%% LyX 2.0.2 created this file.  For more info, see http://www.lyx.org/.
%% Do not edit unless you really know what you are doing.
\documentclass[11pt,english]{article}
\usepackage{ae,aecompl}
\renewcommand{\familydefault}{\rmdefault}
\usepackage[T1]{fontenc}
\usepackage[latin9]{inputenc}
\usepackage{geometry}
\geometry{verbose,tmargin=1in,bmargin=1in,lmargin=1in,rmargin=1in}
\usepackage{babel}
\usepackage{setspace}
\onehalfspacing
\usepackage[unicode=true]
 {hyperref}

\makeatletter
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% User specified LaTeX commands.
%\VignetteIndexEntry{stargazer}
\usepackage{dcolumn}

\makeatother

\begin{document}

\title{stargazer: \\
beautiful \LaTeX{}, HTML and ASCII tables from R statistical output}


\author{Marek Hlavac}
\maketitle

\section{Introduction}

\emph{stargazer} is an R package that creates \LaTeX{} code, HTML code and ASCII
text for well-formatted regression tables, with multiple models side-by-side,
as well as for summary statistics tables, data frames, vectors and matrices.


\section{Why Should I Use \emph{stargazer}?}

Compared to available alternatives, \emph{stargazer} excels in at
least three respects: its ease of use, the large number of models
it supports, and its beautiful aesthetics. These advantages have made
it the R-to-\LaTeX{} package of choice for many satisfied users at
research and teaching institutions around the world.


\subsection{Ease of Use}

\emph{stargazer} was designed with the user's comfort in mind. The
learning curve is very mild, and all arguments are very intuitive,
so that even a beginning user of R or \LaTeX{} can quickly become
familiar with the package's many capabilities. The package is intelligent,
and tries to minimize the amount of effort the user has to put into
adjusting argument values.

If \emph{stargazer} is given a set of regression model objects, for
instance, the package will create a side-by-side regression table.
By contrast, if the user feeds it a data frame, \emph{stargazer} will
know that the user is most likely looking for a summary statistics
table or -- if the \emph{summary} argument is set to FALSE -- wants
to output the content of the data frame.\newpage{}

A quick reproducible example shows just how easy \emph{stargazer}
is to use. You can install \emph{stargazer} from CRAN in the usual
way:\\


\noindent \verb|install.packages("stargazer")| \newline
\verb|library(stargazer)| \newline

To create a summary statistics table from the \emph{`attitude'} data
frame (which should be available with your default installation of
R), simply run the following:\\


\noindent \verb|stargazer(attitude)| 

\begin{table}[!htbp] \centering    \caption{}    \label{}  \begin{tabular}{@{\extracolsep{5pt}}lccccc}  \\[-1.8ex]\hline  \hline \\[-1.8ex]  Statistic & \multicolumn{1}{c}{N} & \multicolumn{1}{c}{Mean} & \multicolumn{1}{c}{St. Dev.} & \multicolumn{1}{c}{Min} & \multicolumn{1}{c}{Max} \\  \hline \\[-1.8ex]  rating & 30 & 64.633 & 12.173 & 40 & 85 \\  complaints & 30 & 66.600 & 13.315 & 37 & 90 \\  privileges & 30 & 53.133 & 12.235 & 30 & 83 \\  learning & 30 & 56.367 & 11.737 & 34 & 75 \\  raises & 30 & 64.633 & 10.397 & 43 & 88 \\  critical & 30 & 74.767 & 9.895 & 49 & 92 \\  advance & 30 & 42.933 & 10.289 & 25 & 72 \\  high.rating & 30 & 0.333 & 0.479 & 0 & 1 \\  \hline \\[-1.8ex]  \normalsize  \end{tabular}  \end{table}

To output the contents of the first four rows of some data frame,
specify the part of the data frame you would like to see, and set
the \emph{summary} option to FALSE:\\


