代做BU.232.630 – Nonlinear Econometrics for Finance代做Python编程

- 首页 >> Java编程
 

Nonlinear econometrics for finance

BU.232.630.W1

Mondays 1:30 - 4:30 pm

January 22nd  - March 11th

Spring I 2024

DC Campus

Required Texts & Learning Materials

All materials will be posted online on OneDrive with a link on Canvas in the welcome announcement.

.     The slides will be posted one or two days before class.

.     Academic articles will also be posted, as needed.

Recommended Texts

A suggested, non-mandatory, technical reading is the book Econometrics by Bruce Hansen. A copy of the book is on OneDrive.

The first ten chapters are largely about linear models (for which I will also provide a set of lecture notes).

Chapter 13 and Chapter 5 are about the generalized method of moments and maximum likelihood, techniques which will be central to our discussion.

Another suggested, non-mandatory, reading is the book Asset Pricing by John Cochrane. This is a less

technical reading than the previous book but has a substantial finance content. An older version of this book is also posted on OneDrive.

Technology Requirements

We will use Python heavily. Please install the software before the beginning of classes. You should already have installed it from your Computational Finance course in the fall.

Course Description

Nonlinear Econometrics introduces econometric tools needed to analyze financial data and build state-of-the-art nonlinear financial models. This is an advanced class requiring strong foundations in multivariate calculus, matrix algebra, probability and statistics. The course covers methods of asymptotic (i.e., large-sample) inference in extremum (nonlinear) estimation. Among them, particular emphasis is placed on nonlinear least-squares (NLS), the generalized method of moments (GMM) and maximum likelihood (ML) estimation.

Prerequisite(s)

Computational Finance and Linear Econometrics are prerequisites. We will rely heavily on both courses.

Complete familiarity with classical methods of inference in linear models – as introduced in Linear Econometrics - is critical to gain complete understanding of this course’s nonlinear methods. Programming in Python – as discussed in Computational Finance – will be used heavily throughout.

Learning Objectives

By the end of this course, students will be able to:

1.   Evaluate linear econometric models in terms of their statistical fit

2.   Evaluate nonlinear econometric models in terms of their statistical fit

3.   Evaluate economic theories using linear and nonlinear methods

Attendance

Participants are expected to attend all scheduled class sessions. Failure to attend class will result in an inability to achieve the objectives of the course. Full attendance - and active participation - are required for you to succeed in this course. Please remember to bring your name tag to class and display it on your desk.

Classroom protocol

.     All behaviors and communications in class sessions must be professional, civil and compliant with Carey student policies

.     Participants are expected to turn off their phones while in class

Assignments

Assignment

Group or individual

Learning Objectives

Weight

3 homeworks

Group

1 (first HW)

2 and 3

(second and third HW)

10% each

3 in-class quizzes

Individual

1, 2 and 3

5% each

Final exam

Individual

1, 2 and 3

55%

Total

 

 

100%

Homework (30%): There will be 3 homework assignments, each worth 10% of the final grade. The assignments have a very important pedagogical role. They are designed to check your understanding of the  material covered in class by making you work through an array of theoretical and applied problems. You can work on these in groups (maximum 3 people) but you do not have to do so, if you so choose.

Quizzes (15%): There will be 3 in-class quizzes, each worth 5% of the final grade. The quizzes are in weeks 3, 5, and 7 - at the end of class. They will be short tests, with 2 or 3 questions to be solved in about 15 minutes, designed to check your understanding and knowledge of topics covered in previous weeks.

Final Exam (55%): The (cumulative) final exam will be between 2 and 3 hours long.

Regarding coding

You will, sometime, have issues (everybody does). If you do, you can ask the TA for your class (see slides for  Lecture 1) but only after doing the following: (1) consulting available Python resources (virtually every question has been addressed online) and (2) asking one (or more) of your peers. In other words, every time you ask a   question about coding you should first begin with your question and then add why (1) and (2) above where not helpful. In the absence of (1) and (2), the TA may not answer your query. This is an advanced course and you  should begin training yourself to be creative and independent.

Grading

The grade of A is reserved for those who demonstrate extraordinary performance as determined by the instructor. The grade of A- is awarded only for excellent performance. The grades of B+ and B are awarded for good performance. The grades of B-, C+, C, and C- are awarded for adequate but substandard performance. The grades of D+, D, and D- are not awarded at the graduate level. The grade of F indicates the student’s failure to satisfactorily complete the course work. For Core/Foundation courses, the grade point average of the class should not exceed 3.35. For Elective courses, the grade point average should not exceed 3.45.

Policy on Generative AI

Academic integrity is a cornerstone of the Carey Business School. Generative artificial intelligence (AI) tools such as ChatGPT are widely available, and these technologies present a number of exciting opportunities in the classroom. In this course, you may use generative AI tools on any assignment (but never on quizzes or the final exam). Use of AI must be cited. All professors have access to an AI indicator on “TurnItIn” which will let them know the extent to which you likely used AI to complete an assignment. For guidance with referencing AI- generated content, please use the following:

MLA Style Center

The Chicago Manual of Style Online

APA Style

Tentative Course Calendar

Instructors reserve the right to alter course content and/or adjust the pace to accommodate class progress. Students are responsible for keeping up with all adjustments to the course calendar.

Week

Topic

Reading

Goal

HW

1

Introduction to

nonlinear

econometrics and

technical

fundamentals

Class slides

.     Finite sample

properties of the

sample mean: expected value and variance

.     Asymptotic properties

of the sample mean: (1) consistency and (2)

asymptotic normality .     Slutskys theorem

.     Taylors expansions .     Introduction to

nonlinear least-squares

(NLS)

First HW

assigned

Week

Topic

Reading

Goal

HW

2

Nonlinear least

squares (NLS)

Class slides

.     Asymptotic properties of NLS: (1)

consistency and (2)  asymptotic normality

.     HAC estimation in NLS

 

3

Generalized Method of Moments (GMM) I

 

QUIZ 1 at the end of class

Class slides

.     Asset pricing

.     The Consumption CAPM (CCAPM)  (video)

.     The GMM criterion

.     Applying GMM to asset pricing models and

beyond

.     Asymptotic properties of GMM: (1)

consistency and (2)  asymptotic normality (video)

First HW due

Second HW

assigned

4

Generalized Method of Moments (GMM) II

Class slides

.     The exactly identified case

.     The over-identified case

.     Optimal weight matrix

.     HAC estimation in

GMM

.     Test of over-identifying restrictions

 

5

Maximum likelihood (MLE) I

 

Quiz 2 at the end of

class

Class slides

.     Examples: IID normal case, AR(1), logit

.     Asymptotic properties    of MLE: (1) consistency and (2) asymptotic

normality (video)

Second HW due

Third HW

assigned

Week

Topic

Reading

Goal

HW

6

Maximum likelihood (MLE) II

Class slides

.     Volatility models: ARCH/GARCH

.     The likelihood of volatility models

.     The asymptotic

properties of the ML estimator in these

models

 

7

Maximum likelihood (MLE) III

 

Quiz 3 at the end of

class

Class slides

 

.     More on volatility estimation

.     Robustness/efficiency in econometric

estimation

.     Course recap

.     Quasi-MLE (QMLE) inference, QMLE vs GMM, QMLE vs ML (video)

Third HW due

8

Final Exam

 

 

 

 

 

站长地图