Assignment 1
1 Submission
Please submit your works on the 125785 Stream website in the “Submission online - Assignment 1 (Auckland)”
• Please submit only one PDF file which includes:
– R codes used for your answers.
– R outputs that are helpful for your answers.
– Both R codes and outputs must be included together with the explanation and discussion of the answers. Do not put them into the appendix.
• Use the filename name__surname__studentID__assignment1.pdf
• The online submission is designed to facilitate the students. However, if you cannot submit online, you can also choose to submit via email.
• Late submission is subject to penalty (point deduction) unless a permission is given at least 1 week before the deadline.
2 Instruction
• There are 3 parts. Each part is worth 10 marks. Total marks is 30 marks.
• Part A is a replication of the research paper.
• Part B contains 3 questions on linear model.
• Part C contains 3 questions on statistical and causal models.
3 Part A: Empirical Replication (10 marks)
1. Main reference:
• Goulding, Christian L. and Harvey, Campbell R. and Mazzoleni, Michele, Breaking Bad Trends (October 5, 2023). Available at SSRN: https://ssrn.com/abstract=3594888 or http://dx.doi.org/10.2139/ssrn.3594888
• Goulding, Christian L. and Harvey, Campbell R. and Mazzoleni, Michele, Breaking Bad Trends (14 January 2024). Financial Analysts Journal, 2024, 80(1): 84-98. DOI: 10.1080/0015198X.2023.2270084
2. Data:
• Select one investment that has the data available in YahooFinance and starting at least one year before 1990.
• Evaluation period: Jan1990-Dec2024
3. Required Exhibit:
• Exhibit 2: Static-Trend Performance vs. Number of Asset Turning Points per Year (January 1990 to December 2024)
4. Required Tables
• Exhibit E.1: Trend Strategy Statistics in Various Subsamples
• Panel A Full Sample
• Panel B Through GFC: 1990-2008
• Panel C Post GFC: 2009-2024
5. Statistics
• Average Excess Return (% Annualized)
• Volatility (% Annualized)
• Sharpe Ratio
6. Strategies
• Strategy 1: Buy and Hold
• Strategy 2a: Static Fast Trend 1 month
• Strategy 2b: Static Slow Trend 12 months
• Strategy 3: Dynamic Trend
7. Write a mini-research report (around 1,000 words) with the following sections
• Title (approx. 10 words)
• Abstract (approx. 100 words)
• Introduction (approx. 200 words)
• Literature Review and Hypothesis Development (approx. 300 words)
• Data Description (approx. 100 words)
• Analysis and Interpretation (approx. 200 words)
• Conclusion and Recommendation (approx. 100 words)
• References
• Exhibit
• Table
• Appendix (Optional)
• R codes
8. Marking is based on: Accuracy (40%), Discussion (40%), Presentation (20%)
4 Part B: Linear Model (10 marks)
4.1 B.1 (3 marks)
The Sell in May and Go Away does not invest the market during May to October and invests in the market during November to April.
• Use S&P500 monthly return from January 1980 to December 2024.
• Assume when going away, the strategy earns 0%.
• See the discussion of the strategy in the US at https://www.investopedia.com/terms/s/sell-in- may-and-go-away.asp
(a) Discuss the descriptive statistics (average return and standard deviation) of the buy-and-hold return and the sell-in-May return.
(b) Use two-sample t-test and paired t-test to test whether the buy-and-hold return and volatility is significantly higher than the sell-in-May return market. Discuss the appropriateness of each test.
4.2 B.2 (4 marks)
Use the (raw) dataset “wage1” in the library(wooldridge) to analyse multiple determinants of income.
lwage = α + β1 educ + β2 e犹per + β3tenure + β4 female + β5 female * educ + ∈ Note: Refer to help for variable description. lwage is log(wage)
(a) Estimate the model and interpret the results in statistic and economic terms of the return to education and the economic meaning of β5 .
(b) Discuss if the model satisfies the linear regression assumptions. Support the discussion with the test results and solutions if necessary. [Hint: there are many assumptions]
4.3 B.3 (3 marks)
Discuss the best way to estimate each of the model in the Anscombe’s Quartet. [Hint: There are 4 models in total.]
5 Part C: Statistical and Causal Models (10 marks)
5.1 C.1 (3 marks)
What is wrong with the following claims?
(a) “Data show that income and marriage have a high positive correlation. Therefore, your earnings will increase if you get married.”
(b) “Data show that as the number of fires increase, so does the number of fire fighters. Therefore, to cut down on fires, you should reduce the number of fire fighters.”
(c) “Data show that people who hurry tend to be late to their meetings. Don’t hurry, or you’ll be late.”
5.2 C.2 (5 marks)
In an attempt to estimate the effectiveness of a new drug, a randomized experiment is conducted. In all, 50% of the patients are assigned to receive the new drug and 50% to receive a placebo. A day before the actual experiment, a nurse hands out lollipops to some patients who show signs of depression, mostly among those who have been assigned to treatment the next day (i.e., the nurse’s round happened to take her through the treatment-bound ward). Strangely, the experimental data revealed a Simpson’s reversal: Although the drug proved beneficial to the population as a whole, drug takers were less likely to recover than nontakers, among both lollipop receivers and lollipop nonreceivers. Assuming that lollipop sucking in itself has no effect whatsoever on recovery, answer the following questions:
(a) Is the drug beneficial to the population as a whole or harmful?
(b) Does your answer contradict our gender example, where sex-specific data was deemed more appropriate?
(c) Draw a graph (informally) that more or less captures the story.
(d) How would you explain the emergence of Simpson’s reversal in this story?
(e) Would your answer change if the lollipops were handed out (by the same criterion) a day after the study?
[Hint: Use the fact that receiving a lollipop indicates a greater likelihood of being assigned to drug treatment, as well as depression, which is a symptom of risk factors that lower the likelihood of recovery.]
5.3 C.3 (2 marks)
You are researching whether the CEO risk taking propensity (explanatory variable) affect the firm performance (outcome variable). The control variables are 1) size 2) book-to-market ratio 3) leverage 4) profitability
(a) Draw the Directed Acyclic Graphs (DAGs). Is it possible to identify the effect of CEO risk taking on firm performance? Provide the evidences to support the answer.
(b) What control variables need to be included and excluded in the regression model? Provide the evidences to support the answer.