The output generated by R commands is usually not formated for including in reports and so while building Markdown or Latex reports it will be useful to pipe them through one of these packages to make them publication quality

library("knitr")
library("xtable")
library("stargazer")

Packages

the useful packages and commands are

kable

This is a function from knitr that produces tables using dataframe or matrix as input

kable(head(mtcars[,1:4]),
      format = "pandoc", # default
      digits = 2,        # specify decimal places
      caption = "Title of the table",
      col.names = c("miles","cylinders","displacement","horsepower"),
      row.names = TRUE,
      align = c("c"),   # align = c("c","c","c","r")
      # padding = 2     # inner spacing
      )
Title of the table
miles cylinders displacement horsepower
Mazda RX4 21.0 6 160 110
Mazda RX4 Wag 21.0 6 160 110
Datsun 710 22.8 4 108 93
Hornet 4 Drive 21.4 6 258 110
Hornet Sportabout 18.7 8 360 175
Valiant 18.1 6 225 105

xtable

Use this to convert model summaries to data.frames.
let’s use annova model as an example.

data(tli)
fm1 <- aov(tlimth ~ sex + ethnicty + grade + disadvg, data=tli)

Now convert the model into a data.frame using xtable and then use the kable function instead of the print function to print the xtable.

fm1.table <- xtable(fm1)
kable(fm1.table, caption = "Annova table")
Annova table
Df Sum Sq Mean Sq F value Pr(>F)
sex 1 75.37255 75.37255 0.3751912 0.5416830
ethnicty 3 2572.14918 857.38306 4.2679008 0.0071831
grade 1 36.30740 36.30740 0.1807318 0.6717271
disadvg 1 59.30338 59.30338 0.2952017 0.5882062
Residuals 93 18682.86749 200.89105 NA NA

Stargazer

Stargazer is a good option too. Here we show how three different models are compared side by side.

## 2 OLS models
linear.1 <- lm(rating ~ complaints + privileges + learning + raises + critical, data=attitude)
linear.2 <- lm(rating ~ complaints + privileges + learning, data=attitude)
 
## create an indicator dependent variable, and run a probit model
attitude$high.rating <- (attitude$rating > 70)
probit.model <- glm(high.rating ~ learning + critical + advance, data=attitude, family = binomial(link = "probit"))

build a dataframe using the stargazer function and then print using kable. However, in the code chunk below include the option results='hide' to hide the stargazer default output

star.1 <- stargazer(linear.1, linear.2, probit.model,
                    title="Title: Regression Results",
                    align=TRUE,
                    type = "html",
                    style = "ajs", # "ajs"
                    notes="this is a test note"
                    )
kable(star.1)
Title: Regression Results
RATING HIGH.RATING
OLS probit
1 2 3
complaints .692*** .682***
(.149) (.129)
privileges .104 .103
(.135) (.129)
learning .249 .238 .164**
(.160) (.139) (.053)
raises .033
(.202)
critical .015 .001
(.147) (.044)
advance .062
(.042)
Constant 11.011 11.258 -7.476*
(11.704) (7.318) (3.570)
Observations 30 30 30
R2 .715 .715
Adjusted R2 .656 .682
Log Likelihood -9.087
Akaike Inf. Crit. 26.175
Residual Std. Error 7.139 (df = 24) 6.863 (df = 26)
F Statistic 12.063*** (df = 5; 24) 21.743*** (df = 3; 26)
Notes: *P < .05
**P < .01
***P < .001
this is a test note

compare the output with what xtable gives for just one model

kable(xtable(linear.1))
Estimate Std. Error t value Pr(>|t|)
(Intercept) 11.0111304 11.7039358 0.9408058 0.3561782
complaints 0.6920526 0.1488643 4.6488827 0.0001014
privileges -0.1035620 0.1347297 -0.7686650 0.4495906
learning 0.2490613 0.1596189 1.5603496 0.1317680
raises -0.0334606 0.2022762 -0.1654205 0.8699986
critical 0.0154883 0.1472500 0.1051840 0.9171040

The End