DEPARTMENT OF STATISTICS AND DATA SCIENCE

Course available to First-Year students, topic varies

This course is an introduction programming for Data Science. It will prepare students to use essential programming methods as implemented in either Python or R as a tool in the subsequent data science courses including STAT 301-1, STAT 301-2, STAT 301-3, STAT 303-1, STAT 303-2, STAT 303-3, STAT 304-0, STAT 305-0, STAT 362-0, and STAT 390-0, etc.

Please note STAT 201-0 is an introductory programming course for statistics and data science, not an introductory statistics course. It will not satisfy the requirement of "an introductory statistics course" and cannot be used as a substitution for STAT 202-0, STAT 210-0, or STAT 232-0.

For: Undergraduate students

Data collection, summarization, correlation, regression, sampling, confidence intervals, tests of significance. Introduction to data analysis techniques using R programming, no prior programming experience required. Does not require calculus and makes minimal use of mathematics.

For: Undergraduate students

Typically offered: Yearly in Fall, Winter, Spring

NOTE: May not receive credit for both STAT 202-0 and STAT 210-0.

When selecting an introductory statistics course to fulfill a major/minor requirement, students should consult the Undergraduate Catalog and/or the department to confirm the course they want to register for will fulfill the requirement.

A mathematical introduction to probability theory and statistical methods, including properties of probability distributions, sampling distributions, estimation, confidence intervals, and hypothesis testing. STAT 210-0 is primarily intended for economics majors.

Prerequisite: strong background in high school algebra (calculus is not required).

For: Undergraduate students

Typically offered: Yearly in Fall, Winter, Spring

NOTE: May not receive credit for both STAT 202-0 and STAT 210-0. 

When selecting an introductory statistics course to fulfill a major/minor requirement, students should consult the Undergraduate Catalog and/or the department to confirm the course they want to register for will fulfill the requirement.

Sequences and series, and convergence tests. Power series, Taylor polynomials and error. Double integrals, triple integrals, and change of variables.

Students may receive credit for only one of MATH 235‐0, MATH 226‐0, or STAT 228‐0.

Prerequisite: MATH 218-3 or MATH 220-2, and MATH 228-1 or MATH 230-1 or MATH 281-1 or MATH 285-2 or MATH 290-2 or MATH 291-2 or ES_APPM 252-1.

For: Undergraduate students

Typically offered: Yearly

Enrollment in STAT 228-0 is restricted to declared Data Science majors and Statistics majors and minors.

Basic concepts of using statistical models to draw conclusions from experimental and survey data. Topics include simple linear regression, multiple regression, analysis of variance, and analysis of covariance. Practical application of the methods and the interpretation of the results will be emphasized.

Prerequisites: STAT 202-0, STAT 210-0, or consent of the instructor; MATH 220-1.

For: Undergraduate students

Typically offered: intermittently

NOTE: Registration for STAT 301-1,2,3 is restricted to Data Science minors, Data Science majors, Statistics majors, Ad Hoc Masters Applied Statistics students. Registration priority is given to undergraduate students with a declared Data Science minor or major and graduate students accepted into the ad hoc MS in Applied Statistics program with the course on their approved plan of study

301-1: First course in Data Science, with focus on data management, manipulation, and visualization skills and techniques for exploratory data analysis. The course also introduces the R programming language in the context of Data Science. Students may not receive credit for both this course and STAT 303-1.

Prerequisite: STAT 201-0 or COMP_SCI 110-0 and STAT 202-0 or STAT 210-0 or consent of the instructor.

Typically offered: Yearly in Fall

For: Graduate students and Undergraduate students

301-2: Introduction to supervised machine/statistical learning with a focus on application using R. Course covers essential concepts in machine learning while surveying standard machine learning models such as linear and logistic regression. Course provides a foundation for learning more machine learning methods. Students may not receive credit for both this course and STAT 303-2.

Prerequisite: STAT 301-1 or consent of instructor.

Typically offered: Yearly in Winter

For: Graduate students and Undergraduate students

301-3: An intermediate course that covers machine learning methods in R, including supervised and unsupervised learning. It provides the knowledge and skills necessary to tackle real world problems with machine learning. Students may not receive credit for both this course and STAT 303-3.

Prerequisite: STAT 301-2 or consent of the instructor.

