MESS

Miscellaneous Esoteric Statistical Scripts - an R package

https://github.com/ekstroem/mess

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (15.0%) to scientific vocabulary

Keywords

biostatistics power-analysis statistical-analysis statistical-methods statistical-models
Last synced: 6 months ago · JSON representation

Repository

Miscellaneous Esoteric Statistical Scripts - an R package

Basic Info
  • Host: GitHub
  • Owner: ekstroem
  • Language: R
  • Default Branch: master
  • Homepage:
  • Size: 8.22 MB
Statistics
  • Stars: 4
  • Watchers: 2
  • Forks: 9
  • Open Issues: 1
  • Releases: 0
Topics
biostatistics power-analysis statistical-analysis statistical-methods statistical-models
Created almost 11 years ago · Last pushed 7 months ago
Metadata Files
Readme Changelog

README.md

MESS

Development version of the R package MESS (Miscellaneous Esoteric Statistical Scripts). This package contains a collection of various semi-useful functions that I have written and over the years.

There is no real overall theme to the functions in the package but I have tried to group the contents in the overview below.

To install the development version of MESS run the following command from within R (this requires that the devtools package is already installed on the system.)

r devtools::install_github('ekstroem/MESS')

Travis-CI Build Status Download counter

Package overview

The list below is far from complete.

Statistical functions

  • cmd - Correlation matrix distance. A measure of the similarity of two matrices of equal dimensions.
  • drop1.geeglm - A drop1 extension for geeglm objects
  • gkgamma - compute Goodman-Kruskal's gamma statistic for a two-dimensional table of ordered categories
  • monte_carlo_chisq_test - Monte Carlo tests of 2x2 tables with fixed margin(s). Also works for r x c tables.
  • mfastLmCpp - fast computation of simple regression slopes for each predictor represented by a column in a matrix
  • ks_cumtest - One-sample Kolmogorov-Smirnov discrete cumulative comparison.
  • qic -
  • rud - Randomized treatments for an RCT based on an urn model
  • screenr -

Power calculations are - for better or worse - part of my job, and while I generally recommend researchers to simulate their design and test procedure, there are some benefits to be gained from asymptotic approximations in standard designs.

In time these will be moved to the Austin package, but for now they still reside in MESS.

  • power_prop_test extends the standard power.prop.test function to accommodate different group sizes.
  • power_t_test extends the standard power.t.test function to accommodate different group sizes and/or variances.
  • power_mcnemar_test - power calculations for exact and asymptotic McNemar test in a 2 by 2 table
  • power_binom_test - power calculations for exact test of a simple null hypothesis in a Bernoulli experiment

Graphical functions

  • col.shade
  • col.tint
  • col.alpha
  • rootonorm - plot Tukey's hanging root-o-gram for comparison of a histogram to a normal distribution.
  • wallyplot - plot a Wally plot for evaluation of a residual plot.

Utility functions

  • age - computes the age in years of a person from two date (birth date and current date)
  • auc - computes the area under the curve for two vectors (x-values and y-values). Can handle ranges and missing observations
  • categorize - produce tables using a data argument
  • colCumSum - fast computation of column cumulative sums for matrices
  • expand_table - Expand table or matrix to data frame where each observation in the table becomes a single observation in the data frame with corresponding information for each for each combination of the table dimensions.
  • fac2num - convert a factor to numerical. I keep forgetting the simple code for this so ended up writing a function that could do it.
  • filldown - Fill down missing values in a vector with the latest non-missing value. A last measurement carried forward function. And fast.
  • lower.tri.vector -
  • write.xml - save a data frame as an xml file

Computational functions

  • conditional_rowMeans - a function similar to rowMeans but it only returns the mean if a prespecified number of observations is available.
  • pairwise_Schur_product - compute Schur products (element-wise) of all pairwise combinations of columns in matrix
  • qdiag - fast extraction of matrix diagonal
  • quadform - fast computation of a quadratic form t(X) %*% M %*% X
  • repmat - fast replication of a matrix. Can be replicated both row-wise and columns-wise.
  • sinv - invert a symmetric positive-definite matrix. Some speedup can be gained if we know the matrix is symmetric
  • tracemp - fast computation of trace of matrix product trace(t(A) %*% B)

