Ph.D. Track for Statistics in the Social Sciences

Contact the Statistics Department for enrollment information.

The goal of the PhD track is to provide education in a particular area of social science for Ph.D. students in Statistics. This is sufficient as one of the three core sequences required for a Ph.D. in Statistics.

The core requirements of the track consist in:

1. Taking 3 graded courses in the chosen area of social science, from a list of such sets approved by the Statistics faculty; students are expected to take courses if necessary to satisfy pre-requisite requirements of these courses.
2. Taking 2 STAT/CS&SS courses from a list of 7.

For a more detailed description of requirements, please see summarizing document here. At the present time there are two areas of subject specialization: Statistical Demography and Econometrics.

Other subject area sequences may be added later by action of the Statistics faculty. Students who complete the 5 courses can waive one of the three core sequences currently required for the Ph.D. in Statistics. However, in this case the student must satisfactorily complete either the Probability Sequence (521-522-523) or the Statistical Theory sequence (581-582-583).

Additionally, at least three consecutive quarters of participation in the CS&SS seminar (1 credit/quarter) will be required.

Track Requirements (see below for course descriptions):

CS&SS Seminar (CS&SS 590)

(i) Subject area courses: students take sequence (a) or (b)

(A) Statistical Demography: SOC 431; SOC 433; SOC 513

(B) Econometrics: ECON 583, ECON 584, ECON 585

including any courses required to satisfy pre-requisite requirements.

(ii) STAT/CS&SS courses: students complete 2

STAT/CS&SS 536, 544, 560, 564, 566, 567

CS&SS 565

STAT 519 (Recommended for students specializing in Time Series Econometrics)

Course Descriptions

(i) SUBJECT SEQUENCES

A. STATISTICAL DEMOGRAPHY SEQUENCE

SOC 431 Fertility and Mortality (3)

Theories of fertility and mortality, demographic transitions, individual variations. Specific analytic approaches. Familiarity with basic fertility and mortality measures, and with the life table, is assumed.

SOC 433 Research Methods in Demography (3)

Basic measures and models used in demographic research. Sources and quality of demographic data. Rate construction, standardization, the life table, stable population models, migration models, population estimation and projection, measures of concentration and dispersion, measures of family formation and dissolution.

SOC 513 Demography and Ecology (3)

Theories and research on human fertility, mortality, mobility, migration, and urbanization in social/economic context. Comparative and historical materials on Europe, the United States, and the Third World.

B. ECONOMETRICS SEQUENCE

ECON 583 Econometric Theory I (3)

Estimation and testing in linear and nonlinear regression models. Asymptotic theory, bootstrapping. Theoretical developments are reinforced with a variety of empirical examples and applications.

ECON 584 Econometric Theory II (3)

Continuation of 583. Analysis of stationary and nonstationary, univariate, and multivariate time series models. Emphasis on empirical applications.

ECON 585 Applied Microeconometrics (3)

Econometric issues that arise in applied microeconomic research. Topics include the use of panel data and models with limited and qualitative dependent variables.

(ii) STAT and CS&SS COURSES

519 Time Series Analysis (3)

Descriptive techniques. Stationary and nonstationary processes, including ARIMA processes. Estimation of process mean and autocovariance function. Fitting ARIMA models to data. Statistical tests for white noise. Forecasting. State space models and the Kalman filter. Robust time series analysis. Regression analysis with correlated errors. Statistical properties of long memory processes. (This course is recommended for students specializing in Time-Series Econometrics.)

536 Log-Linear Modeling and Logistic Regression for the Social Sciences(3)

Log-linear modeling of multidimensional contingency tables. Logistic regression. Applications to social mobility, educational opportunity, and assortative marriage. Applied and computing focus.

544 Bayesian Statistical Methods (3)

Statistical methods based on the idea of a probability distribution over the parameter space. Coherence and utility. Subjective probability. Likelihood principle. Conjugate families. Structure of Bayesian inference. Limit theory for posterior distributions. Sequential experiments. Exchangeability. Bayesian nonparametrics. Empirical Bayes methods.

560 Hierarchical Modeling for the Social Sciences (4)

Explores ways in which data are hierarchically organized, such as voters nested within electoral districts that are in turn nested within states. Provides a basic theoretical understanding and practical knowledge of models for clustered data and a set of tools to help make accurate inferences.

564 Bayesian Statistics for the Social Sciences (4)

Statistical methods based on the idea of probability as a measure of uncertainty. Topics covered include subjective notion of probability, Bayes' Theorem, prior and posterior distributions, and data analysis techniques for statistical models.

565 Inequality: Current Trends and Explanations (3)

This course will cover the recent growth in economic inequality in the US, and the competing explanations for these new trends. The explanations take three forms: those that emphasize supply side shifts in the demographics of the labor market; those that emphasize the demand side shifts in industrial composition and firm-level restructuring; and those that emphasize the broader political context that affects policies like the minimum wage, the strength of unions, and the impact of foreign trade. We focus strongly on evaluating the data and methods used to make these arguments.

566 Causal Modeling (3)

Construction of causal hypotheses. Theories of causation, counterfactuals, intervention vs. passive observation. Contexts for causal inference: randomized experiments; sequential randomization; partial compliance; natural experiments, passive observation. Path diagrams, conditional independence and d-separation. Model equivalence and causal under-determination.

567 Statistical Analysis of Social Networks (4)

Statistical and mathematical descriptions of social networks. Topics include graphical and matrix representations of social networks, sampling methods, statistical analysis of network data, and applications.