The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

Semi-Distance Correlation and MV Index: Measure Dependence Between Categorical and Continuous Variables

The goal of package semidist is to provide an easy way to implement the semi-distance methods (Zhong et al., 2023) and MV index methods (Cui, Li and Zhong, 2015; Cui and Zhong, 2019).

Installation

To install semidist,

install.packages("semidist")

Example

Here is a simple example showing how to use semidist to measure the dependence between a categorical variable and a multivariate continuous variable, and apply the measure on testing the independence and conduct groupwise feature screening.

library(semidist)
X <- mtcars[, c("mpg", "disp", "drat", "wt")]
y <- factor(mtcars[, "am"])

sdcov(X, y)
#> [1] 31.78288
sdcor(X, y)
#> [1] 0.3489821

sd_test(X, y)
#> 
#>  Semi-Distance Independence Test (Permutation Test with K = 10000)
#> 
#> Data: X and y,   Sample size = 32
#> Test statistic = 940.344,    p-value = 0.0005999
#> Alternative hypothesis: Two random variables are not independent

sd_sis(X, y, d = 2)
#> $group_info
#> $group_info$`Grp mpg`
#> [1] "mpg"
#> 
#> $group_info$`Grp disp`
#> [1] "disp"
#> 
#> $group_info$`Grp drat`
#> [1] "drat"
#> 
#> $group_info$`Grp wt`
#> [1] "wt"
#> 
#> 
#> $measurement
#>   Grp mpg  Grp disp  Grp drat    Grp wt 
#> 0.3447938 0.3488447 0.5054821 0.5358834 
#> 
#> $selected
#> [1] "wt"   "drat"
#> 
#> $ordering
#> [1] "Grp wt"   "Grp drat" "Grp disp" "Grp mpg"

# Suppose we have prior information for the group structure as
# ("mpg", "drat"), ("disp", "hp") and ("wt", "qsec")
group_info <- list(
  mpg_drat = c("mpg", "drat"),
  disp_wt = c("disp", "wt")
)
sd_sis(X, y, group_info, d = 2)
#> $group_info
#> $group_info$mpg_drat
#> [1] "mpg"  "drat"
#> 
#> $group_info$disp_wt
#> [1] "disp" "wt"  
#> 
#> 
#> $measurement
#>  mpg_drat   disp_wt 
#> 0.3518051 0.3488598 
#> 
#> $selected
#> [1] "mpg"  "drat"
#> 
#> $ordering
#> [1] "mpg_drat" "disp_wt"

References

1. Wei Zhong, Zhuoxi Li, Wenwen Guo and Hengjian Cui. (2023) “Semi-Distance Correlation and Its Applications.” Journal of the American Statistical Association.
2. Hengjian Cui and Wei Zhong (2019). “A Distribution-Free Test of Independence Based on Mean Variance Index.” Computational Statistics & Data Analysis, 139, 117-133.
3. Hengjian Cui, Runze Li and Wei Zhong (2015). “Model-Free Feature Screening for Ultrahigh Dimensional Discriminant Analysis.” Journal of the American Statistical Association, 110, 630-641.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.