In EventStudyTools/api-wrapper.r: Event Study Analysis

knitr::opts_chunk$set(
  comment = "#>",
  collapse = TRUE,
  warning = FALSE,
  message = FALSE
)

Motivation {#motivation}

The provided sample data and request files serve as an example to demonstrate the functionality of the EventStudyTools R-package.

These files contain data related to the addition of several well-known firms to the S&P 500 index during the late 1990s. Using this data, the R package helps you examine whether a company's stock value increases upon being added to the S&P 500 index. This research question has been previously addressed, such as in a 1997 study by Anthony W. Lynch and Richard R. Mendenhall, which found a positive effect of approximately 3.8% from the day after the announcement to the day before the effective date of the change.

With our R-package, you can conveniently explore this and similar research questions.

Perform an Event Study from R {#perform-an-event-study-from-r}

Authentication {#authentication}

For performing an Event Study with our API you need:

• API url (defaults to http://api.eventstudytools.com)
• API key

You get an API key from our website EventStudyTools. In the first step we need to authenticate to the web API. There are three ways to handle this two parameters:

library(readr)
library(EventStudy)

apiUrl <- "http://api.eventstudytools.com"
apiKey <- "Please insert your key here"

Option 1 and 2: You can save API key and URL in the options object

# The URL is already set by default
# options(EventStudy.URL = apiUrl)
options(EventStudy.KEY = apiKey)

# use EventStudy estAPIKey function
estAPIKey(apiKey)

# initialize object
estSetup <- EventStudyAPI$new()

Option 2: Set the API Key and URL directly during the EventStudyAPI R6-class initialization

# Setup API Connection
estSetup <- EventStudyAPI$new(apiUrl)
estSetup$authentication(apiKey)

This API package is designed to conduct all analyses available on our website while allowing for the customization of all parameters. You can either set every parameter in R (details provided later) or perform a quick Event Study using default parameters, giving you flexibility and control over your analysis.

Event Study Types {#event-study-types}

Our API offers different types of Event Studies:

• Return Event Study: arc
• Trading Volume Event Study: avc
• Abnormal Volatility Event Study: avyc

Default parameters for all type of above Event Studies are:

• Benchmark model: Market Model for arc and avc and GARCH(1, 1) Model for avyc
• Statistics: All available test statistics are calculated
• Result file type: csv
• Return type calculation: log
• Handling non-trading days: later

The type of Event Study can be set by parameter:

estType <- "arc"

Data Files {#data-files}

By default all data files must be named as follows. Furthermore, they have to be in the current directory:

• 01_RequestFile.csv
• 02_firmData.csv
• 03_MarketData.csv

You are also able to set custom file names and paths by defining it in a named vector:

dataFiles <- c("request_file" = "01_RequestFile.csv", 
               "firm_data"    = "02_firmData.csv", 
               "market_data"  = "03_MarketData.csv")

Results {#results}

All results will be written by default into the directory ./results. You can easily change this path by setting it as a parameter:

resultPath <- "results"

Attention

If the resultPath do not exist, the R package will create this directory.

Performing the Event Study {#performing-the-event-study}

Finally, the Event Study is performed by:

estResult <- estSetup$performDefaultEventStudy(estType    = estType,
                                               dataFiles  = dataFiles, 
                                               destDir    = resultPath)

It will write all result files into the result directory. Furthermore, results will be parsed into a R object.

Data File Description {#data-file-description}

For performing an Event Study we need three files (file names can be chosen arbitrarily):

1. A request file where the structure of the Event Study is defined
2. A firm data file containing the stock data for each firm defined in the request file
3. A market data file containing the reference market data (multiple reference markets per study are possible)

All files must be saved without header, semi-colon separated and dates has to be in following format: 30.04.1997. In next section we will describe the file structure based on the S&P 500 example Event Study more detailed. You always find more information (if necessary) on our website: EventStudyTools..

We added the S&P 500 example Event Study to this package. The three above mentioned files can be generated by following command:

getSP500ExampleFiles()

We named the request and data files in following manner:

• 01_RequestFile.csv
• 02_FirmData.csv
• 03_MarketData.csv

Event Definitions: 01_RequestFile.csv {#event-definitions-01_requestfile.csv}

This CSV file contains the event definitions and consists of 9 columns. The order must follow the sequence below, as the columns are unnamed in the CSV.

• Event ID [Integer]: A unique event identifier
• Firm ID [String]: The firm name or stock ID. This ID must match the ID in the firm data
• Market ID [String]: The reference market ID. This ID must match the ID in the market data
• Event Date [30.04.1997]: Date of the event
• Grouping Variable [String]: This column is used to group events. Most test statistics are based on looking at groups.
• Start Event Window [Integer]: This integer value defines the start of the event window. This value must smaller or equal zero (e.g. trading days before event).
• End Event Window [Integer]: This integer value defines the end of the event window. This value must greater or equal zero (e.g. trading days after event).
• End of Estimation Window [Integer]: This negative value defines the end of the estimation window (counted from event day).
• Estimation Window Length [Integer]: Length of the estimation window

In the example below, we have an event window of [-2, 2] (an event window of length 5), an estimation window of length 120, and the estimation window ending 11 days before the event.

df <- read_delim("01_RequestFile.csv", col_names = F, delim = ";")
names(df) <- c("Event ID", "Firm ID", "Market ID", "Event Date", "Grouping Variable", "Start Event Window", "End Event Window", "End of Estimation Window", "Estimation Window Length")
knitr::kable(head(df), pad=0)

Attention

The first column (Event IDs) must be unique and numeric.

Firm Data: 02_FirmData.csv {#firm-data-02_firmdata.csv}

The stock data for each firm defined in the request file. It contains 3 columns.

• Firm ID [String]: The firm or stock ID. This ID must match the ID in the Firm ID in the request file.
• Date [30.04.1997]: Date of the closing price.
• Closing Price [Double]: Closing price of volume of that day.

The following table shows the first 20 entries of our example firm data.

library(readr)
df <- readr::read_delim("02_FirmData.csv", col_names = F, delim = ";")
names(df) <- c("Firm ID", "Date", "Closing Price")
knitr::kable(head(df))

Firm Data: 03_MarketData.csv {#firm-data-03_marketdata.csv}

This file is similary structured as 02_FirmData.csv:

• Market ID [String]: The market ID or stock ID. This ID must match the ID in the Market ID in the request file.
• Date [30.04.1997]: Date of the closing price.
• Closing Price [Double]: Closing price of volume of that day.

The following table shows the first 20 entries of our example firm data.

library(readr)
df <- readr::read_delim("03_MarketData.csv", col_names = F, delim = ";")
names(df) <- c("Market ID", "Date", "Closing Price")
knitr::kable(head(df))

You are also able to apply a Fama-French 3-Factor Model or a Fama-French Momentum-4-Factor Model. This will change the necessary data you need for performing an Event Study (e.g. by adding Fama-French Factors). You find more information at https://www.eventstudytools.com/instructions-axc.

More Vignettes {#more-vignettes}

1. Event Study: Parameters: In this Vignette we show how you can set parameters and which parameters are allowed.
2. Use case: Dieselgate.
3. RStudio Addins: We wrote a RStudio addin for performing different types of Event Studies
   • Abnormal Return Event Study
   • Abnormal Volume Event Study
   • Abnormal Volatility Event Study

How to Cite {#how-to-cite}

Please cite our work in your publication.

EventStudyTools/api-wrapper.r documentation built on April 16, 2023, 1:04 p.m.