Typically offered: Yearly in Spring

For: Graduate students and Undergraduate students

NOTE: Registration for STAT 302 is restricted to Data Science minors, Data Science majors, Statistics majors, Ad Hoc Masters Applied Statistics students. Registration priority is given to undergraduate students with a declared Data Science minor or major and graduate students accepted into the ad hoc MS in Applied Statistics program with the course on their approved plan of study

Introduction to the knowledge, skills, and tools required to visualize data of various formats across statistical domains and to create quality visualizations for both data exploration and presentation.

Prerequisite: STAT 201-0 or COMP_SCI 110-0 and STAT 202-0 or equivalent

Typically offered: Yearly

For: Graduate students and Undergraduate students

NOTE: Registration for STAT 303-1,2,3 is restricted to Data Science minors, Data Science majors, Statistics majors, Ad Hoc Masters Applied Statistics students. Registration priority is given to undergraduate students with a declared Data Science minor or major and graduate students accepted into the ad hoc MS in Applied Statistics program with the course on their approved plan of study

303-1: First course in Data Science, with focus on data management, manipulation, and visualization skills and techniques for exploratory data analysis. The course also introduces the Python programming language in the context of Data Science. Students may not receive credit for both this course and STAT 301-1.

Prerequisite: STAT 201-0 or COMP_SCI 110-0 and STAT 202-0 or STAT 210-0 or consent of the instructor.

Typically offered: Yearly in Fall

For: Graduate students and Undergraduate students

303-2: Introduction to supervised machine/statistical learning with a focus on application using Python. Course covers essential concepts in machine learning while surveying standard machine learning models such as linear and logistic regression. Course provides a foundation for learning more machine learning methods. Students may not receive credit for both this course and STAT 301-2.

Prerequisite: STAT 303-1 or consent of the instructor. Python experience required.

Typically offered: Yearly in Winter

For: Graduate students and Undergraduate students

303-3: An intermediate course that covers machine learning methods in Python, including supervised and unsupervised learning. It provides the knowledge and skills necessary to tackle real world problems with machine learning. Students may not receive credit for both this course and STAT 301-3.

Prerequisite: STAT 303-2 or consent of the instructor. Python experience required.

Typically offered: Yearly in Spring

For: Graduate students and Undergraduate students

NOTE: Registration is restricted to Data Science majors and students in select Statistics graduate programs

This course will introduce students to the design, implementation, analysis, and proper application of abstract data types, data structures, and their algorithms. Python will be used to implement and explore various algorithms and data structures. Students should be prepared for a significant amount of hands-on programming.

Prerequisites: STAT 201-0 or COMP_SCI 110-0 and STAT 202-0 or STAT 210-0 or STAT 232-0

Python experience recommended.

Typically offered: Yearly

For: Undergraduate students

Enrollment in STAT 304-0 is restricted to declared Data Science majors. Statistics majors and Data Science minors by department permission if space allows.

NOTE: Registration is restricted to Data Science majors and students in select Statistics graduate programs

This course aims to give students an extensive data processing and visualization skillset using various Python libraries. It will also focus on relational databases and queries in SQL. Students will learn data scraping from online sources and mobile applications as well as a brief introduction to statistical and predictive analysis after the data is clean and ready to use.

Prerequisites: STAT 201-0 or COMP_SCI 110-0 and STAT 202-0 or STAT 210-0 or STAT 232-0

Python experience recommended.

Typically offered: Yearly

For: Undergraduate students

Enrollment in STAT 305-0 is restricted to declared Data Science majors. Statistics majors and Data Science minors by department permission if space allows.

Statistical Theory and Methods 1: Sample spaces, computing probabilities, random variables, distribution functions, expected values, variance, correlation, limit theory.  Co-requisites: STAT 202-0 or STAT 210-0, and STAT 228-0 or MATH 235-0 or both MATH 226-0 and MATH 230-2

Typically offered: Yearly in Fall

For: Undergraduate students and Graduate students

NOTE: May not receive credit for both STAT 320-1 and any of STAT 383-0, MATH 310-1, MATH 311-1, MATH 314-0, MATH 385-0, ELEC_ENG 302-0, or IEMS 202-0.

Statistical Theory and Methods 2: Parameter estimation, confidence intervals, hypothesis tests.

