|
|
|
|
Statistics Courses
Bendheim Center for
Finance
|
|
501
Asset Pricing I: Pricing Models and Derivatives
|
|
|
Provides an
introduction to the modern theory of asset pricing. Topics include: (i) No arbitrage, Arrow-Debreu prices and equivalent
martingale measure; (ii) security structure and market completeness; (iii)
mean-variance analysis, Beta-Pricing, CAPM; and (iv) introduction to
derivative pricing.
|
|
|
|
502
Corporate Finance and Financial Accounting
|
|
|
Modern
financial theory and its implications for decisions faced by corporate
financial officers. We will focus on investment decisions and capital
budgeting under various assumptions about the investment environment (for example,
certain or uncertain outcomes) and the legal/regulatory environment (such
as different types of tax regimes). We also examine financing decisions
concerning the type of securities to be issued, amount of dividends to be
paid, etc., plus a selection of additional topics, such as
convertible/hybrid securities, real options, or corporate structure and
control will also be covered.
|
|
|
|
503
Asset Pricing II: Stochastic Calculus and Advanced Derivatives
|
|
|
This course
covers the pricing and hedging of advanced derivatives including topics
such as exotic options, greeks, interest rate
derivatives, credit derivatives and real options. The course will cover
basics of stochastic calculus necessary for finance. It is designed for
Masters students.
|
|
|
|
504
Financial Econometrics
|
|
|
This
course covers econometric and statistical methods as applied to finance.
Topics include: 1. Overview of Statistical Methods 2. Predictability of asset
returns 3. Discrete time volatility models 4. Efficient Portfolio and CAPM
5. Multifactor Pricing Models 6. Intertemporal
Equilibrium and Stochastic Discount Models 7. Expectation and present value
relation 8. Simulation methods for financial derivatives 9. Econometrics of
financial derivatives 10. Forecast and Management of Market Risks 11.
Multivariate time series in finance 12. Nonparametric methods in financial
econometrics. J. Fan.
|
|
|
|
531
Computational Finance in C++
|
|
|
The intent of this course is to introduce the student to
the technical and algorithmic aspects of a wide spectrum of computer
applications currently used in the financial industry, and to prepare the
student for the development of new applications. The student will be
introduced to C++, the weekly homework will involve writing C++ code, and
the final project will also involve programming in the same environment.
Other Information: There will be no midterm, and the final grade will be
computed as follows: 30% Homework 70% Final Project Homework Policy - the
weekly assignment will be posted on Friday evening (right after the meeting
with the Teaching Assistant), the work being due the following Wednesday.
NO LATE HOMEWORK WILL BE ACCEPTED! Rene A. Carmona.
|
|
top
|
Civil and Environmental Engineering
|
|
460
Risk Assessment and Management
|
|
|
Fundamentals
of integrated risk assessment and risk-based decision analysis. Stochastic models
of natural and man-made hazards. Evaluation of failure chances and
consequences. Decision criteria; acceptable risk. Risk control based on
event tree, fault tree, system reliability, and random processes in space
and time. Issues in risk-based regulation, liability, and insurance. Case
studies involving energy-related technologies, the environment, civil
infrastructure, and financial risk. Prerequisite: 245.
|
|
top
|
Ecology and Evolutionary Biology
|
|
525 Quantitative
Field Ecology
|
|
top
|
|
Economics
|
202 Statistics and Data Analysis for Economics
|
|
|
An introduction to
probability and statistical methods for empirical work in economics. Probability,
random variables, sampling, descriptive statistics, probability
distributions, estimation and hypotheses testing, introduction to the
regression model. Economic applications are emphasized. Prerequisites: ECO
100 and ECO 101 and MAT 103.
|
|
|
|
|
|
|
Develop
facility with basic econometric methods and the ability to apply them to
actual problems and understand their application in other substantive
course work in economics. Prerequisites: ECO 100 and ECO 101 and ECO 202 (formerly
ECO 200), or ORF 245, and MAT 103.
