MSF 632: Statistical and Quantitative Methods for Finance
Course Instructor:
Office Number:
Office Hours:
Email:
Course Meeting Times:
Course Website: Canvas
Textbook
Quantitative Investment Analysis (4th Edition), by R. DeFusco, et al.
References for Python
- Practical Statistics for Data Scientists, by P. Bruce, et al.
- Using Python for Introductory Econometrics, by F. Heiss and D. Brunner
- Applied Univariate, Bivariate, and Multivariate Statistics Using Python
- Mastering Python for Finance, by James M. Weiming
- Scipy lecture notes
Course Description
The purpose of this course is to acquaint students with basic econometric techniques which are applicable to financial data analysis. The following topics will be covered; (1) some basic probability concepts and return distributions;(2) A review of elementary statistical inference (3) Simple and multiple regression models: specification and estimations; (4) Inferences in regression models (5) Diagnostic checking on the regression residuals; (6) Regression models with time series data; (7) Estimation of index models and capital asset pricing model and (8) Measuring and modeling volatility, correlations and liquidity. Throughout the course, emphasis will be placed on the understanding the fundamental concepts of financial econometric techniques. R computer language will be used to analyze real world problems.
This course builds a foundation for further study in advanced courses, including Portfolio Management, Derivatives, Risk Management, and Financial Engineering. This course will also help students to prepare for the CFA level 2 Exam. The skills of Python programming is highly valuable for job market seekers. The current demand for data-driven quantitative financial analysts is very high.
Learning Objectives
Successful completion of the course will equip students with basic, quantitative understanding of financial data analysis. Through course homework and projects, students will acquire various hands-on skills for performing real data work.
Approach to Learning
Students will learn quantitative tools (powered by economic theories) to analyze financial markets. Examples, cases, problems, articles, and other materials will be used to illustrate the application of theory to various real-life decision situations.
Snapshot of Weekly Lecture Topics
- Time Value of Money and Discounted Cash Flow Analysis
- Financial Data Description
- Data Visualization using Python
- Probability Concepts and Common Distributions
- Statistical Sampling and Estimation
- Hypothesis Testing
- Linear Regression Models
- Multiple Linear Regression
Detailed Class Schedules: (Sample)
- Week 1: Time Value of Money & Discounted Cash Flow
Subjects: Interest Rates (and Discount Rates), Timeline of Cash Flows (CFs), Future Value of CFs, Present Value of CFs, Effective Annual Rate (EAR), Annual Percentage Rate (APR), Annuity, Annuity Due, Perpetuity, Capital Budgeting, Net Present Value (NPV), Internal Rate of Return (IRR)
Textbook: Chap. 1.1-1.8, Page 1-44
- Week 2: Financial Data Organization & Description (using Python)
Subjects: Numerical & Categorical, Cross-Section vs. Time Series vs. Panel Data, Frequency Distribution, Contingency Table, Mean vs. Median vs. Mode, Quartiles & Quintiles & Percentiles, Data Dispersion Measures
Textbook: Chap. 2.1-2.3, Page 45-67; Chap. 2.5-2.7, Page 85-110
- Week 3: Financial Data Visualization (using Python)
Subjects: Histogram, Bar Chart, Line Chart, Scatter Plot, Heat Map; Stock Return Distributions, Risk vs. Return; Sample Mean, Sample Variance, Standard Deviation, Skewness, Kurtosis, Correlation btw Two Series of Data.
Textbook: Chap. 2.4, Page 68-84; Chap. 2.7-2.10, Page 111-135
- Week 4: Probability Concept and Common Distributions
Subjects: Expected Value, Variance & Covariance, Portfolio Expected Return, Return Volatility, Bayes’ Rule, Uniform Distribution, Exponential Distribution, Binomial Distribution, Normal and Lognormal Distributions.