Prerequisite: STAT 320-1 or equivalent course* (STAT 383-0, MATH 310-1, MATH 311-1, MATH 314-0, MATH 385-0, ELEC_ENG 302-0, or IEMS 302-0)

*NOTE: If you take a STAT 320-1 equivalent course, please see this pdf for information on the topics that may not be covered in the equivalent course but that you will be required to understand for STAT 320-2. Students who have not taken STAT 320-1 are responsible for independently learning these topics prior to starting STAT 320-2.

Typically offered: Yearly in Winter

For: Undergraduate students and Graduate students

Statistical Theory and Methods 3: Comparison of parameters, goodness-of-fit tests, regression analysis, analysis of variance, and nonparametric methods.

Prerequisites: STAT 320-2, MATH 240-0

Typically offered: Yearly in Spring

For: Undergraduate students and Graduate students

Probability sampling, simple random sampling, error estimation, sample size, stratification, systematic sampling, replication methods, ratio and regression estimation, cluster sampling.

Prerequisites: MATH 230-1 or MATH 228-1 and 2 quarters of statistics, or consent of instructor

Typically offered: currently not offered

For: Undergraduate students and Graduate students

Introduction to modern statistical thinking about causal inference. Topics include completely randomized experiments, confounding, ignorability of assignment mechanisms, matching, observational studies, noncompliance, and Bayesian methods.

Prerequisites: STAT 320-2, STAT 350-0

Typically offered: Yearly

For: Undergraduate students and Graduate students

Design of experiments and surveys, numerical summaries of data, graphical summaries of data, correlation and regression, probability, sample mean, sample proportion, confidence intervals and tests of significance, one and two sample problems, ANOVA.

Typically offered: Yearly in Fall

For: Graduate students

Application of statistical methods and data analysis techniques to the life sciences. Descriptive statistics, normal distribution, random variables, sampling distribution, confidence intervals, hypothesis tests, p-values and multiple correction, linear and non-linear regression, variable selection, diagnostics, logistic regression, contingency tables, resampling, clustering, classification, and dimension reduction.

Prerequisite: 1 introductory statistics course

For: Undergraduate students*

*Combined section with IBIS 432-0-1 for graduate students

NOTE: this course cannot be counted toward a major or minor in Statistics

Permission number required to register for this course

Exploration of theory and practice of computational statistics for simulation and statistical inference with emphasis on statistical programming in R. Prerequisite: STAT 320-2 or equivalent.

Prerequisite: STAT 320-2 or consent of the instructor

Typically offered: Yearly in Fall

For: Undergraduate students and Graduate students

Statistical methods for describing and analyzing multivariate data. Principal component analysis, factor analysis, canonical correlation, clustering. Emphasis on statistical and geometric motivation, practical application, and interpretation of results.

Prerequisites: STAT 320-2, MATH 240-0, and STAT 350-0

Typically offered: Intermittently

For: Undergraduate students and Graduate students

Simple linear regression and correlation, multiple regression, residual analysis, model building, variable selection, multi-collinearity and shrinkage estimation, nonlinear regression.

Prerequisite STAT 201-0 or COMP_SCI 110-0 and STAT 202-0 or STAT 210-0 or STAT 232-0 or PSYCH 201 or IEMS 201 or IEMS 303.

Co-requisite: STAT 320-1 or STAT 383-0 or MATH 310-1 or MATH 311-1 or MATH 314-0 or MATH 385-0 or ELEC_ENG 302-0 or IEMS 202-0

Typically offered: Yearly in Fall, also offered in Winter in some years

For: Undergraduate students and Graduate students

Methods of designing experiments and analyzing data obtained from them: one-way and two-way layouts, incomplete block designs, factorial designs, random effects, split-plot and nested designs.

Prerequisite: STAT 320-1 or MATH 310-1 or MATH 314 or consent of the instructor

Typically offered: Yearly

For: Undergraduate students and Graduate students

Survey of nonparametric methods, with emphasis on understanding their application. Estimation of a distribution function, density estimation, and nonparametric regression.

Prerequisite: STAT 350-0

Typically offered: Intermittently

For: Undergraduate students and Graduate students

This course covers modern regression methods, including: (1) generalized linear models (binary, categorical, and count data), (2) random effects, mixed effects, and nonlinear models, and (3) model selection. The course emphasizes both the theoretical development of the methods, as well as their application, including the communication of models and results both verbally and in writing.

Co-requisites: STAT 320-2 or 420-2 or MATH 310-2 and a first course in regression is required at the level of STAT 350-0.

Typically offered: Yearly

For: Graduate students and Undergraduate students

Introduction to modern time series analysis. Autocorrelation, time series regression and forecasting, ARIMA and GARCH models.

Prerequisites: STAT 320-1. Corequisite: STAT 350-0.

Typically offered: Yearly

For: Undergraduate and Graduate students

Introduction to the theory and application of hierarchical linear models. Two and three level linear models, hierarchical generalized linear models, and application of hierarchical models to organizational research and growth models.

Prerequisites: STAT 320-2, STAT 350-0

Typically offered: every other year, last offered Spring 2019

For: Undergraduate students and Graduate students

Introduction to basic concepts and principles in Bayesian inference such as the prior, likelihood, posterior and predictive distributions, as well as an introduction to a variety of computational algorithms for Bayesian inference. Students learn how to develop, describe, implement and critique statistical models from a Bayesian perspective. 

Prerequisites: STAT 320-1, STAT 320-2, STAT 301-2 or 350-0, or consent of instructor. 

Topics in theoretical and applied statistics to be chosen by instructor.

Prerequisites: variable, see course description in CAESAR

Typically offered: variable

For: Undergraduate students and Graduate students

NOTE: Registration is restricted to Data Science majors

This course aims to focus on the theory and applications of advanced Machine Learning (ML) and Deep Learning (DL) topics. It also includes an introduction to Bayesian Modeling and Reinforcement Learning (RL). The students are expected to have a basic understanding of ML from STAT 301-1-2-3/303-1-2-3. The coding language for the homework projects is Python.

Prerequisites: STAT 301-3 or STAT 303-3. Co-requisite MATH 240-0.

Typically offered: Yearly

For: Undergraduate students

Enrollment in STAT 362-0 is restricted to declared Data Science majors. Statistics majors and Data Science minors by department permission if space allows.

Statistical methods for analyzing financial data. Models for asset returns, portfolio theory, parameter estimation. The statistical software R is used.

Prerequisites: STAT 320-3, MATH 240-0

Typically offered: variable

For: Undergraduate students and Graduate students

Development, analysis, interpretation, use, and misuse of statistical data and methods for description, evaluation, and political action regarding war, disappearances, justice, violence against women, trafficking, profiling, elections, hunger, refugees, discrimination, etc.

Prerequisites: Two of STAT 325-0, STAT 350-0, STAT 320-2, STAT 320-3; or ECON 381-1, ECON 381-2; or MATH 386-1, MATH 386-2; or IEMS 303-0, IEMS 304-0

Typically offered: currently not offered

For: Undergraduate students and Graduate students

Probability and statistics. Ordinarily taken only by students in ISP; permission required otherwise.

Prerequisites: MATH 281-1, MATH 281-2, MATH 281-3; PHYSICS 125-1, PHYSICS 125-2, PHYSICS 125-3.

NOTE: May not receive credit for both STAT 383-0 and any of STAT 320-1; MATH 310-1, MATH 311-1, MATH 314-0, MATH 385-0; EECS 302-0; or IEMS 202-0. 

NOTE: this course cannot be counted toward a major or minor in Statistics

NOTE: Registration is restricted to Data Science majors

An opportunity to develop and create solutions for stakeholders with data needs. Students will work in teams to appropriately scope and solve data problems. Students should expect to spend significant amounts of time coordinating and working with team mates outside of class.

Prerequisites: STAT 301-3 or STAT 303-3 or consent of instructor

Typically offered: Yearly

For: Undergraduate students

Enrollment in STAT 390-0 is restricted to declared Data Science majors.

Independent work under the guidance of a faculty member.

NOTE: Consent of department and instructor required

For: Undergraduate students

This course is for students doing advanced studies in statistics and certain other fields will provide an introduction to modern machine learning methods. Topics include supervised learning, sparsity, logistic regression, SVM, kernel methods, deep learning, unsupervised learning, and real world problems including fairness and interpretability of black box models.

Not for data science majors/minors - students studying data science should take STAT 362-0 instead.