|
|
|
312 Econometrics: A Mathematical Approach
|
|
|
This
course is an introduction to econometrics. Econometrics is a sub-discipline
of statistics that provides methods for inferring economic structure from
data. This course has two goals. The first goal is to give you means to
evaluate an econometric analysis critically and logically. Second, you
should be able to analyze a data set methodically and comprehensively using
the tools of econometrics. Prerequisites: ECO 100 and ECO 101 and ECO 202
(formerly ECO 200), or ORF 245, and MAT 200 or MAT 201.
|
|
|
313 Econometric Applications
|
|
|
This
course provides hands-on experience in econometric analysis designed to help
students to acquire the skills necessary to carry out their own empirical
research in economics. Various aspects of empirical research in economics
will be covered including 1) development of testable economic models, 2)
appropriate use of data, 3) specification and estimation of econometric
models. A range of applications will be presented and discussed in class.
Other Requirements: Course Not Open to Freshmen, course not required for
concentrators. Prerequisites: ECO 302 (formerly ECO 303) or ECO 312
(formerly ECO 306).
|
|
|
317 The Economics of Uncertainty
|
|
|
This
is an advanced microeconomic theory course. Using the concepts and
mathematical techniques developed in ECO 310, the following topics are studied:
1 Theories of choice under uncertainty. 2 Risk aversion and applications to
insurance and portfolio choice. 3 Equilibrium under uncertainty with
applications to financial markets. 4 Asymmetric
information: moral hazard and adverse selection. 5 Applications to
the design of incentives, contracts, contests, and auctions. Concepts in
game theory are developed as needed. Other Requirements: Course Not Open to
Freshmen. Prerequisites and Restrictions: ECO 310 (formerly ECO 305). ECO
202 (formerly ECO 200) or equivalent knowledge of probability theory.
|
|
|
513 Advanced Econometrics: Time Series Models
|
|
|
Concepts
and methods of time series analysis and their applications to economics. Time
series models to be studied include simultaneous stochastic equations, VAR,
ARIMA, and state-space models. Methods to analyze trends, second-moment
properties via the auto covariance function and the spectral density
function, methods of estimation and hypothesis testing and of model
selection will be presented. Kalman filter and
applications as well as unit roots, cointegration,
ARCH, and structural breaks models are also studied.
|
|
|
|
|
|
|
A first-year
course in the first-year econometrics sequence: it is divided into two
parts. The first gives students the necessary background in probability
theory and statistics. Topics include definitions and axioms of
probability, moments, some univariate distributions,
the multivariate normal distribution, sampling distributions, introduction to asymptotic theory, estimation and
testing. The second part introduces the linear regression model and
develops associated tools. Properties of the ordinary least squares
estimator will be studied in detail and a number of tests developed.
|
|
|
518 Econometric Theory II
|
|
|
This
course begins with extensions of the linear model in several directions: (1)
pre-determined but not exogenous regressors; (2) heteroskedasticity and serial correlation; (3)
classical GLS; (4) instrumental variables and generalized method of movements estimators. Applications include simultaneous
equation models, VARS and panel data. Estimation and inference in
non-linear models are discussed. Applications include nonlinear least
squares, discrete dependent variables (probit, logit, etc.), problems of censoring, truncation and
sample selection, and models for duration data. Prerequisites and
Restrictions: ECO 517.
|
|
|
519 Advanced Econometrics: Nonlinear Models
|
|
|
This is half of the
second-year sequence in econometrics methodology (Econ. 513 is the other).
The course covers nonlinear statistical models for the analysis of
cross-sectional and panel data. It is intended both for students
specializing in econometric theory and for students interested in applying
statistical methods to statistical data. Approximately half of the course
is devoted to development of the large-sample theory for nonlinear
estimation procedures, while the other half concentrates on application of
the methods to various econometric models. Other Information: Open to
graduate students only. Qualified undergraduate students must receive
written permission from the instructor to register for the course.
|
|
|
525 Financial Economics I
|
|
|
Asset pricing in
competitive markets where traders have homogeneous information. Empirical
tests of asset-pricing models and associated "anomalies" are also
surveyed. Measures of riskiness and risk aversion, atemporal
asset-pricing models, dynamic portfolio choice, option pricing and the term
structure of interest rates, corporate investment and financing decisions,
and taxation are studied.