\noindent \verb|stargazer(attitude[1:4,], summary=FALSE, rownames=FALSE)| 

\begin{table}[!htbp] \centering    \caption{}    \label{}  \begin{tabular}{@{\extracolsep{5pt}} cccccccc}  \\[-1.8ex]\hline  \hline \\[-1.8ex]  rating & complaints & privileges & learning & raises & critical & advance & high.rating \\  \hline \\[-1.8ex]  $43$ & $51$ & $30$ & $39$ & $61$ & $92$ & $45$ & FALSE \\  $63$ & $64$ & $51$ & $54$ & $63$ & $73$ & $47$ & FALSE \\  $71$ & $70$ & $68$ & $69$ & $76$ & $86$ & $48$ & TRUE \\  $61$ & $63$ & $45$ & $47$ & $54$ & $84$ & $35$ & FALSE \\  \hline \\[-1.8ex]  \normalsize  \end{tabular}  \end{table}  

Now, let us try to create a simple regression table with three side-by-side
models -- two Ordinary Least Squares (OLS) and one probit regression
model -- using the \emph{lm()} and \emph{glm()} functions. We can
set the\emph{ align} argument to TRUE, so that coefficients in each
column are aligned along the decimal point. \emph{Table 3} shows the
result.\newpage{}

\noindent \verb|##  2 OLS models| \newline
\verb|linear.1 <- lm(rating ~ complaints + privileges + learning + raises + critical,| \newline
\verb|data=attitude)| \newline
\verb|linear.2 <- lm(rating ~ complaints + privileges + learning, data=attitude)| \newline
\verb|## create an indicator dependent variable, and run a probit model| \newline
\verb|attitude$high.rating <- (attitude$rating > 70)| \newline
\verb|probit.model <- glm(high.rating ~ learning + critical + advance, data=attitude,| \newline
\verb|family = binomial(link = "probit"))| \newline \newline
\verb|stargazer(linear.1, linear.2, probit.model, title="Results", align=TRUE)|\begin{table}[htb] \centering    \caption{Results}    \label{}  \footnotesize 
\begin{tabular}{@{\extracolsep{5pt}}lD{.}{.}{-3} D{.}{.}{-3} D{.}{.}{-3} }  \\[-1.8ex]\hline  \hline \\[-1.8ex]   & \multicolumn{3}{c}{\textit{Dependent variable:}} \\  \cline{2-4}  \\[-1.8ex] & \multicolumn{2}{c}{rating} & \multicolumn{1}{c}{high.rating} \\  \\[-1.8ex] & \multicolumn{2}{c}{\textit{OLS}} & \multicolumn{1}{c}{\textit{probit}} \\  \\[-1.8ex] & \multicolumn{1}{c}{(1)} & \multicolumn{1}{c}{(2)} & \multicolumn{1}{c}{(3)}\\  \hline \\[-1.8ex]   complaints & 0.692^{***} & 0.682^{***} &  \\    & (0.149) & (0.129) &  \\    & & & \\   privileges & -0.104 & -0.103 &  \\    & (0.135) & (0.129) &  \\    & & & \\   learning & 0.249 & 0.238^{*} & 0.164^{***} \\    & (0.160) & (0.139) & (0.053) \\    & & & \\   raises & -0.033 &  &  \\    & (0.202) &  &  \\    & & & \\   critical & 0.015 &  & -0.001 \\    & (0.147) &  & (0.044) \\    & & & \\   advance &  &  & -0.062 \\    &  &  & (0.042) \\    & & & \\   Constant & 11.011 & 11.258 & -7.476^{**} \\    & (11.704) & (7.318) & (3.570) \\    & & & \\  \hline \\[-1.8ex]  Observations & \multicolumn{1}{c}{$30$} & \multicolumn{1}{c}{$30$} & \multicolumn{1}{c}{$30$} \\  R$^{2}$ & \multicolumn{1}{c}{$0.715$} & \multicolumn{1}{c}{$0.715$} &  \\  Adjusted R$^{2}$ & \multicolumn{1}{c}{$0.656$} & \multicolumn{1}{c}{$0.682$} &  \\  Log likelihood &  &  & \multicolumn{1}{c}{$-9.087$} \\  Akaike Inf. Crit. & \multicolumn{1}{c}{210.375} & \multicolumn{1}{c}{206.412} & \multicolumn{1}{c}{26.175} \\ Bayesian Inf. Crit. & \multicolumn{1}{c}{220.183} & \multicolumn{1}{c}{213.418} & \multicolumn{1}{c}{31.780} \\   Residual Std. Error & \multicolumn{1}{c}{$7.139 (df = 24)$} & \multicolumn{1}{c}{$6.863 (df = 26)$} &  \\  F statistic & \multicolumn{1}{c}{$12.063^{***} (df = 5; 24)$} & \multicolumn{1}{c}{$21.743^{***} (df = 3; 26)$} &  \\  \hline  \hline \\[-1.8ex]  \textit{Note:}  & \multicolumn{3}{r}{$^{*}$p$<$0.1; $^{**}$p$<$0.05; $^{***}$p$<$0.01} \\  \normalsize  \end{tabular}  \end{table}

