The internet is filled with R resources. (Case in point, this website!) Here are a few non-obvious ones to new users:
There are over 17,000 packages and counting on the CRAN network. Fortunately you can get by with just a few. Here are some to consider. Each package is installed by typing install.packages("packagename")
in the console (more instructions here).
Alongside the tidyverse, here are some useful packages for econometrics.
sjPlot
for regression tables and regression plots. If you just want to generate predictions from regression models check out ggeffects
(an input to sjPlot
).
modelsummary
broom
is a great package for “tidying” model results into data frames.patchwork
for combining multiple ggplot
objects into one figure.plm
for panel data econometrics.lmtest
for coefficient tests on linear models. You can combine this with sandwhich
to cluster standard errors.forecast
for time series econometrics.fixest
for linear models with fixed effects and clustering.There is also tidymodels
a collection of packages for econometrics and machine learning.
fabricatr
for simulating fake data.fredr
gives you access to the FRED (Federal Reserve Bank of St. Louis) database. tidyquant
provides access to Yahoo Finance and other financial data sources.fivethirtyeight
provides over 100 data sets featured on the sports/politics/etc. blog fivethirtyeight.wbstats
for World Bank data.ipumsr
for IPUMS census and survey data.Lahman
provides access to a wide variety of baseball data.rtweet
.tidycensus
for U.S. Census data.nhanesA
provides access to National Health and Nutrition Examination Survey (NHANES).Ecdat
for a bunch of other econometrics data sets.Check out Awesome Public Datasets for other datasets on economics and much more.
You have the skills. But anybody can write the letter “R” on their resume. So how do you separate from the pack? Here are two ideas: