DataSum: Comprehensive Data Summarization for Statistical Analysis
Summarizing data frames by calculating various statistical measures, including measures of central tendency, dispersion, skewness(), kurtosis(), and normality tests. The package leverages the 'moments' package for calculating statistical moments and related measures, the 'dplyr' package for data manipulation, and the 'nortest' package for normality testing. 'DataSum' includes functions such as getmode() for finding the mode(s) of a data vector, shapiro_normality_test() for performing the Shapiro-Wilk test (Shapiro & Wilk 1965 <doi:10.1093/biomet/52.3-4.591>) (or the Anderson-Darling test when the data length is outside the valid range for the Shapiro-Wilk test) (Stephens 1974 <doi:10.1080/01621459.1974.10480196>), Datum() for generating a comprehensive summary of a data vector with various statistics (including data type, sample size, mean, mode, median, variance, standard deviation, maximum, minimum, range, skewness(), kurtosis(), and normality test result) (Joanes & Gill 1998 <doi:10.1111/1467-9884.00122>), and DataSumm() for applying the Datum() function to each column of a data frame. Emphasizing the importance of normality testing, the package provides robust tools to validate whether data follows a normal distribution, a fundamental assumption in many statistical analyses and models.
Documentation:
Downloads:
Linking:
Please use the canonical form
https://CRAN.R-project.org/package=DataSum
to link to this page.