Course Materials

Material status
Required
Optional

# Module 1

Introduction

Learning objectives: Explain what empirical research contributes to public policy and administration; distinguish questions that data can answer from questions it cannot; and set up the tools we will use all semester, including the course website, Canvas, and Google Colab.

Before class

  • Wheelan, Naked Statistics. Introduction and Chapter 1, “What’s the Point?”Optional

# Module 2

Research Design

Learning objectives: Describe how theory, models, and research questions fit together; distinguish descriptive, causal, and normative questions; and turn a broad policy interest into a research question that can actually be answered with evidence.

Before class

  • Remler & Van Ryzin, Chapter 1. Research in the Real World.Required
  • Remler & Van Ryzin, Chapter 2. Theory, Models, and Research Questions. You can skip “Logic Models: Mechanisms of Programs” and “Alternative Perspectives on Theory in Social Research.”Required

# Module 3

Measurement & Central Tendency

Learning objectives: Explain how validity, reliability, measurement error, and levels of measurement affect the quality of policy research; identify appropriate measures of central tendency; and calculate and interpret means, medians, and modes.

Before class

  • Remler & Van Ryzin, Chapter 8. Making Sense of Numbers. You can skip “Relationships Between Categorical Variables,” “Practical Significance,” and “Statistical Software.”Required
  • Remler & Van Ryzin, Chapter 4. Measurement. Focus on “What Is Measurement?,” “Validity” (excluding criterion-related validity), “Measurement Error,” “Reliability,” “Validity and Reliability: Contrasted and Compared,” and “Levels of Measurement.”Optional

# Module 4

Distribution of Data

Learning objectives: Calculate and interpret standard deviation, coefficient of variation, and z-scores; use the standard normal distribution to compare observations measured on different scales; describe the direction and strength of relationships between numerical variables using scatterplots and Pearson’s correlation coefficient; and create simple data subsets based on specified criteria.

Before class

# Module 5

Sampling & Estimation

Learning objectives: Distinguish populations, samples, parameters, and statistics; compare probability and non-probability sampling methods and identify common sources of sampling bias; explain how sampling variability, sampling distributions, and the central limit theorem support statistical inference; and construct and interpret confidence intervals as estimates of population parameters.

Before class

# Module 6

Surveys

Learning objectives: Compare survey methods for collecting primary data in public policy and administration; explain how question wording, response options, and question order can influence survey responses; and design clear, unbiased survey questions that address a research question.

Before class

# Module 7

Means Comparisons

Learning objectives: State hypotheses for differences in means; distinguish independent-samples and paired-samples t-tests; interpret mean differences, confidence intervals, and p-values; and distinguish statistical significance from practical importance.

Before class

In class

# Module 8

Survey Analysis Presentation & ANOVA

Learning objectives: Present survey findings using clear tables and charts; explain sampling and measurement limitations; state the null and alternative hypotheses for a one-way ANOVA; interpret its p-value to determine whether there is evidence that at least one population mean differs; and explain why follow-up pairwise comparisons require adjustment for multiple testing to identify which groups differ.

After class

# Module 9

Regression

Learning objectives: Specify simple and multiple linear regression models for a continuous outcome; interpret slopes, intercepts, and categorical predictors relative to a reference group; explain what holding other predictors constant means; interpret confidence intervals, p-values, and R-squared; assess linearity, residual patterns, and influential observations; and communicate policy implications without treating association as proof of causation.

Before class

Reading preparation: Choose a public policy outcome and two plausible predictors. State the expected direction of each relationship, identify a possible confounder, and explain why a regression coefficient alone would not establish a causal effect.

# Module 10

Policy Brief Presentation

Learning objectives:

Before class