Empirical Finance Spring II 2024
Assignment 2
Q1. (110pts) Event study using Paramount Global
Open PARA-weekly.csv, and you will find the stock prices of Paramount Global (PARA) from April 15, 2019,to April 15, 2024. Note that ViacomCBS changed its corporate name to Paramount as of February 16 2022. We are working with the adjusted closing prices. Define log weekly returns by first taking the logarithm of prices and then differencing them at weekly intervals. The sample should be from April 22, 2019, to April 15, 2024 (excluding the first observation).
1. (20pts) Report the sample mean and standard deviation.
(Grading rule: No partial credit given here. Either 0 or full 20 points.)
2. (30pts) Identify periods during which the log returns dropped below -0.28 (-28%). In one sentence, explain key events that affected Paramount’s stock prices in those periods.
(Grading rule: If all dates are correctly provided, then you receive 20 points. If all events are properly described, you receive additional 10 points. Any deficiencies will result in deductions in increments of 10 points.)
3. (30pts) Based on the previous answer, create a dummy variable that consists of a vector of zeros and ones, indicating when the weekly log returns dropped below -0.28. Then, estimate the following regression
rt = α + βdt + Et
where rt represents the weekly log return of Paramount and dt is the dummy vari- able. Report the estimate of β with its standard error and R2. The objective of this exercise is to understand the role of dummy variable in the regression.
(Grading rule: Any deficiencies will result in deductions in increments of 10 points.)
4. (30pts) Create a categorical variable consisting of a vector of zeros, with ones indi- cating when the weekly log returns increased above 0.15 and negative ones indicat- ing when the weekly log returns dropped below -0.15. Then, estimate the following regression
rt = + δct + Et
where rt represents the weekly log return of Paramount and ct is the categorical variable. Report the estimate of δ with its standard error and R2. The objective of this exercise is to understand how denoting good events as +1 and bad events as -1 can improve the fit of the regression.
(Grading rule: Any deficiencies will result in deductions in increments of 10 points.)
Q2. (70pts) Cross-sections of returns
Download “q2data.xlsx.” You will find 3 log stock returns (labeled “A,B, C”) and 4 factors (labeled “MKT-RF, SMB, HML, RF”) covering the period from March 2013 to February 2024. The data are in monthly intervals and expressed in percentage terms.
1. (20pts) Subtract RF from each of A,B,C and regress on MKT-RF. This is the empirical regression for CAPM. Report the estimated β and adjusted R2 from the regression.
Note that you are estimating the CAPM equation for A,B, and C stocks separately.
(Grading rule: Any deficiencies will result in deductions in increments of 10 points.)
2. (20pts) Similarly estimate the Fama-French 3 factor model for A, B, and C stocks. Compare the estimates of β with those from the CAPM equation.
(Grading rule: Any deficiencies will result in deductions in increments of 10 points.)
3. (30pts) Based on the coefficient estimates for “SMB” and “HML” factors, discuss the characteristics of A, B, and C stocks.
(Grading rule: Any deficiencies will result in deductions in increments of 10 points.)
Q3. (20pts) Reading assignment
Read the article “Can ChatGPT forecast stock price movements? Return predictability and large language models” and summarize in two paragraphs.
(Grading rule: I expect everyone to receive full 20 points here.)