|
|
|
575 Topics in Financial Economics
|
|
|
The course surveys
both the theoretical and empirical methods and results in selected research
topics in financial economics. Topics vary from year to year reflecting
current developments and the instructor's interests.
|
|
top
|
|
Electrical Engineering
|
|
485
Signal Analysis and Communication Systems
|
|
|
|
The course deals with
the engineering aspects of analog and digital communications. Systems
discussed include AM/FM radio and TV broadcasting, digital communications
such as phase and frequency shift keying, satellite communications, and
mobile (cellular) telephony. Topics studied include: continuous
wave-modulation (AM and FM), pulse modulated systems, multiplexing, random
processes and noise modeling, correlation functions and power spectra, SNR
(signal-to-noise) evaluation in analog communications, probability of error
calculation in digital communications, synchronization and spread spectrum
systems. Other Requirements: Course Not Open to Freshmen Prerequisites and
Restrictions: ELE 301 and ORF309. Other Information: Class lectures wil involve interactive stimulations of communications
principles and systems. Students will be provided with the simulation
software packages which will be used in both the class and for homeworks.
|
|
|
|
486 Digital Communications and Networks
|
|
|
|
Historical
overview of digital communications. Introductory information theory. Data
compression. Error detection and correction code. Baseband transmission
systems and optimum reception. Digital modulation and demodulation. Basic
concepts and elements of networks. Layered architectures and protocols.
Prerequisites and Restrictions: ELE301 and 380 are prerequisites.
Familiarity with topics covered by ELE485 is desirable. Other Information:
The students will be provided with the instructor's lecture note, H.
Kobayashi "Digital Communications and Networks", which serves as
the textbook for this course.
|
|
|
|
488 Image Processing and Transmission
|
|
|
|
Introduction
to the basic theory and techniques of two- and three-dimensional image processing.
Topics include image perception, enhancement, restoration, compression,
image transforms, tomography, and image understanding. Applications to
HDTV, machine vision, medical imaging, etc. Other Requirements: Course Not
Open to Freshmen. Prerequisites and Restrictions: ELE 301.
|
|
|
|
524 Theory of Statistical Inference
|
|
|
|
Logical
foundations of estimation, from classical Bayesian and decision theory
viewpoints. Gives an introduction to statistical hypothesis testing.
Examines parametric and non-parametric approaches and large-sample theory.
|
|
|
|
525 Random Processes in Information Systems
|
|
|
|
Presents
the fundamentals of applied random processes needed by students in communications,
computer engineering, controls, and signal processing. Probability, random
variables (discrete and continuous), random processes, stationarity
and ergodicity, spectral analysis, Gaussian
processes, Brownian motion and diffusion processes, estimation and
filtering, Poisson processes and birth-and-death processes, queueing and loss-systems models. Other Information:
Students taking this course should have a prior course in applied
probability at the undergraduate level. Sergio Verdu.
|
|
|
|
|
|
|
|
|
An exploration of the
Shannon theory of information, covering
noiseless-source coding theory of ergodic sources
and channel-coding theorems, including channels with memory,
multiple-access, and Gaussian channels. Sergio Verdu.
|
|
|
|
529 Theoretical Foundations of Random Processes
|
|
|
|
|
530 Theory of Detection and Estimation
|
|
|
|
The
subject of signal detection and estimation is concerned with the processing
of information-bearing signals for the purpose of making inferences about
the information that they contain. The purpose of this course is to provide
an introduction to the fundamental theoretical principles underlying the
development and analysis of techniques for such processing. The level of
this course is suitable for research students in communications, control,
signal processing, and related areas.
|
|
|
|
|
|
535 Machine Learning and Pattern Recognition
|
|
|
An
introduction to the theoretical foundations of machine learning and pattern
recognition. Topics include Bayesian pattern classification; parametric
methods; nearest-neighbor classification; kernel methods; density
estimation; VC theory; neural networks; stochastic approximation.
