Overview
This is the documentation of the ExPanDaR (Explore Panel Data with R) package. ExPanDaR provides the code base for the ExPanD web app. ExPanD is a shiny based app supporting interactive exploratory data analysis.
ExPanD has two purposes:
- Provide a toolbox for researchers to explore data on the fly, now also allowing them to download R notebook code that reflects their analysis.
- Enable users to assess the robustness of empirical evidence without providing them with access to the underlying data.
While I hope that ExPanD will be particularly helpful in the academic review, publication and replication process I also think that it is convenient for typical exploratory data analysis workflows. In addition, it has already proven to be helpful in the classroom.
This is what ExPanD looks like:
If you are interested to see what ExPanD has to offer without diving into R, click here to explore an instance of ExPanD that hosts World Bank data or click here for a financial accounting and stock returns dataset of U.S. firms.
To see how ExPanD can be customized, take a look at this blog post that generates this display of the development of fuel economy in the U.S. car market.
If you want to analyze your own data instead, you can also access a variant of ExPanD app here that allows user-side data uploads. No worries: Your data won’t be stored on the server and will get erased from memory as soon as you close the web connection.
Installation
If you are in for the full treat and want to test ExPanD from within R, run the following in your R session to install the ExPanDaR package from CRAN.
Or, if you want to install the current development version from Github:
Basic Usage
You can either start ExPanD without arguments so that it starts with a file upload dialog…
…or use it to explore a cross-sectional data frame with at least two numeric variables…
…or start with one of the two example datasets that come with the package to understand hot to use it on long-format panel data.
Please note: The last parameter (export_nb_option) allows the user to download a notebook and the data to continue the analysis in R. Maybe not the best idea if you are hosting your app publicly and want to keep its data private.
ExPanD(df = worldbank,
df_def = worldbank_data_def,
var_def = worldbank_var_def,
df_name = "World Bank Data",
config_list = ExPanD_config_worldbank,
export_nb_option = TRUE)
ExPanD(df = russell_3000,
df_def = russell_3000_data_def,
df_name = "Russell 3000",
config_list = ExPanD_config_russell_3000,
export_nb_option = TRUE)Use ExPanDaR functions in your own EDA workflow
Besides providing the ExPanD app, ExPanDaR comes with a set of functions that might be helpful in your own exploratory data analysis workflow, e.g., functions to quicky produce standard tables and plots. See the article “Using the functions of the ExPanDaR package” on this page for a quick walk-trough.