Textbook: Chap. 3.1-3.4, Page 147-183; Chap 4.1-4.3, Page 195-227
- Week 5: Statistical Sampling and Estimation
Subjects: Simple vs. Stratified Random Sampling, Central Limit Theorem, Point Estimators, Confidence Intervals, Sample Size Selection, Various Sampling Biases, Random Walk, Monte Carlo Simulation (using Python)
Textbook: Chap. 4.4, Page 228-230; Chap 5.1-5.5, 241-267
- Week 6: Hypothesis Testing
Subjects: Null vs. Alternative Hypothesis, Hypothesis Testing (HT) for Mean, HT for Variance & Correlation, Statistical Significance, Nonparametric Test
Textbook: Chap. 6.1-6.5, Page 275-313
- Week 7: Linear and Multiple Regression
Subjects: Definition of Linear Regression, LR with an independent variable, Standard Error of Estimate, Coefficient of Determination, Variance Analysis Assumptions of Multiple Linear Regression, Predicting Dependent Variable, Adjusted R2, Testing Coefficients, Dummy Variables, Heteroskedasticity, Serial Correlation, Multicollinearity, Model Specification
Textbook: Chap. 7.1-7.8, Page 327-352; Chap. 8.1-8.6, Page 365-414 If time permits, we will cover some basic concepts of Time Series Analysis (Chap. 9, Page 451-454) and Machine Learning (Chap. 10, Page 527-533).
- Week 8: Final Exam
Review for the final exam will be given this week.
Homework and Projects
There will be 4 homework assignments and 4 projects. The homework and project will be posted every two weeks at the Canvas. Due Dates will be announced when Homework/Project is posted online.
Instructions and Requirements
- Your homework and project reports must be typed out in Microsoft Words.
- Put your name and student ID in the frontpage of your report.
- Your original Python programing codes should be attached with the report.
- Be respectful and professional in communications.
- Submit your reports on time by email.
- Each student must work, write, and submit the report independently.
- Clarify in your report if you receive significant help from someone else. There is no penalty if you are honest about this.
Final Exam
- A two-hour final exam containing 10 to 15 questions will be given.
- The location, date, and time of the final exam will be announced later.
- You can only use scratch papers and a calculator during the exam.
- No cell phone or other electronic devices are permitted during the exam.
Class Participation
Students must attend all online lectures and watch the recorded lecture videos on Canvas. Be ready that you could be asked to answer questions during the lecture. Class participation is counted in the final grade. So your engagement in class definitely matters. Notify your professor in advance if there is emergency.
Students should keep themselves updated on any changes on the course website. In case of absence, it is the student’s responsibility to catch up with the material covered. Without advance notice and approval, no extensions or retake options are granted if you miss the exam or other deadlines.
Grading Policy
Student scores on 4 major graded components, which are all out of 100 points, are each multiplied by the relevant weight from the table below and the resulting sum is the numeric grade that determines the letter grade for the course.
| Course Component | Weight of Numeric Grades |
| Final Exam | 40% |
| 4 Course Projects | 25% |
| 4 Graded Assignments | 25% |
| Class Participation | 10% |
Numeric grades for the course are rounded up to the nearest tenth (1 decimal place) and final letter grades are based on the rounded figure. For example, 69.9001 would round up to 70.0, which would be a C, but 68.9000 would round up to 68.9, which would be a D. Grades for individual components are rounded up to the nearest whole number (0 decimal places).
Final semester letter grades are only changed if there is a grading error. Grades are not raised when a student is very close to the cutoff between two grades.
The instructor may modify the grading policy for the course if, in his opinion, events, conditions, etc. warrant modifications. The most common such situation involves the University reducing the time for final exams; if so, the weight on the final may be reduced and the weight on one or more tests may be increased.
Letter grades are determined by numeric grades for the course and the ranges described in the table below:
| Grade | Range |
| A+ | 97.0 or greater* |
| A | 93.0 – 96.9 |
| A- | 89.0 – 92.9 |
| B+ | 86.0 – 88.9 |
| B | 83.0 – 85.9 |
| B- | 80.0 – 82.9 |
| C+ | 75.0 – 79.9 |
| C | 70.0 – 74.9 |
| D | 60.0 – 69.9 |
| F | 59.9 or less |
Incompletes
A grade of incomplete may be given to students who are passing the course (with a C or higher) but who may be unable to complete scheduled coursework for a cause beyond reasonable control. An incomplete can only be given if a student has completed at least half the work for the semester, is passing the course, and has a documented excusable reason such as a serious illness or unanticipated family emergency for being unable to complete the remainder of the work as scheduled. Poor time management or failure to deal with a situation earlier in the semester would not be accepted as a reason for an incomplete.
To print: Right-click and choose “Print,” then follow your browser’s print settings.
To download: Right-click and choose “Print,” then select “Save as PDF.”