Prerequisite: ELE 525, or the permission of the instructor.
|
|
top
|
|
|
|
|
|
|
|
310
Mathematical Statistics
|
|
|
The
statistical problems of estimation, testing, and decision making will be
formulated theoretically, especially in those situations where optimal
solutions exist. Conventional and Bayesian methods will be compared.
Broadening the usual assumptions leads to robust methods of estimation and
testing. Three classes. Prerequisite: 309.
|
|
|
|
390
Probability Theory
|
|
|
|
391
Random Processes
|
|
|
(1) Wiener
measure. (2) Stochastic differential equations. (3) Markov diffusion
processes. (4) Linear theory of stationary processes. (5) Ergodicity, mixing, central limit theorem of processes,
Gibbs random field. If time permits, the theory of products of random
matrices and PDE with random coefficients will be discussed.
|
|
top
|
|
Operations Research and Financial Engineering
|
105
The Science and Technology of Decision Making
|
|
|
A practical but penetrating
introduction to quantitative models of decision making. This course fuses
problem-based learning and spreadsheet computation with the principal
models of operations research and probability. Examples are drawn from
engineering, economics, finance, operations management, business and
medical decision making. A sound background in high-school mathematics is
assumed, but the course is otherwise self-contained.
|
|
|
145
Introduction to Statistical Thinking
|
|
|
The
purpose of this course is to provide the students with an introduction to
basic statistical concepts and the tools for analyzing and interpreting
data. The students will be exposed to real-life problems so that they can
see the uses and limitations of statistics. This course not only imparts
knowledge of the technical tools to perform standard statistical
procedures, but also exposes the students to the statistical thinking and
reasoning involved in drawing conclusions and making decisions.
|
|
|
245
Fundamentals of Engineering Statistics. Fall
|
|
|
A
study of fundamentals of statistical methods and their applications in
engineering. Basic concepts of probability, discrete and continuous
distributions, sampling and quality control, statistical inference,
empirical models, and least squares. Three lectures. Open to freshmen. J.
Fan.
|
|
|
309
Probability and Stochastic Systems (also Mathematics 309 and Electrical
Engineering 380)
|
|
|
An introduction
to probability and its applications. Random variables, expectation, and
independence. Poisson processes, Markov chains, Markov processes, and
Brownian motion. Stochastic models of queues, communication systems, random
signals, and reliability. Prerequisite: Mathematics 201, 203, 217, or
instructor's permission. E. Cinlar, V. Henderson.
|
|
|
311
Optimization under Uncertainty
|
|
|
A survey of
quantitative approaches for making optimal decisions under uncertainty,
including decision trees, Monte Carlo
simulation, and stochastic programs. Forecasting and planning systems are
integrated with a focus on financial applications. Two 90-minute classes.
|
|
|
405
Regression and Applied Time Series
|
|
|
Statistical
Analysis of financial data: Density estimation, heavy tail distributions
and dependence. Regression: linear, nonlinear, nonparametric.
Time series analysis: classical models (AR, MA, ARMA, ..),
state space systems and filtering, and stochastic volatility models (ARCH,
GARCH, ....)
|
|
|
|
417 Dynamic Programming
|
|
An introduction to stochastic dynamic programming and
stochastic control. The course deals with discrete and continuous-state dynamic
programs, finite and infinite horizons, stationary and nonstationary data.
Applications drawn from inventory management, sequential games, stochastic
shortest path, dynamic resource allocation problems. Solution algorithms
include classical policy and value iteration for smaller problems and
stochastic approximation methods for large-scale applications.
|
|
|
|
418 Optimal Learning
|
|
Optimal learning addresses the problem of collecting information that
is used to estimate statistics or fit a model which is then used to
make decisions. Of particular interest are sequential problems where
decisions adapt to information as it is learned. The course will
introduce students to a wide range of applications, demonstrate how to
express the problem formally, and describe a variety of practical
solution strategies.
|
|
|
|
|
|
|
This
course is about modeling, measuring and managing financial risks for
individuals and financial organizations. It introduces methods and discusses
instruments that are used to this effect. Topics include mean-variance
portfolio analysis, bond portfolio immunization, option pricing, heding, Greek letters, risk measures, utility
functions. Prerequisite: Permission of instructor required and ORF 335.
|
|
|
504
Financial Econometrics
|
|
|
This
course covers econometric and statistical methods as applied to finance.