Prerequisites: Math 240-0, Math 230-2, and STAT 320-2 or statistics graduate standing

Typically offered: Yearly

For: Graduate students

Introduction to Statistical Theory & Methodology 1: Distribution theory, characteristic functions, moments and cumulants, random variables, sampling theory, and common statistical distributions.

Typically offered: Yearly in Fall

For: Graduate students

Introduction to Statistical Theory & Methodology 2: Methods of estimation, hypothesis tests, confidence intervals, least squares, likelihood methods, and large-sample methods.

Typically offered: Yearly in Winter

For: Graduate students

Introduction to Statistical Theory & Methodology 3: Normal linear models and its various extensions

Typically offered: Yearly in Spring

For: Graduate students

Sampling designs (simple random, unequal probability, stratified, cluster, systematic, random walk, induced, multiphase, choosing sample sizes), sample adjustment (weighting/calibration), variance estimation, non-sampling errors, topics re government statistical agencies.

Prerequisites: Two previous courses in probability and statistics, at least one at the 300 level in Statistics (other than STAT 330-0), Econometrics, IE/MS, Math; or permission of instructor

Typically offered: currently not offered

For: Graduate students

Foundations of measure theoretic probability, with applications to statistics.

Prerequisites: MATH 320-1 and STAT 420-1

Typically offered: yearly in Fall

For: Graduate students

A second course in measure-theoretic probability, with an eye towards statistics. Topics include Markov chains, conditional expectation, martingales, Poisson processes, Brownian motion, and selected advanced topics, together with statistical applications.

Prerequisite: STAT 430-1 or permission of instructor.

Typically offered: yearly in Winter

For: Graduate students

In this course, students are expected to explore some mathematical foundations of modern machine learning under a problem-solving framework. Topics include probability theory, frequentist statistics, Bayesian statistics, tensor algebra, vector calculus, convex and stochastic optimization, stochastic processes and sampling, Markov Chain Monte Carlo, sequential optimization and dynamic programming. This class strongly emphasizes on developing problem-solving skills.

Prerequisite: 420-1 (recommended but not required)

Typically offered: Yearly

For: Graduate students

Statistical methods for combining results of replicated experiments. Effect size indexes and their estimators, combined estimation and test of heterogeneity, modeling between-study variation in effect sizes, models for publication selection.

Prerequisites: A graduate-level course in statistics

Typically offered: every other year, last offered Spring 2018

For: Graduate students

We introduce statistical applications of stochastic processes, such as in survival analysis, Markov Chain Monte Carlo, and clinical trials. An integral part will be the student presentations on related topics.

Prerequisites: STAT 420-1, STAT 420-2, STAT 420-3, STAT 430-1, and STAT 430-2

Typically offered: yearly in Spring

For: Graduate students

Probit, logit, log-linear, and latent-class models. Multi-dimensional contingency tables; polytomous responses with continuous independent variables.

Prerequisites: STAT 350-0 and STAT 420-3

Typically offered: variable

For: Graduate students

Inference and fitting of generalized linear models with application to classical linear models, binomial and multinomial logit models, log-linear models, Cox's proportional hazards model and GEE's for longitudinal data.

Prerequisites: STAT 350-0 and STAT 420-3

Typically offered: every other year, last offered Fall 2018

For: Graduate students

Introduction to computational algorithms for Bayesian inference. Observed data and data augmentation methods are considered in detail. Methods are illustrated with real examples.

Prerequisites: STAT 350-0 and 420-1,2,3 or equivalent or students who have earned a Master’s degree in Statistics or permission of the instructor.

Typically offered: Yearly

For: Graduate students

Topics in theoretical and applied statistics to be chosen by instructor.

Prerequisites: variable, see course description in CAESAR

Typically offered: variable

For: Graduate students

An introduction of statistical methodologies in cutting-edge fields of computational biology and bioinformatics topics including microarray data analysis; biological sequence analysis; ChIP-seq; RNA-seq; scRNA-seq and Crispr-cas9 data etc. Prerequisite: STAT 202 or equivalent

Typically offered: Yearly

For: Graduate students

Independent work under the guidance of a faculty member.

NOTE: Consent of instructor required

For: Graduate students

It is an internship program where students would do an unpaid or paid internship on campus or in a non-NU company.

NOTE: Consent of department required

For: Statistics MS Graduate students