Datasets

  • bdstat - Monthly live births and deaths in Denmark from January 1901 to March 2013
  • earthquakes - Information on earthquakes worldwide in 2015 with a magnitude greater than 3 on the Richter scale.
  • happiness - Data on happiness, taxation rates, countris and continents
  • kwdata - example data to show that Krushkal-Wallis' test examines more than differences in medians.
  • soccer - List of players on the Danish national soccer team

Owner

  • Name: Claus Ekstrøm
  • Login: ekstroem
  • Kind: user
  • Location: Copenhagen, Denmark
  • Company: University of Copenhagen

Statistician, scientist, researcher, R tinkerer

GitHub Events

Total
  • Issues event: 3
  • Issue comment event: 3
  • Push event: 4
Last Year
  • Issues event: 3
  • Issue comment event: 3
  • Push event: 4

Committers

Last synced: over 2 years ago

All Time
  • Total Commits: 267
  • Total Committers: 4
  • Avg Commits per committer: 66.75
  • Development Distribution Score (DDS): 0.052
Past Year
  • Commits: 1
  • Committers: 1
  • Avg Commits per committer: 1.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
ekstroem g****b@e****m 253
ekstroem g****b@e****k 10
Niels Olsen t****s@h****k 3
James Jenkins j****s@j****e 1
Committer Domains (Top 20 + Academic)

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 9
  • Total pull requests: 2
  • Average time to close issues: 4 months
  • Average time to close pull requests: 2 days
  • Total issue authors: 9
  • Total pull request authors: 2
  • Average comments per issue: 2.44
  • Average comments per pull request: 0.5
  • Merged pull requests: 2
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • thorwb (1)
  • shahronak47 (1)
  • katherineking4 (1)
  • ekstroem (1)
  • timktsang (1)
  • atzs-hun (1)
  • sfn-mes (1)
  • shunranw (1)
  • genejockey (1)
Pull Request Authors
  • james-jenkins (1)
  • naolsen (1)
Top Labels
Issue Labels
bug (2)
Pull Request Labels

Packages

  • Total packages: 2
  • Total downloads:
    • cran 2,027 last-month
  • Total docker downloads: 42,026
  • Total dependent packages: 13
    (may contain duplicates)
  • Total dependent repositories: 9
    (may contain duplicates)
  • Total versions: 20
  • Total maintainers: 1
cran.r-project.org: MESS

Miscellaneous Esoteric Statistical Scripts

  • Versions: 16
  • Dependent Packages: 12
  • Dependent Repositories: 9
  • Downloads: 2,027 Last month
  • Docker Downloads: 42,026
Rankings
Dependent packages count: 4.6%
Forks count: 7.9%
Downloads: 8.5%
Dependent repos count: 9.8%
Average: 13.3%
Stargazers count: 23.6%
Docker downloads count: 25.7%
Maintainers (1)
Last synced: 6 months ago
conda-forge.org: r-mess
  • Versions: 4
  • Dependent Packages: 1
  • Dependent Repositories: 0
Rankings
Dependent packages count: 28.8%
Dependent repos count: 34.0%
Average: 40.8%
Forks count: 44.7%
Stargazers count: 55.7%
Last synced: 6 months ago

Dependencies

DESCRIPTION cran
  • R >= 3.5 depends
  • MASS * imports
  • Matrix * imports
  • Rcpp * imports
  • clipr * imports
  • geeM * imports
  • geepack * imports
  • ggformula * imports
  • ggplot2 * imports
  • glmnet * imports
  • kinship2 * imports
  • methods * imports
  • mvtnorm * imports
  • parallel * imports
  • knitr * suggests
  • lme4 * suggests
  • magrittr * suggests
  • rmarkdown * suggests
  • testthat * suggests