Topics include: 1. Overview of Statistical Methods 2. Predictability of
asset returns 3. Discrete time volatility models 4. Efficient Portfolio and
CAPM 5. Multifactor Pricing Models 6. Intertemporal
Equilibrium and Stochastic Discount Models 7. Expectation and present value
relation 8. Simulation methods for financial derivatives 9. Econometrics of
financial derivatives 10. Forecast and Management of Market Risks 11.
Multivariate time series in finance 12. Nonparametric methods in financial
econometrics. J. Fan.
|
|
|
505
Modern Regression and Applied Time Series
|
|
|
Linear
and mixed effect models. Nonlinear regression. Nonparametricegression
and classification. Time series analysis: stationarity
and classical linear models (AR, MA, ARMA, ..).
Nonlinear and nonstationary time series models.
State space systems, hidden Markov models and filtering. ORF 405 and 505
will have the same lectures. There will be one extra assignment a week for
505, and also, different midterm and final exams. MFin
students should enroll in the 505 version. Prerequisites and Restrictions:
ORF 245 and MAT 202. Rene Carmona.
|
|
|
515
Asset Pricing II: Stochastic Calculus and Advanced Derivatives
|
|
|
This course covers
the pricing and hedging of advanced derivatives including topics such as exotic
options, greeks, interest rate derivatives,
credit derivatives and real options. The course will cover basics of
stochastic calculus necessary for finance. It is designed for Masters
students.
|
|
|
524
Statistical Theory and Methods
|
|
|
This is
a graduate level introduction to statistical theory and methods. It
introduces some of the most important and commonly-used principles of
statistical inference. It covers the statistical theory and methods for
point estimation, confidence intervals, and hypothesis testing, and the
applications of the fundamental theory to linear models and categorical
data. J. Fan.
|
|
|
525
Generalized Regression Models
|
|
|
Course introduces the
most important and broadly used statistical methods used in many scientific
data analyses, including general linerar,
mixed-effects, generalized linear modes, regression
and ANOVA models. Objectives of the course are to give students a solid
understanding of these methods and give them experience in applying them to
real data using statistical computing packages and then interpreting
results. Course is designed for both master's and
Ph.D. students, and advanced undergraduates.
|
|
|
|
|
|
|
Fundamental models of
random phenomena in financial engineering and operations research: Poisson
processes, Markov chains, Brownian motion, and diffusion processes. S. Dayanik.
|
|
|
527
Stochastic Calculus and Finance
|
|
|
An introduction to
stochastic analysis based on Brownian motion. Topics include local
martingales, the It?integral
and calculus, stochastic differential equations, the Feynman-Kac formula, representation theorems, Girsanov theory, and applications in finance. P. Cheridito.
|
|
|
530
Financial Data Mining
|
|
|
531
Computational Finance in C++
|
|
|
The intent of this
course is to introduce the student to the technical and algorithmic aspects
of a wide spectrum of computer applications currently used in the financial
industry, and to prepare the student for the development of new
applications. The student will be introduced to C++, the weekly homework
will involve writing C++ code, and the final project will also involve
programming in the same environment. Other Information: There will be no
midterm, and the final grade will be computed as follows: 30% Homework 70%
Final Project Homework Policy - the weekly assignment will be posted on
Friday evening (right after the meeting with the Teaching Assistant), the
work being due the following Wednesday. NO LATE HOMEWORK WILL BE ACCEPTED!
Rene A. Carmona.
|
|
|
|
|
|
|
Sequential decision
problems, primarily in the context of the management of physical and
financial assets. The course will focus on modeling and computational
methods, using approximation techniques for a broad range of problem
classes including multistage asset allocation, asset acquisition and
technology switching, high dimensional shortest paths, dynamic assignment
and related pricing problems. Techniques will focus on Monte-Carlo based
methods for exploring state spaces and estimating value functions,
including stochastic approximation methods, temporal-differencing,
Q-learning, and methods for handling high-dimensional problems. Warren B.
