A report to help diagnosing careless responders

This function wraps functions from the careless package to help inspect and diagnose careless participants. It is optimized for using in R Markdown files.

carelessReport(
  data,
  items = names(data),
  nFlags = 1,
  flagUnivar = 0.99,
  flagMultivar = 0.95,
  irvSplit = 4,
  headingLevel = 3,
  datasetName = NULL,
  responseTime = NULL,
  headingSuffix = " {.tabset}",
  digits = 2,
  missingSymbol = "Missing"
)

Arguments

data: The dataframe.
items: The items to look at.
nFlags: How many indicators need to be flagged for a participant to be considered suspect.
flagUnivar: How extreme a score has to be for it to be flagged as suspicous univariately.
flagMultivar: This has not been implemented yet.
irvSplit: Whether to split for the IRV, and if so, in how many parts.
headingLevel: The level of the heading in Markdown (the number of #s to include before the heading).
datasetName: The name of the dataset to display (to override, if desired).
responseTime: If not NULL, the name of a column containing the participants' response times.
headingSuffix: The suffix to include; by default, set such that the individual participants IRP plots are placed in separate tabs.
digits: The number of digits to round to.
missingSymbol: How to represent missing values.

Value

NULL, invisibly; and prints the report.

Examples

### Get the BFI data taken from the `psych` package
dat <- ufs::bfi;

### Get the variable names for the regular items
bfiVars <-
  setdiff(names(dat),
          c("gender", "education", "age"));

### Inspect suspect participants, very conservatively to
### limit the output (these are 2800 participants).
carelessReport(data = dat,
               items = bfiVars,
               nFlags = 5);
#> 
#> Package "careless" needed for this function to work. You can install it using:
#> 
#>   install.packages('careless');