condesc.RdMeasures the association between a continuous variable and some continuous and/or categorical variables
condesc(y, x, weights = NULL,
na.rm.cat = FALSE, na.value.cat = "NAs", na.rm.cont = FALSE,
limit = NULL, correlation = "kendall", robust = TRUE,
nperm = NULL, distrib = "asympt", digits = 2)the continuous variable to describe
a data frame with continuous and/or categorical variables
numeric vector of weights. If NULL (default), uniform weights (i.e. all equal to 1) are used.
logical, indicating whether NA values in the categorical variables should be silently removed before the computation proceeds. If FALSE (default), an additional level is added to the categorical variables (see na.value.cat argument).
character. Name of the level for NA category. Default is "NAs". Only used if na.rm.cat = FALSE.
logical, indicating whether NA values in the continuous variables should be silently removed before the computation proceeds. Default is FALSE.
for the relationship between y and a category of a categorical variable, only associations (point-biserial correlations) higher or equal to limit will be displayed. If NULL (default), they are all displayed.
character. The type of correlation measure to use between two continuous variables : "pearson", "spearman" or "kendall" (default).
logical. If TRUE (default), meadian and mad are used instead of mean and standard deviation.
numeric. Number of permutations for the permutation test of independence. If NULL (default), no permutation test is performed.
the null distribution of permutation test of independence can be approximated by its asymptotic distribution ("asympt", default) or via Monte Carlo resampling ("approx").
numeric. Number of digits for mean, median, standard deviation and mad. Default is 2.
A list of the following items :
associations between y and the variables in x
a data frame with categorical variables from x and associations measured by point biserial correlation.
If nperm is not NULL, permutation tests of independence are computed and the p-values from these tests are provided.
Rakotomalala R., 'Comprendre la taille d'effet (effect size)', [http://eric.univ-lyon2.fr/~ricco/cours/slides/effect_size.pdf]
data(Movies)
condesc(Movies$BoxOffice, Movies[,c("Budget","Genre","Country")])
#> $variables
#> variable measure association
#> 1 Genre Eta2 0.173
#> 2 Country Eta2 0.048
#> 3 Budget Kendall tau 0.518
#>
#> $categories
#> categories median.in.category overall.median mad.in.category
#> 1 Genre.SciFi 680900.0 107326.5 607448.0
#> 2 Genre.Animation 668896.0 107326.5 633265.0
#> 3 Country.USA 328559.0 107326.5 274892.0
#> 4 Genre.Action 240080.0 107326.5 202793.0
#> 5 Country.Europe 108121.5 107326.5 104606.5
#> 6 Genre.Comedy 202090.0 107326.5 191819.0
#> 7 Genre.Other 186084.5 107326.5 171739.5
#> 8 Country.Other 55643.0 107326.5 37068.5
#> 9 Genre.Horror 302635.0 107326.5 171803.0
#> 10 Genre.Documentary 9303.0 107326.5 7890.0
#> 11 Genre.ComDram 67341.0 107326.5 64317.0
#> 12 Genre.Drama 37160.0 107326.5 34368.0
#> 13 Country.France 57140.0 107326.5 54425.0
#> overall.mad correlation
#> 1 104060 0.294
#> 2 104060 0.211
#> 3 104060 0.192
#> 4 104060 0.087
#> 5 104060 0.068
#> 6 104060 0.004
#> 7 104060 -0.005
#> 8 104060 -0.013
#> 9 104060 -0.015
#> 10 104060 -0.108
#> 11 104060 -0.114
#> 12 104060 -0.162
#> 13 104060 -0.211
#>