Powell.
|
|
|
|
|
|
|
Graduate introduction
to probability theory: measure spaces, expectation, sigma-algebras, conditioning;
convergence concepts and laws of large numbers; stochastic processes,
filtrations, and stopping times; Poisson random measures, Brownian motion,
and martingales. Erhan Cinlar.
|
|
|
553
Stochastic Differential Equations
|
|
|
|
|
|
|
Markov processes with
general state spaces; transition semigroups,
generators, resolvants; hitting times, jumps, and
Levy systems; additive functionals and random
time changes; killing and creation of Markovian
motions. Erhan Cinlar.
|
|
|
557,
558 Stochastic Analysis Seminar
|
|
|
This seminar course
will introduce the students to recent developments in stochastic analysis
as they relate to the mathematical models of pricing and hedging in
incomplete markets. Rene A. Carmona.
|
|
|
569,
570 Special Topics in Statistics and Operations Research
|
|
|
Driven
by many sophisticated applications and fueled by modern computing power,
many useful data-analytic modeling techniques have been proposed to relax traditional
parametric models and to exploit possible hidden structure. The techniques
are also called semiparametric and nonparametric
regression. The course will cover many powerful ideas in the data-analytic
modeling with emphasis on the analysis of functional data. The course will
emphasize on the underlying theory and methodology that are driven by many
applications. J. Fan.
An introduction to the uses of simulation and direct computation in
analyzing stochastic models and interpreting real phenomena. The course
deals with generating discrete and continuous random variables, stochastic
ordering, the statistical analysis of simulated
data, variance reduction techniques, statistical validation techniques, nonstationary Markov chains and Markov chain Monte Carlo methods. Applications are drawn from
problems in finance, manufacturing and communication networks. William A.
Massey.
|
|
top
|
|
Politics
|
346
Applied Quantitative Analysis
|
|
|
Develops
the use of statistical techniques appropriate for empirical exploration of political
topics. Each statistical topic is motivated by a significant question in
political science that can be addressed by an available data set. Computers
will be used both as part of the lecture and for completing classwork. Emphasis is on hands-on training that will
give students the capacity to use these statistical techniques in other
courses and independent work. Prerequisites: WWS 303/POL 345, or ECO 202 or
ECO 302, or instructor’s permission. Two lectures, one preceptorial.
|
|
|
571
Quantitative Analysis I
|
|
|
Introduces
students without a previous background in statistics to statistical
techniques commonly used in political science. Hypothesis testing is
introduced in the context of contingency tables and cross-tabulations. Also
covers basic descriptive statistics, correlation coefficients, regression
analysis, and the testing of composite hypotheses.
|
|
|
572
Quantitative Analysis II
|
|
|
Builds
on the concepts introduced in POL 571. Topics include the linear probability
model, probit and logit
models, instrumental variables, systems of equations, maximum-likelihood
estimation, time-series analysis, and the analysis of panel data. The
emphasis is on the application of advanced statistical techniques to
important problems in political science research. Prerequisite: POL 571.
|
|
|
573
Quantitative Analysis III
|
|
|
Builds on the
material covered in POL 571 and POL 572. Provides an introduction to the
use of maximum-likelihood methods in political science. Develops the probit, logit, and regression
models within a maximum-likelihood framework, and introduces applications
to count data, and scaling models applied to legislative voting data.
Emphasizes the flexibility maximum-likelihood techniques provided to modelers.
Familiarity with matrix algebra and calculus techniques is assumed.
|
|
|
|
|
|
501
Statistical Demography
|
|
top
|
|
|
|
251
Quantitative Methods. Spring (QR)
|
|
|
The
purpose of this course is to introduce students to the basic techniques of
statistical analysis used in psychological research. Students will learn the
logic underlying the statistical techniques and learn how to perform
statistical analyses and interpret the results. Students will also discuss
“real-world” examples of applied statistics. Two hours of lectures, one
one-hour laboratory. This course is a pre-requisite for majoring in
psychology. Passing this course satisfies the quantitative requirement for
psychology concentrators. This course is offered each spring semester. A.
R. Conway.
|
|
top
|
|
Sociology
|
301
Sociological Research Methods
|
|
|
The course is
intended to introduce the student to a variety of methods for doing social
science research, and to have students get actual experience with research in:
surveys, experiments, participant observation, sampling procedures, content
analysis, and basic statistical analysis. Analysis and critique of existing
studies is undertaken. The main objective is to enable the student to carry
out social science research, and to critically evaluate research studies.
Other Requirements: Course Not Open to Freshmen.
|
|
|
|
|
|
|
This
course provides an introduction to quantitative methods used in sociology.
We begin by considering the two basic objectives of statistical
methods--data reduction and statistical inference. We consider these
objectives in studying relationships among variables culminating with an
analysis of the linear model. The course material is explored through the
analysis of real sociological data sets using the statistical package,
STATA.
|
|
|
|
|
|
|
This
course provides a thorough examination of linear regression from a data
analytic point of view. Sociological applications are strongly emphasized. Topics
include: (a) a review of the linear model; (b) regression diagnostics for
outliers and collinearity; (c) smoothers; (d)
robust regression; and (e) resampling methods.
Students taking the course should have completed an introductory course in
probability and statistics. Other Requirements: Course Open to Graduate
Students Only.
|
|
|
|
Woodrow Wilson School
|
332 Advanced Quantitative Analysis for Public
Policy
|
|
|
The course is
designed for students preparing to incorporate advanced statistical methods
in their policy research. In the context of case studies, it will cover the
principal methods of data analysis and applied statistics in social science
and policy research, including multiple regression, analysis of variance
and nonparametric methods. Students are expected to have some knowledge of
basic probability and statistical concepts such as means, standard
deviations, histograms and the normal curve but they need not be adept at
linear algebra or advanced calculus.
|
|
|
507
(b,c) Quantitative Analysis: Basic and Advanced
|
|
|
Study
of basic data analysis techniques, stressing application to public policy. Includes
measurement, descriptive statistics, data collection, probability,
exploratory data analysis, hypothesis testing, simple and multiple
regression, correlation, and graphical procedures. Some training offered in
the use of computers. No previous training in statistics is required.
Assumes a fluency in high school algebra and familiarity with basic
calculus concepts (in advanced, assumes a fluency in calculus.)
|
|
|
508
(b) Econometrics and Public Policy: Basic
|
|
|
Provides
a thorough examination of statistical methods employed in public policy
analysis, with a particular emphasis on regression methods which are
frequently employed in research across the social sciences. This course
emphasizes intuitive understanding of the central concepts, and develops in
students the ability to choose and employ the appropriate tool for a
particular research problem, and understand the limitations of the
techniques. Prerequisite: 507b.
|
|
|
508
(c) Econometrics and Public Policy: Advanced
|
|
|
Discusses
the main tools of econometric analysis, and the way in which they are
applied to a range of problems in social science. Emphasis is on using
techniques, and on understanding and critically assessing others' use of them.
There is a great deal of practical work on the computer using a range of
data from around the world. Topics include regression analysis, with a
focus on regression as a tool for analyzing non-experimental data, discrete
choice, and an introduction to time-series analysis. There are applications
from macroeconomics, policy evaluation, and economic development.
Prerequisite: grounding in topics covered in 507c.
|
|
|
509
Generalized Linear Statistical Models (Also ECO509)
|
|
|
Focuses primarily on the
analysis of survey data using generalized linear statistical models. The
course starts with a review of linear models for continuous responses and
then proceeds to consider logistic regression models for binary data,
log-linear models for count data-including rates and contingency tables and
hazard models for duration data. Attention is paid to the logical and
mathematical foundations of the techniques, but the main emphasis is on the
applications, including computer usage. Assumes prior exposure to statistics
at the level 507c or higher and familiarity with matrix algebra and
calculus. Prerequisite: 507c.
|
|
top
|
|
|
