select_traits {AnthropMMD}

Select a subset of traits meeting certain criteria

Description

This function provides several strategies to discard some useless traits (non-polymorphic, non-discriminatory, etc.) upstream the MMD analysis.

Usage

select_traits(tab, k = 10, strategy = c("none", "excludeNPT",
"excludeQNPT", "excludeNOMD", "keepFisher"), OMDvalue = NULL, groups,
angular = c("Anscombe", "Freeman"))

Arguments

tab

A table of sample sizes and frequencies, typically returned by the function binary_to_table with the argument relative = TRUE.

k

Numeric value: the required minimal number of individuals per group. Any trait that could be taken on fewer individuals in at least one group will be removed from the dataset. This allows to select only the traits with a sufficient amount of information in each group.

strategy

Strategy for trait selection, i.e. for the removal of non-polymorphic traits. The four options are fully described in Santos (2018) and in the help page of StartMMD.

OMDvalue

To be specified if and only if strategy = "excludeNOMD". Set the desired threshold for the “overall measure of divergence” that must be reached for a trait to be kept.

groups

A factor or character vector, indicating the group to be considered in the analysis. Since some groups can have a very low sample size, this will allow to discard those groups in order to facilitate the trait selection via the argument k. (Otherwise, almost all traits would be removed.)

angular

Formula for angular transformation, see Harris and Sjøvold (2004). Useful only for the calculation of overall measure of divergence.

Value

A list with two components:

filtered

The dataset filtered according to the user-defined criteria.

OMD

The “overall measure of divergence” for each trait.

Author(s)

Frédéric Santos, [e-mail]

References

Harris, E. F. and Sjøvold, T. (2004) Calculation of Smith's mean measure of divergence for intergroup comparisons using nonmetric data. Dental Anthropology, 17(3), 83–93.

Santos, F. (2018) AnthropMMD: an R package with a graphical user interface for the mean measure of divergence. American Journal of Physical Anthropology, 165(1), 200–205. doi: 10.1002/ajpa.23336

See Also

start_mmd

Examples

## Load and visualize a binary dataset:
data(toyMMD)
head(toyMMD)

## Convert this dataframe into a table of sample sizes and
## relative frequencies:
tab <- binary_to_table(toyMMD, relative = TRUE)
tab

## Filter this dataset to keep only those traits that have at
## least k=10 individuals in each group:
select_traits(tab, k = 10)
## Only Trait1 is excluded.

## Filter this dataset to keep only those traits that have at
## least k=11 individuals in each group, and show significant
## differences at Fisher's exact test:
select_traits(tab, k = 11, strategy = "keepFisher")
## Traits 1, 5 and 8 are excluded.