\newpage{}

In \emph{Table 4}, we go a little bit further, and make some formatting
and labeling adjustments. In particular, we remove all empty lines
from the table (using \textit{no.space}), and use \emph{omit.stat}
to leave out several statistics -- namely, the log-likelihood (``\emph{LL'}'),
residual standard error (``\emph{ser}'') and the F-statistic (``\emph{f}'').
Additionally, we label each of the dependent and independent variables
with an easy-to-understand name. To do so, we use the \emph{dep.var.labels}
and \emph{covariate.labels} arguments. The result is a complex, publication-quality
\LaTeX{} table. The relevant command call looks like this:

\noindent \newline
\verb|stargazer(linear.1, linear.2, probit.model, title="Regression Results",| \newline
\verb|align=TRUE, dep.var.labels=c("Overall Rating","High Rating"),| \newline
\verb|covariate.labels=c("Handling of Complaints","No Special Privileges",|
\newline \verb|"Opportunity to Learn","Performance-Based Raises","Too Critical","Advancement"),|
\newline \verb|omit.stat=c("LL","ser","f"), no.space=TRUE)|

\begin{table}[!htbp] \centering    \caption{Regression Results}    \label{}  \begin{tabular}{@{\extracolsep{5pt}}lD{.}{.}{-3} D{.}{.}{-3} D{.}{.}{-3} }  \\[-1.8ex]\hline  \hline \\[-1.8ex]   & \multicolumn{3}{c}{\textit{Dependent variable:}} \\  \cline{2-4}  \\[-1.8ex] & \multicolumn{2}{c}{Overall Rating} & \multicolumn{1}{c}{High Rating} \\  \\[-1.8ex] & \multicolumn{2}{c}{\textit{OLS}} & \multicolumn{1}{c}{\textit{probit}} \\  \\[-1.8ex] & \multicolumn{1}{c}{(1)} & \multicolumn{1}{c}{(2)} & \multicolumn{1}{c}{(3)}\\  \hline \\[-1.8ex]   Handling of Complaints & 0.692^{***} & 0.682^{***} &  \\    & (0.149) & (0.129) &  \\    No Special Privileges & -0.104 & -0.103 &  \\    & (0.135) & (0.129) &  \\    Opportunity to Learn & 0.249 & 0.238^{*} & 0.164^{***} \\    & (0.160) & (0.139) & (0.053) \\    Performance-Based Raises & -0.033 &  &  \\    & (0.202) &  &  \\    Too Critical & 0.015 &  & -0.001 \\    & (0.147) &  & (0.044) \\    Advancement &  &  & -0.062 \\    &  &  & (0.042) \\    Constant & 11.011 & 11.258 & -7.476^{**} \\    & (11.704) & (7.318) & (3.570) \\   \hline \\[-1.8ex]  Observations & \multicolumn{1}{c}{30} & \multicolumn{1}{c}{30} & \multicolumn{1}{c}{30} \\  R$^{2}$ & \multicolumn{1}{c}{0.715} & \multicolumn{1}{c}{0.715} &  \\  Adjusted R$^{2}$ & \multicolumn{1}{c}{0.656} & \multicolumn{1}{c}{0.682} &  \\  Akaike Inf. Crit. & \multicolumn{1}{c}{210.375} & \multicolumn{1}{c}{206.412} & \multicolumn{1}{c}{26.175} \\ Bayesian Inf. Crit. & \multicolumn{1}{c}{220.183} & \multicolumn{1}{c}{213.418} & \multicolumn{1}{c}{31.780} \\   \hline  \hline \\[-1.8ex]  \textit{Note:}  & \multicolumn{3}{r}{$^{*}$p$<$0.1; $^{**}$p$<$0.05; $^{***}$p$<$0.01} \\  \normalsize  \end{tabular}  \end{table} 

\newpage{}In \textit{Table 5}, we limit ourselves to the two linear
models, and report 90 percent confidence intervals (using \textit{ci}
and \textit{ci.level}) instead of standard errors. In addition, we
report the coefficients and confidence intervals on the same row (using
\textit{single.row}).

