SimDesign (version 2.2)

Analyse: Compute estimates and statistics

Description

Compute all relevant test statistics, parameter estimates, detection rates, and so on. This is the computational heavy lifting portion of the Monte Carlo simulation. If a suitable Generate function was not supplied then this function can be used to be generate and analyse the Monte Carlo data (though in general this setup is not recommended for larger simulations).

Usage

Analyse(condition, dat, fixed_objects = NULL)

Arguments

condition

a single row from the design input (as a data.frame), indicating the simulation conditions

dat

the dat object returned from the Generate function (usually a data.frame, matrix, vector, or list)

fixed_objects

object passed down from runSimulation

Value

returns a named numeric vector or data.frame with the values of interest (e.g., p-values, effects sizes, etc), or a list containing values of interest (e.g., separate matrix and vector of parameter estimates corresponding to elements in parameters). If a data.frame is returned with more than 1 row then these objects will be wrapped into suitable list objects

Details

In some cases, it may be easier to change the output to a named list containing different parameter configurations (e.g., when determining RMSE values for a large set of population parameters).

The use of try functions is generally not required in this function because Analyse is internally wrapped in a try call. Therefore, if a function stops early then this will cause the function to halt internally, the message which triggered the stop will be recorded, and Generate will be called again to obtain a different dataset. That said, it may be useful for users to throw their own stop commands if the data should be re-drawn for other reasons (e.g., an estimated model terminated correctly but the maximum number of iterations were reached).

References

Chalmers, R. P., & Adkins, M. C. (2020). Writing Effective and Reliable Monte Carlo Simulations with the SimDesign Package. The Quantitative Methods for Psychology, 16(4), 248-280. 10.20982/tqmp.16.4.p248

Sigal, M. J., & Chalmers, R. P. (2016). Play it again: Teaching statistics with Monte Carlo simulation. Journal of Statistics Education, 24(3), 136-156. 10.1080/10691898.2016.1246953

See Also

stop

Examples

# NOT RUN {
analyse <- function(condition, dat, fixed_objects = NULL) {

    # require packages/define functions if needed, or better yet index with the :: operator
    require(stats)
    mygreatfunction <- function(x) print('Do some stuff')

    #wrap computational statistics in try() statements to control estimation problems
    welch <- t.test(DV ~ group, dat)
    ind <- stats::t.test(DV ~ group, dat, var.equal=TRUE)

    # In this function the p values for the t-tests are returned,
    #  and make sure to name each element, for future reference
    ret <- c(welch = welch$p.value,
             independent = ind$p.value)

    return(ret)
}

# }