Skip to content

Violets are BLUE. OLS is too. (R package)

License

Unknown, MIT licenses found

Licenses found

Unknown
LICENSE
MIT
LICENSE.md
Notifications You must be signed in to change notification settings

vincentarelbundock/violets

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Violets are BLUE. OLS is too.

violets is a package for R which re-estimates fancy statistical models using simple OLS.

Original idea by @abhworthington. Hex logo by @researchremora. Thanks!

Install and load:

# install from github
library(remotes)
install_github('vincentarelbundock/violets')
# load
library(violets)

Your Poisson model of horse kicks to the head could be BLUE:

url <- 'https://vincentarelbundock.github.io/Rdatasets/csv/pscl/prussian.csv'
dat <- read.csv(url, stringsAsFactors = FALSE)

mod <- glm(y ~ corp + year, data = dat, family = 'poisson')
violets(mod)
## Violets are BLUE. OLS is too.

## 
## Call:
## stats::lm(formula = f, data = mf)
## 
## Coefficients:
## (Intercept)        corpI       corpII      corpIII       corpIV       corpIX  
##  -3.073e-01   -1.874e-15   -2.000e-01   -2.000e-01   -4.000e-01   -1.500e-01  
##       corpV       corpVI      corpVII     corpVIII        corpX       corpXI  
##  -2.500e-01    5.000e-02   -2.000e-01   -4.500e-01   -5.000e-02    4.500e-01  
##     corpXIV       corpXV         year  
##   4.000e-01   -4.000e-01    1.310e-02

Your probit model of deaths aboard the titanic could be BLUE:

url <- 'http://vincentarelbundock.github.io/Rdatasets/csv/Stat2Data/Titanic.csv'
dat <- read.csv(url, stringsAsFactors = FALSE)

mod <- glm(Survived ~ Sex + Age + PClass, data = dat, family = binomial(link = 'probit'))
violets(mod)
## Violets are BLUE. OLS is too.

## 
## Call:
## stats::lm(formula = f, data = mf)
## 
## Coefficients:
## (Intercept)      Sexmale          Age    PClass2nd    PClass3rd  
##    1.130523    -0.501326    -0.006005    -0.207434    -0.393344

Your ordered logit model of ??? could be BLUE:

library(MASS)
url <- 'https://vincentarelbundock.github.io/Rdatasets/csv/geepack/koch.csv'
dat <- read.csv(url, stringsAsFactors = FALSE)

dat$y <- as.factor(dat$y)
mod <- polr(y ~ day + trt, data = dat)

violets(mod)
## Violets are BLUE. OLS is too.

## 
## Call:
## stats::lm(formula = f, data = mf)
## 
## Coefficients:
## (Intercept)          day          trt  
##     2.70219     -0.06464     -0.36806

About

Violets are BLUE. OLS is too. (R package)

Resources

License

Unknown, MIT licenses found

Licenses found

Unknown
LICENSE
MIT
LICENSE.md

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages