Prerequisite:  Graduate student or advanced special student status.  This course does not fulfill elective requirements of the MS or PhD degree in survey methodology. 

Course Syllabus 

The field of survey methodology draws on theories and practices developed in several academic disciplines - mathematics, statistics, psychology, sociology, computer science, and economics.  To become an accomplished professional in the survey research field requires a mastery of research literatures as well as experience designing, conducting, and analyzing surveys.   

This course introduces the student to a set of principles of survey design that are the basis of standard practices in the field.  The course exposes the student to research literatures that use both observational and experimental methods to test key hypotheses about the nature of human behavior that affect the quality of survey data.  It will also present important statistical concepts and techniques in sample design, execution, and estimation, as well as models of behavior describing errors in responding to survey questions.  Thus, both social science and statistical concepts will be presented. 

The course uses the concept of total survey error as a framework to discuss coverage properties of sampling frames, alternative sample designs and their impacts on standard errors of survey statistics, alternative modes of data collection, field administration operations, the role of the survey interviewer, impacts of nonresponse on survey statistics, the effect of question structure, wording and context on respondent behavior, models of measurement error, postsurvey processing, and estimation in surveys. 

The course is intended as an introduction to the field, taught at a graduate level.  Lectures and course readings assume that students understand basic statistical concepts (at the level of an undergraduate course) and have exposure to elements of social science perspectives on human behavior.  For those lacking such a background, supplementary readings are recommended. 

Back to Course List 

This is an introductory course in mathematical statistics, presenting point estimation, sufficiency, completeness, Cramer-Rao inequality, maximum likelihood, confidence intervals for parameters of normal distributions, chi-square tests, analysis of variance, regression, correlation, and nonparametric methods. 

Back to Course List 

This is an introductory course in sampling theory, presenting simple random sampling, sampling for proportions, estimation of sample size, sampling with varying probabilities of selection, stratification, systematic selection, cluster sampling, double sampling, and sequential sampling. 

Back to Course List 

This course will examine one, two, three, and four-way layouts in analysis of variance, fixed effects models, linear regression in several variables, Gauss-Markov-Theorem, multiple regression analysis, and experimental designs. 

Back to Course List 

The purpose of this class is to learn basic statistical methods through the use of linear model theory and regression. Particular topics covered include one- and two-sample t-tests, multiple linear regression, analysis of variance, regression diagnostics, model-buiding techniques, random effects models, and mixed models. The emphasis will be to understand and apply the methods presented, and develop a feel for how problems in data analysis can be viewed in several different ways. In all cases the emphasis will be on understanding the techniques, rather than deriving their theoretical properties. The student will be expected to apply the techniques on weekly homework assignments, a midterm project, and a final project.

Back to Course List 

Builds on the introduction to linear models and data analysis provided in Statistical Methods I. Topics include: Multivariate analysis techniques (Hotelling's T-square, Principal Components, Factor Analysis, Profile Analysis, MANOVA); Categorical Data Analysis (contingency tables, measures of association, log-linear models for counts, logistic and polytomous regression, GEE) and Lifetime Data Analysis (Kaplan-Meier plots, logrank tests, Cox regression).

Back to Course List 

This course reviews alternative data collection techniques used in surveys. It concentrates on the impact these techniques have on the quality of survey data, including measurement error properties, levels of nonresponse, and coverage error. The course reviews the research literature in face-to-face interviewing, telephone surveys, and self-administered questionnaires. Special attention is paid to the statistical and social science literatures on interviewer effects and nonresponse. Current advances in computer assistance in data collection will also be reviewed, including computer assisted telephone interviewing (CATI), computer assisted personal interviewing (CAPI), touch tone data collection, and other methods. Students in the course will read and discuss the methodological research literature in the field and complete exercises that study the effects of different modes of data collection on survey data quality. 

Back to Course List 

Course Syllabus (Section 0101)
Course Syllabus (Section 0201)
Summer Course Syllabus

Prerequisite: Completion of either Social Statistics I (SURV 601) or Statistical Methods I (SURV 615), or a graduate course in statistics approved by the instructor.

Applied Sampling is an applied statistical methods course, but differs from most statistical methods courses. It is concerned almost exclusively with the design of data collection. The course examines problems of applying sampling methods to human populations, particularly the principles of sample selection and basic estimation. The course is at a moderately advanced statistical level, and while not developing the mathematical aspects of sampling theory, statistical notation and outlines of algebraic proofs will be given. The course will cover the main techniques used in sampling practice: simple random sampling, stratification, systematic selection, cluster sampling, multistage sampling, and probability proportional to size sampling. These methods will be elaborated in two types of sample designs, area probability and telephone sampling. The course will also cover sampling frames, cost models, sampling error estimation techniques, non-sampling errors, and compensating for missing data.

Back to Course List 

This course examines the stages of questionnaire design: developmental interviewing, question writing, question evaluation, pretesting, and questionnaire ordering and formatting. It reviews the literature on questionnaire construction, the experimental literature on question effects, and the psychological literature on information processing. In addition, the course reviews the effects of essential design features on questions and questionnaires, including mode of data collection, the use of computer assisted interviewing techniques, and self vs. proxy respondent selection. Students will both critique existing questions and questionnaires and follow the stages of questionnaire design in developing their own questionnaire. 

Back to Course List 

This course will examine major sources of survey error--such as reporting errors and nonresponse bias--from the perspective of social and cognitive psychology and related disciplines. It will cover such topics as the psychology of memory and its bearing on classical survey issues (e.g., underreporting and telescoping); models of language use and their implications for the interpretation and misinterpretation of survey questions; and studies of attitudes, attitude change, and their possible application to increasing response rates and improving the measurement of opinions. A range of theories and findings from the social and behavioral sciences will be explored in an effort to understand why survey errors occur and what can be done to reduce them. 

Back to Course List 

This two course sequence is an applied workshop in sample survey design, implementation, and analysis. During this first semester survey design is emphasized. Under the guidance of the instructor, students encounter the problem of moving from substantive concepts to questions on a survey questionnaire, designing a sample, and pretesting the questionnaire. 

Back to Course List 

The second semester of this two course sequence applied workshop emphasizes data collection and analysis. Students encounter the problem of administering the questionnaire to a sample, processing and editing the data, and analyzing the results. 

Back to Course List 

Back to Course List

The first of a two course sequence, this course reviews the U.S. statistical system and its goals. The federal statistical agencies are described, and their primary missions and data collections (both surveys and administrative records) are examined. The effects of the decentralized system are considered. The statistical systems of other countries are compared with the U.S. system. Organizational and budgetary aspects are presented. Statistical techniques and terms common to the U.S. Federal Statistical System are introduced. 

Back to Course List 

Requirements: Knowledge of regression analysis
Recommendations: SURV 615

Course Syllabus

This course introduces students to a wide range of models for analyzing categorical data.  Topics include loglinear models, binomial and multinomial logistic regression, and latent class models.  The focus will include the theoretical basis for these models, as well as a considerable emphasis on their application in the analysis of data.

Back to Course List 

This course will be research oriented seminar discussing fundamental issues in understanding nonresponse process, inventing methods to reduce nonresponse rates and error, and understanding its impact on statistical adjustments of inferences from incomplete data.

Back to Course List 

The course provides an introduction to survey research methods for designing multinational and multicultural surveys, beginning with an overview of the field of comparative surveys. It introduces students to the origin and development of important comparative surveys and discusses some unique design features and implementation challenges inherent in their design and implementation. Quality and risk management frameworks for comparative surveys are presented, as are tools for monitoring quality processes and outcomes. One section of the course focuses on issues in study design, considering organizational structure, data collection infrastructure and...sues in defining objectives, identifying constructs, developing questions, and monitoring design process quality that are particular to or especially complex in the field of comparative surveys. It also covers some technical challenges in crafting questions into actual instruments for different modes of application in a multilingual and multicultural context, dealing with issues such as the visual display of text in various languages, placement of response categories and instructions, use of color, screen density, and other features of contemporary survey instruments. The large section on design and implementation concludes with a module on question adaptation and translation focusing on the critical role that version production often plays and treatment of harmonization issues as these relate to the development and implementation of socio-demographic background variables. Examples will be drawn from demographic and social indicator surveys, attitudinal surveys, health and education surveys, and quality of life surveys. I expect to have two guest presenters contribute on areas of their special expertise.

Back to Course List 

Summer Course Syllabus

Prerequisite: This course is taught at an intermediate level, emphasizing both the theory and practice of the analysis of survey error. The course does not require rigorous training in mathematics; however, proficiency in basic mathematics is essential. Knowledge of calculus is useful but not required for the course. A first course in survey sampling methods and a basic understanding of sampling concepts such as stratification, clustering and weighting is required. Students should also have familiarity with basic statistical concepts, such as point estimates, sampling variance, confidence intervals, p-values and the maximum likelihood method of estimation. Familiarity with logistic regression models is useful but not required.

This course presents a statistical framework for modeling and estimating classification error in surveys. It begins by examining some of the early models for survey measurement error (Census Bureau models; Kish model; etc.) and demonstrating their similarities, strengths and weaknesses. Then these models are cast in a general latent class modeling (LCM) framework where the true values of a variable are assumed to be unobserved (latent) and the survey response constitutes a single indicator of this latent variable. The model parameters include the target population proportions for a categorical variable to be estimated in the survey and the misclassification probabilities (for e.g., false positive and false negative, for dichotomous response variables) for measuring the variable. Survey item reliability and construct validity as well as estimator bias are defined and interpreted within this general framework. Methods for estimating the model parameters and issues of model identifiability will be discussed.

...ine the allocation.

The second project will be to use a set of data collected from a sample of military personnel and develop survey weights.  The weights should account for cases with unknown eligibility, nonrespondents, and uses of auxiliary data to improve estimators.  Students will devise quality control checks and will set up the analysis file to allow use of either linearization or replication variance estimation.

A third application will be an area probability design in which students will use an existing sample of primary units and determine a plan for sampling segments and persons within segments.  Rates will be determined to achieve target sample sizes for different demographic groups.

Back to Course List 

Back to Course Listist 

Course Syllabus

This seminar will explore how emerging communication technologies will shape the survey interview of the future. We will ask - and attempt to answer - questions such as:

• How is video telephony likely to impact the quality of survey responses?
  
• Will respondents react to animated interviewing agents as if they are human interviewers, or just an object in the user interface of a self-administered questionnaire, or something in between?
  
• Are respondents more willing to lie when they speak than when their communication leaves a textual trace as in Instant Messaging or email?
  
• What kinds of paradata (information about the response process that can be informative about data quality) are made available by new communication technologies, e.g. respondents' facial expressions, direction of gaze while answering, posture, etc.?

Prerequisites: familiarity with the growing literature on cognitive aspects of survey methodology; SURV 632 or SURV METH 632 unless permission is obtained from the instructors

This course will cover four topics relating findings from the cognitive sciences to problems in survey research.  The four topics are improving comprehension of survey questions, conversational analytic approaches to the interactions between interviewers and respondents, visual effects in the design of self-administered and web questionnaires, and cognitive interviewing.

Back to Course List 

Back to Course List

Advanced Topics in Survey Methodology: Measurement Error Models
SURV 699M

This course examines both the impact of measurement error on many standard statistical techniques, as well as methods which directly incorporate measurement error information into statistical modeling. Particular emphasis is placed on regression models, and how various kinds of measurement error information can be used to "correct" standard methods. Emphasis is placed both on theoretical aspects, including large sample theory, as well as applications using computer
software including R and STATA. The course completely covers the material in the textbook Measurement Error Models by Wayne A. Fuller, which was the first textbook dedicated entirely to errors-in-variable methods.

Back to Course List 

Course Syllabus

Course Syllabus

Prerequisite: Data Collection Methods in Survey Research

This advanced seminar will cover selected topics on computer assisted survey data collection in depth. Students will be exposed to the survey and related literature and key gaps in knowledge or challenges facing the field. Key topics will include the design, programming and testing (both functionality and usability) of CAI instruments; the hardware, software, and infrastructure to support computer assisted surveys (e.g., case management, call scheduling, etc.); and the role of data, metadata, and paradata in computer-assisted surveys. Students will get hands-on experience programming both CAI surveys (using Blaise) and Web survey (using GlobalPark’s software). A key focus will be on design issues.

Back to Course List 

This course will examine testing hypotheses: parametric methods. Neyman-Pearson lemma. Uniformly most powerful tests. Locally optimal tests. Large sample theory, asymptotically best procedures. Nonparametric methods, Wilcoxen, Fisher-Yates, median tests. Linear models, analysis of variance, regression and correlation. Sequential analysis. 

Back to Course List 

This introductory course on the analysis of data from complex sample designs covers: the development and handling of selection and other compensatory weights; methods for handling missing data; the effect of stratification and clustering on estimation and inference; alternative variance estimation procedures; methods for incorporating weights, stratification, clustering, and imputed values in estimation and inference procedures for complex sample survey data; and generalized design effects and variance functions. The course will utilize exercises on real survey data to illustrate the methods addressed in class. Students will learn the use of computer software that takes account of complex sample design in estimation. 

Back to Course List 

This course reviews the total error structure of sample survey data, reviewing current research findings on the magnitudes of different error sources, design features that affect their magnitudes, and interrelationships among the errors. Coverage, nonresponse, sampling, measurement, and postsurvey processing errors are treated. For each error source reviewed, social science theories about its causes are first presented. Next statistical models estimating the error source are described. Whenever possible empirical studies from the survey methodological literature are reviewed in order to illustrate the relative magnitudes of error in different designs. Emphasis will be placed on aspects of the survey design necessary to estimate different error sources. Relationships among the different error sources will be presented to show how attempts to control one source may increase another source. Attempts to model total survey error will be presented.

Students in the class will identify one research project, preferably one connected to their current work, that offers an opportunity for empirical investigation of one or more error sources. An analysis paper presenting the findings of the project will be submitted at the end of the course.

Back to Course List 

Course Syllabus

Back to Course List

This course treats research designs from which causal inferences are sought. Classical experimental design will be contrasted with quasi-experiments, evaluation studies, and other observational study designs. Emphasis will be placed on how design features impact the nature of statistical estimation and inference from the designs. Issues of blocking, balancing, repeated measures, control strategies, etc., will be treated. 

Back to Course List 

Inference from complex sample survey data covers the theoretical and empirical properties of various variance estimation strategies (e.g., Taylor series approximation, replicated methods, and bootstrap methods for complex sample designs) and how to incorporate those methods into inference for complex sample survey data. Variance estimation procedures are applied to descriptive estimators and to analysis techniques such as regression, analysis of variance, and analysis of categorical data. Generalized variances and design effects are presented. Methods of model-based inference for complex sample surveys are also examined, and the results contrasted to the design-based type of inference used as the standard in the course. The course will use real survey data to illustrate the methods discussed in class. Students will learn the use of computer software that takes account of the sample design in estimation.
 
Back to Course List 

This course is an advanced course in selected topics in survey sampling. Topics to be covered include: estimation and imputation approaches; small area estimation; and sampling methods for rare populations. A selection of additional topics, chosen by the instructor, will also be covered. Examples of such additional topics are: sample designs for time and space; panel and rotating panel survey designs; maximizing overlap between samples; controlled selection and lattice sampling; sampling with probabilities proportionate to size without replacement; multiple frame sampling; adaptive cluster sampling; capture-recapture sampling; sampling for telephone surveys; sampling for establishment surveys; and measurement error models. Both applied and theoretical aspects of the topics will be examined.
 
Back to Course List 

This course describes modern practices in the administration of large scale surveys. It reviews alternative management structures for large field organizations, supervisory and training regimens, handling of turnover, and multiple surveys with the same staff. Practical issues in budgeting of surveys are reviewed with examples from actual surveys. Scheduling of sequential activities in the design, data collection, and processing of data is described.
 
Back to Course List 

Course Syllabus

Model-based small-area estimation has portance oer the past two decades. Students will learn the state-of-the-art model-based small-area estimation methods (e.g., empirical best prediction, empirical Bayes and hierarchical Bayes, etc.) and the associated important issues regarding measures of uncertainty, model selection, model diagnostics, design-consistency, etc. The bootstrap, jackknife, and delta methods will be discussed in details in the context of measuring uncertainty of EB/EBP. In order to explain certain concepts, it will be necessary to go through a few derivations. Data analyses using several real life examples will be presented. Application of SAS and BUGS in certain small-area data analyses will be shown. The course includes practical exercises.

Back to Course List 

This is an advanced course especially meant for Ph.D. students in statistics or a related field.  The course will begin with the basic concepts in Bayesian inference using simple models.  The Bayesian methodology will then be illustrated for a variety of models in common use.  The models will include linear and generalized linear models, variance component models and mixed models. The modern Bayesian computing, various approximation methods, and model selection will be discussed.

Back to Course List 

Back to Course List