\noindent \newline
\verb|stargazer(linear.1, linear.2, title="Regression Results",| \newline
\verb|dep.var.labels=c("Overall Rating","High Rating"),| \newline
\verb|covariate.labels=c("Handling of Complaints","No Special Privileges",|
\newline \verb|"Opportunity to Learn","Performance-Based Raises","Too Critical","Advancement"),|
\newline \verb|omit.stat=c("LL","ser","f"), ci=TRUE, ci.level=0.90, single.row=TRUE)|

\begin{table}[!htbp] \centering    \caption{Regression Results}    \label{}  \begin{tabular}{@{\extracolsep{5pt}}lcc}  \\[-1.8ex]\hline  \hline \\[-1.8ex]   & \multicolumn{2}{c}{\textit{Dependent variable:}} \\  \cline{2-3}  \\[-1.8ex] & \multicolumn{2}{c}{Overall Rating} \\  \\[-1.8ex] & (1) & (2)\\  \hline \\[-1.8ex]   Handling of Complaints & 0.692$^{***}$ (0.447, 0.937) & 0.682$^{***}$ (0.470, 0.894) \\    No Special Privileges & $-$0.104 ($-$0.325, 0.118) & $-$0.103 ($-$0.316, 0.109) \\    Opportunity to Learn & 0.249 ($-$0.013, 0.512) & 0.238$^{*}$ (0.009, 0.467) \\    Performance-Based Raises & $-$0.033 ($-$0.366, 0.299) &  \\    Too Critical & 0.015 ($-$0.227, 0.258) &  \\    Advancement & 11.011 ($-$8.240, 30.262) & 11.258 ($-$0.779, 23.296) \\   \hline \\[-1.8ex]  Observations & 30 & 30 \\  R$^{2}$ & 0.715 & 0.715 \\  Adjusted R$^{2}$ & 0.656 & 0.682 \\ Akaike Inf. Crit. & 210.375 & 206.412 \\ Bayesian Inf. Crit. & 220.183 & 213.418 \\   \hline  \hline \\[-1.8ex]  \textit{Note:}  & \multicolumn{2}{r}{$^{*}$p$<$0.1; $^{**}$p$<$0.05; $^{***}$p$<$0.01} \\  \normalsize  \end{tabular}  \end{table}  

\newpage{}To produce ASCII text output, rather than \LaTeX{} code,
we simply set the argument \textit{type} to \textit{``text''}:

\noindent \newline
\verb|stargazer(linear.1, linear.2, type="text", title="Regression Results",| \newline
\verb|dep.var.labels=c("Overall Rating","High Rating"),| \newline
\verb|covariate.labels=c("Handling of Complaints","No Special Privileges",|
\newline \verb|"Opportunity to Learn","Performance-Based Raises","Too Critical","Advancement"),|
\newline \verb|omit.stat=c("LL","ser","f"), ci=TRUE, ci.level=0.90, single.row=TRUE)| \newline

\noindent\verb|Regression Results| \newline
\verb|========================================================================|\newline
\verb|                                       Dependent variable:              |\newline
\verb|                         -----------------------------------------------|\newline
\verb|                                        Overall Rating                  |\newline
\verb|                                  (1)                     (2)           |\newline
\verb|------------------------------------------------------------------------|\newline
\verb|Handling of Complaints   0.692*** (0.447, 0.937) 0.682*** (0.470, 0.894)|\newline
\verb|No Special Privileges    -0.104 (-0.325, 0.118)  -0.103 (-0.316, 0.109) |\newline
\verb|Opportunity to Learn      0.249 (-0.013, 0.512)   0.238* (0.009, 0.467) |\newline
\verb|Performance-Based Raises -0.033 (-0.366, 0.299)                         |\newline
\verb|Too Critical              0.015 (-0.227, 0.258)                         |\newline
\verb|Advancement              11.011 (-8.240, 30.262) 11.258 (-0.779, 23.296)|\newline 
\verb|------------------------------------------------------------------------|\newline
\verb|Observations                       30                      30           |\newline
\verb|R2                                0.715                   0.715         |\newline
\verb|Adjusted R2                       0.656                   0.682         |\newline
\verb|Akaike Inf. Crit.                210.375                 206.412        |\newline
\verb|Bayesian Inf. Crit.              220.183                 213.418        |\newline
\verb|========================================================================|\newline
\verb|Note:                                        *p<0.1; **p<0.05; ***p<0.01|\newline

