Analysis of Complex Sample Data covers the following topics: the development and handling of selection and other compensatory weights for survey data analysis; the effects of stratification and clustering on survey estimation and inference; alternative variance estimation procedures for estimated survey statistics; methods and computer software that take into account the effects of complex sample designs on survey estimation and inference; and methods for handling missing data, including weighting adjustment.

This course investigates the practical application of Natural Language Processing (NLP) for analyzing textual data with the goal to answer questions of the social sciences. More specifically, participants of the previous theoretical class will now have the opportunity to implement their own practical research project. Under the guidance of the instructor, the participants will define their own research question; develop a suitable methodology to address this question; conduct and discuss experiments based on the selected methods; and synthesize the results to answer their own-defined research question.

This course will provide a gentle introduction to statistical disclosure control with a focus on generating synthetic data for maintaining the confidentiality of the survey respondents. The first part of the course will introduce several traditional approaches for data protection that are widely used at statistical agencies. Some limitations of these approaches will also be discussed. The second part of the course will introduce synthetic data as a possible alternative. This part of the course will discuss different approaches to generating synthetic datasets in detail. Possible modeling strategies and analytical validity evaluations will be assessed and potential measures to quantify the remaining risk of disclosure will be presented. To provide the participants with hands on experience, all steps will be illustrated using simulated and real data examples in R.

This course examines how to embed experiments in surveys. It covers both the design of survey experiments and the analysis of the results.

The main focus of this course lies on the introduction to statistical models and estimators beyond linear regression useful to social and economic scientists. It provides an overview of generalized linear models (GLM) that encompass non-normal response distributions to model functions of the mean. GLMs thus relate the expected mean E(Y) of the dependent variable to the predictor variables via a specific link function. This link function permits the expected mean to be non-linearly related to the predictor variables. Examples for GLMs are the logistic regression, regressions for ordinal data, or regression models for count data. GLMs are generally estimated by use of maximum likelihood estimation. The course thus not only introduces GLMs but starts with an introduction to the principle of maximum likelihood estimation. A good understanding of the classical linear regression model is a prerequisite and required for the course.

The amount of data generated as a by-product in society is growing fast including data from satellites, sensors, transactions, social media and smartphones, just to name a few. Such data are often referred to as "big data", and can be used to create value in different areas such as health and crime prevention, commerce and fraud detection. Big Data are often used for prediction and classification tasks. Both of which can be tackled with machine learning techniques. In this course we explore how Big Data concepts, processes and methods can be used within the context of Survey Research. Throughout this course we will illustrate key concepts using specific survey research examples including tailored survey designs and nonresponse adjustments and evaluation.

This course introduces students to the basics of Python and SQL for data analysis. Students will explore real publicly-available datasets, using the data analysis tools in Python to create summaries and generate visualizations. Students will learn the basics of database management and organization, as well as learn how to code in SQL and work with PostgreSQL databases. By the end of the class, students should understand how to read in data from CSV files or from the internet and be comfortable using either SQL or Python to aggregate, summarize, describe, and visualize these datasets.

The course will address methods to combine data on given entities (people, households, firms etc.) that are stored in different data sources. By showing the strengths of these methods and by showing how each of them are performed in practice using R, the course will demonstrate the various benefits of record linkage. Participants will also learn about potential challenges that record linkage projects may face.

Social scientists and survey researchers are confronted with an increasing number of new data sources such as apps and sensors that often result in (para)data structures that are difficult to handle with traditional modeling methods. At the same time, advances in the field of machine learning (ML) have created an array of flexible methods and tools that can be used to tackle a variety of modeling problems. Against this background, this course discusses advanced ML concepts such as cross validation, class imbalance, Boosting and Stacking as well as key approaches for facilitating model tuning and performing feature selection. In this course we also introduce additional machine learning methods including Support Vector Machines, Extra-Trees and LASSO among others. The course aims to illustrate these concepts, methods and approaches from a social science perspective. Furthermore, the course covers techniques for extracting patterns from unstructured data as well as interpreting and presenting results from machine learning algorithms. Code examples will be provided using the statistical programming language R.

Large data, fast pace of production, and collaboration are hallmarks of the new data environment. In this context, researchers must have a good understanding of data workflows and they must ensure consistent and reproducible practices in order to collaborate and consistently produce insights. This course deals with some of these essential topics. We will discuss the main types of workflows in data and survey sciences and how tools such as GitHub can enhance collaboration and insure reproducibility. We will also discuss the use of reproducible documents such as Rmarkdown or Jupyter Notebooks before covering how to work with distributed data using Spark. We will finish the course by discussing the use of dashboards and how to develop such tools using R Shiny.

We will discuss the theoretical and empirical properties of the two basic variance estimation strategies, namely Taylor series (linear) approximation and replication methods (including BRR, jackknife, and bootstrap) as they apply to several types of complex sample designs. We will study both descriptive statistics, such as means, and analytic statistics, such as linear and logistic regression. We will contrast model-based and design-based inference, the latter used as the standard in this course. Students will learn to use at least one survey software package with real survey data.

This course is a statistical methods class combining hands-on applications and general review of the theory behind different approaches to sampling.

In this course, students will apply the core skills that they learned in the IPSDS program to address real-world problems. The course will provide experience with the steps involved in carrying out a data consulting project, such as discussing the problems to solve with a client, data handling, and communicating work in both written and oral forms. The project is completed in teams (3-4 students per team).

This course provides a brief overview of the basics of probability and statistics. Students will review basic probability concepts and probability distributions, the Central Limit Theorem and hypothesis testing, and linear and logistic regression. Throughout this course, students should develop and reinforce proper statistical intuition. This includes knowing how to identify a sample and a population and applying appropriate statistical methods such as hypothesis testing, as well being able to identify different types of data and using the proper methods for each type of data. By the end of the course, students should have a strong foundation in statistics with which they can start their graduate coursework.

This course focuses on design and implementation considerations for different phases of the survey lifecycle when conducting surveys internationally or outside of one’s home country. Overview and considerations related to ten topics are discussed: Total Survey Error framework, project stakeholders, triple constraints, bids and contracts, sampling and sample management, questionnaire and instrument design, translation and adaptation, pretesting and cognitive interviews, interviewers and data collection, and interviewer monitoring.

The short course provides a condensed overview of web technologies and techniques to collect data from the web in an automated way. To this end, students will use the statistical software R. The course introduces fundamental parts of web architecture and data transmission on the web. Furthermore, students will learn how to scrape content from static and dynamic web pages and connect to APIs from popular web services. Finally, practical and ethical issues of web data collection are discussed.