.residual(mod_1)
        ),
        trt_2 = list(
            est = coef(mod_2)[[group]],
            se = sqrt(vcov(mod_2)[group, group]),
            df = df.residual(mod_2)
        )
     )
     return(x)
 }

Please note that the vars$subjid column (as defined in the original call to draws()) will be scrambled in the data.frames that are provided to fun. This is to say they will not contain the original subject values and as such any hard coding of subject ids is strictly to be avoided.

By default fun is the ancova() function. Please note that this function requires that a vars object, as created by set_vars(), is provided via the vars argument e.g. analyse(imputeObj, vars = set_vars(...)). Please see the documentation for ancova() for full details. Please also note that the theoretical justification for the conditional mean imputation method (method = method_condmean() in draws()) relies on the fact that ANCOVA is a linear transformation of the outcomes. Thus care is required when applying alternative analysis functions in this setting.

The delta argument can be used to specify offsets to be applied to the outcome variable in the imputed datasets prior to the analysis. This is typically used for sensitivity or tipping point analyses. The delta dataset must contain columns vars$subjid, vars$visit (as specified in the original call to draws()) and delta. Essentially this data.frame is merged onto the imputed dataset by vars$subjid and vars$visit and then the outcome variable is modified by:

imputed_data[[vars$outcome]] <- imputed_data[[vars$outcome]] + imputed_data[["delta"]]

Please note that in order to provide maximum flexibility, the delta argument can be used to modify any/all outcome values including those that were not imputed. Care must be taken when defining offsets. It is recommend that you use the helper function delta_template() to define the delta datasets as this provides utility variables such as is_missing which can be used to identify exactly which visits have been imputed.

See Also

extract_imputed_dfs() for manually extracting imputed datasets.

delta_template() for creating delta data.frames.

ancova() for the default analysis function.

Examples

## Not run: 
vars <- set_vars(
    subjid = "subjid",
    visit = "visit",
    outcome = "outcome",
    group = "group",
    covariates = c("sex", "age", "sex*age")
)

analyse(
    imputations = imputeObj,
    vars = vars
)

deltadf <- data.frame(
    subjid = c("Pt1", "Pt1", "Pt2"),
    visit = c("Visit_1", "Visit_2", "Visit_2"),
    delta = c( 5, 9, -10)
)

analyse(
    imputations = imputeObj,
    delta = deltadf,
    vars = vars
)

## End(Not run)