\noindent \newpage{}Let us now change the order of the explanatory
variables using the \emph{order} argument, and remove the covariate
labels. In particular, we would like \emph{learning} and \emph{privileges}
to come before all the other covariates. In addition, of the summary
statistics reported, let us keep only the number of observations (using
the argument \emph{keep.stat}). Instead of reporting ASCII text, we'll
go back to producing \LaTeX{} tables by returning the \textit{type} argument
to its default value of \textit{``latex''}. \emph{Table 6} is our result. Please note
that users can also set the \textit{type} argument to \textit{``html''} to obtain
HTML code.

\noindent \newline
\verb|stargazer(linear.1, linear.2, title="Regression Results",| \newline
\verb|dep.var.labels=c("Overall Rating","High Rating"),| \newline
\verb|order=c("learning", "privileges"),| \newline
\verb|keep.stat="n", ci=TRUE, ci.level=0.90, single.row=TRUE)| \newline

\noindent \begin{table}[!htbp] \centering    \caption{Regression Results}    \label{}  \begin{tabular}{@{\extracolsep{5pt}}lcc}  \\[-1.8ex]\hline  \hline \\[-1.8ex]   & \multicolumn{2}{c}{\textit{Dependent variable:}} \\  \cline{2-3}  \\[-1.8ex] & \multicolumn{2}{c}{Overall Rating} \\  \\[-1.8ex] & (1) & (2)\\  \hline \\[-1.8ex]   learning & 0.692$^{***}$ (0.447, 0.937) & 0.682$^{***}$ (0.470, 0.894) \\    privileges & $-$0.104 ($-$0.325, 0.118) & $-$0.103 ($-$0.316, 0.109) \\    complaints & 0.249 ($-$0.013, 0.512) & 0.238$^{*}$ (0.009, 0.467) \\    raises & $-$0.033 ($-$0.366, 0.299) &  \\    critical & 0.015 ($-$0.227, 0.258) &  \\    Constant & 11.011 ($-$8.240, 30.262) & 11.258 ($-$0.779, 23.296) \\   \hline \\[-1.8ex]  Observations & 30 & 30 \\  \hline  \hline \\[-1.8ex]  \textit{Note:}  & \multicolumn{2}{r}{$^{*}$p$<$0.1; $^{**}$p$<$0.05; $^{***}$p$<$0.01} \\  \normalsize  \end{tabular}  \end{table} 


\emph{stargazer} can also report the content of vectors and matrices. Let us create a table 
that contains the correlation matrix for the \emph{rating}, \emph{complaints} and \emph{privileges} variables 
in the \emph{`attitude'} data frame:

\noindent \newline
\verb|correlation.matrix <- cor(attitude[,c("rating","complaints","privileges")])| \newline
\verb|stargazer(correlation.matrix, title="Correlation Matrix")| \newline

\noindent \begin{table}[!htbp] \centering 
  \caption{Correlation Matrix} 
  \label{} 
\begin{tabular}{@{\extracolsep{5pt}} cccc} 
\\[-1.8ex]\hline 
\hline \\[-1.8ex] 
 & rating & complaints & privileges \\ 
rating & $1$ & $0.825$ & $0.426$ \\ 
complaints & $0.825$ & $1$ & $0.558$ \\ 
privileges & $0.426$ & $0.558$ & $1$ \\ 
\hline \\[-1.8ex] 
\end{tabular} 
\end{table} 



\newpage{}


\subsection{Including Custom Standard Errors}

Instead of reporting the default standard errors, users can choose
to include custom vectors. Let us take a look at a brief example,
adopted -- with permission -- from Slawa Rokicki's excellent \href{http://rforpublichealth.blogspot.com/}{R for Public Health}
blog. In this example, we will consider the sales of ice cream. More
specifically, we are going to analyze how they might be affected by
the temperature outside. First, we will generate a data set that will,
for 500 cities, include values of the following variables: temperature
(variable \emph{temp}); sales per 100,000 people (\emph{sales}); and
the proportion of the city's population that is female (\emph{female}).

