var_tests {neatStats}

Variance Equality Tests

Description

Displayed sample sizes and SDs and performs Brown-Forsythe and Fligner-Killeen variance equality tests (tests of homogeneity of variances) per group combinations. This is primarily a subfunction of anova_neat, but here it is available separately for other potential purposes.

Usage

var_tests(xvar, group_by, dat = NULL, hush = FALSE, sep = ", ")

Arguments

xvar

Either a numeric vector (numbers of any given variable), or, if dat is given, a column name specifying the variable in the given data frame.

group_by

Either a vector of factors with which to group the xvar values, or, if dat is given, one or more column names specifying the columns in the given data frame.

dat

Either NULL or a data frame from which the respective column names should be selected for xvar and group.

hush

Logical. If TRUE, prevents printing any details to console.

sep

String (underscore "_" by default) for separating group names.

Value

Prints test results.

Note

Brown-Forsythe test (i.e., Levene's test using medians) is calculated via car::leveneTest. Fligner-Killeen test, which may be more robust (i.e., less affected by non-normal distribution), is calculated via stats::fligner.test. (See also Conover et al., 1981, p. 360.)

References

Brown, M. B. & Forsythe, A. B. (1974). Robust tests for the equality of variances. Journal of the American Statistical Association, 69, pp. 364-367.

Conover W. J., Johnson M. E., & Johnson M. M. (1981). A comparative study of tests for homogeneity of variances, with applications to the outer continental shelf bidding data. Technometrics, 23, 351–361.

Fligner, M. A. & Killeen, T. J. (1976). Distribution-free two-sample tests for scale. ‘Journal of the American Statistical Association. 71(353), 210-213.

Fox, J. & Weisberg, S. (2019) An R Companion to Applied Regression, Third Edition, Sage.

Levene, H. (1960). Robust tests for equality of variances. In I. Olkin, H. Hotelling, et al. (eds.). Contributions to Probability and Statistics: Essays in Honor of Harold Hotelling. Stanford University Press. pp. 278–292.

See Also

anova_neat

Examples

data("ToothGrowth") # load base R example dataset

# the statistics of the four functions below should match
var_tests(ToothGrowth$len, ToothGrowth$supp)
var_tests('len', 'supp', ToothGrowth)
car::leveneTest(len ~ supp, data = ToothGrowth)
stats::fligner.test(len ~ supp, ToothGrowth)

# again the results below should match each other
var_tests(ToothGrowth$len,
          interaction(ToothGrowth$supp, ToothGrowth$dose))
var_tests('len', c('supp', 'dose'), ToothGrowth)
car::leveneTest(len ~ supp * as.factor(dose), data = ToothGrowth)
stats::fligner.test(len ~ interaction(supp, dose), ToothGrowth)