\noindent \newline
\verb|set.seed(5)| \newline
\verb|temp <- rnorm(500, mean = 80, sd = 12)| \newline
\verb|sales <- 2 + temp * 3| \newline
\verb|| \newline
\verb|for (i in 1:length(sales)) {| \newline
\verb|	if (temp[i]<75 ||\verb| temp[i]>95) sales[i] <- sales[i] + rnorm(1, 0, 25)| \newline
\verb|	else sales[i] <- sales[i] + rnorm(1, 0, 8)| \newline
\verb|}| \newline
\verb|| \newline
\verb|female <- rnorm(500, mean = 0.5, sd = 0.01)| \newline
\verb|icecream <- as.data.frame(cbind(temp, sales, female))| \newline

\noindent Now, let us run a simple Ordinary Least Squares (OLS) regression
model, and use the \emph{sandwich} package to obtain heteroskedasticity-robust
standard errors:

\noindent \newline
\verb|reg.model <- lm(sales ~ temp + female, data = icecream)| \newline
\verb| | \newline
\verb|library(sandwich)| \newline
\verb|cov <- vcovHC(reg.model, type = "HC") | \newline
\verb|robust.se <- sqrt(diag(cov)) | \newline

\newpage{}We can now use \emph{stargazer} to create a regression
table with the default and heteroskedasticity-robust standard errors
in two columns, side by side:

\noindent \newline
\verb|stargazer(reg.model, reg.model, se=list(NULL, robust.se),| \newline
\verb|column.labels=c("default","robust"), align=TRUE)| \newline


\noindent \begin{table}[!htbp] \centering    \caption{}    \label{}  \begin{tabular}{@{\extracolsep{5pt}}lD{.}{.}{-3} D{.}{.}{-3} }  \\[-1.8ex]\hline  \hline \\[-1.8ex]   & \multicolumn{2}{c}{\textit{Dependent variable:}} \\  \cline{2-3}  \\[-1.8ex] & \multicolumn{2}{c}{sales} \\   & \multicolumn{1}{c}{default} & \multicolumn{1}{c}{robust} \\  \\[-1.8ex] & \multicolumn{1}{c}{(1)} & \multicolumn{1}{c}{(2)}\\  \hline \\[-1.8ex]   temp & 2.972^{***} & 2.972^{***} \\    & (0.067) & (0.084) \\    & & \\   female & -37.819 & -37.819 \\    & (81.064) & (78.926) \\    & & \\   Constant & 23.916 & 23.916 \\    & (41.187) & (40.408) \\    & & \\  \hline \\[-1.8ex]  Observations & \multicolumn{1}{c}{500} & \multicolumn{1}{c}{500} \\  R$^{2}$ & \multicolumn{1}{c}{0.799} & \multicolumn{1}{c}{0.799} \\  Adjusted R$^{2}$ & \multicolumn{1}{c}{0.798} & \multicolumn{1}{c}{0.798} \\ Akaike Inf. Crit. & \multicolumn{1}{c}{4,318.054} & \multicolumn{1}{c}{4,318.054} \\ Bayesian Inf. Crit. & \multicolumn{1}{c}{4,334.912} & \multicolumn{1}{c}{4,334.912} \\   Residual Std. Error (df = 497) & \multicolumn{1}{c}{18.068} & \multicolumn{1}{c}{18.068} \\  F Statistic (df = 2; 497) & \multicolumn{1}{c}{984.916$^{***}$} & \multicolumn{1}{c}{984.916$^{***}$} \\  \hline  \hline \\[-1.8ex]  \textit{Note:}  & \multicolumn{2}{r}{$^{*}$p$<$0.1; $^{**}$p$<$0.05; $^{***}$p$<$0.01} \\  \normalsize  \end{tabular}  \end{table} 

\subsection{Many supported models}

\emph{stargazer} supports objects from the most widely used statistical
functions and packages. In particular, the package supports model
objects from \emph{aftreg }(eha)\emph{, arima} (stats)\emph{, betareg} (betareg), \emph{binaryChoice
}(sampleSelection)\emph{, bj }(rms)\emph{, brglm }(brglm)\emph{, censReg} (censReg)\emph{, coeftest
}(lmtest)\emph{, coxph }(survival), \emph{coxreg }(eha)\emph{, clm
}(ordinal), \emph{clogit }(survival), \textit{cph} (rms), \textit{dynlm}
(dynlm), \emph{ergm }(ergm), \textit{errorsarlm} (spdev), \emph{felm} (lfe), \emph{gam
}(mgcv),\emph{ garchFit }(fGarch),\emph{ gee }(gee),\emph{ glm }(stats), \textit{Glm} (rms),\emph{
glmer }(lme4),\emph{ glmrob}(robustbase), \emph{gls} (nlme), \textit{Gls} (rms), \textit{gmm}
(gmm), \emph{heckit} (sampleSelection), \emph{hetglm} (glmx), \emph{hurdle }(pscl), \emph{ivreg}
(AER), \textit{lagarlm} (spdep), \emph{lm}(stats),\emph{ lme }(nlme), \emph{lmer} (lme4),
\emph{lmrob} (robustbase), \textit{lrm} (rms), \textit{maBina}\textit{\emph{
(erer)}}\textit{, mclogit }\textit{\emph{(mclogit)}}\textit{, mlogit
}\textit{\emph{(mlogit)}}\textit{, mnlogit
}\textit{\emph{(mnlogit)}}\textit{, mlreg} (eha), \emph{multinom} (nnet),\emph{ nlme }(nlme),
\emph{nlmer} (lme4), \textit{ols} (rms), \emph{pgmm}
(plm), \textit{phreg} (eha), \emph{plm}
(plm), \emph{pmg} (plm), \emph{polr} (MASS), \textit{psm} (rms), \textit{rem.dyad}
(relevent), \emph{rlm} (MASS), \textit{rq} (quantreg), \textit{Rq}
(rms), \emph{selection }(sampleSelection)\emph{, svyglm} (survey),
\emph{survreg }(survival), \emph{tobit} (AER), \textit{weibreg} (eha),
\emph{zeroinfl} (pscl), as well as from the implementation of these
in \emph{zelig}. In addition, stargazer also supports the following
zelig models: ``\textit{relogit''}, ``\emph{cloglog.net}'', ``\emph{gamma.net}'',
``\emph{probit.net}'' and ``\emph{logit.net}''. 

The number of models and objects that \emph{stargazer} can accommodate
puts it ahead of most of the alternative R-to-\LaTeX{} options. As
the development of the package continues, this list will continue
expanding to matching models, as well as new, user-made, or customized
statistical models. 


\subsection{Beautiful aesthetics}

\emph{stargazer} is very pleasing to the eye, and allows the user
to customize all variable labels, as well as the formatting of the
resulting table. If you'd like to create tables that look like those
from your discipline's leading journal, \emph{stargazer} can help
you with that as well. You can use the style argument to choose a
template of your choice. Economics and management scholars can thus
create tables that resemble those published in the \emph{American
Economic Review}, in the \emph{Quarterly Journal of Economics}, or
in \emph{Administrative Science Quarterly}. Political scientists can
avail themselves of templates based on the \emph{American Political
Science Review}, the \emph{American Journal of Political Science},
and on \emph{International Organization}. For sociologists and demographers,
the \emph{American Sociological Review}, the \emph{American Sociological
Review} and \emph{Demography} are available.\newpage{}


\section{Citing \emph{stargazer} in Research Publications}

If you use the \emph{stargazer} package in your research publications,
please remember to include the following citation:\\


\noindent \texttt{Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables. R
package version 5.2.3.} \texttt{https://CRAN.R-project.org/package=stargazer}~\\
\texttt{}~\\


\noindent \textbf{Note:} An early version of this document was adapted
from \href{http://www.r-bloggers.com/stargazer-package-for-beautiful-latex-tables-from-r-statistical-models-output/}{my guest blog post}
on Tal Galili's excellent \href{http://www.r-statistics.com/}{R-statistics blog}. 
\end{document}