Syllabus
While the course provides insight into key elements of research methods, we expect you to havea certain amount of knowledge regarding four issues mentioned below:(i) Essentials of correct citing and quoting (academic ethics)(ii) Essentials of academic writing (style, the logic of test structuration, etc.)(iii) Basics of probability(iv) Descriptive statistics (mean, median, standard deviation, etc.)+ previous exposure to academic text is considered the sine qua non
Broadly speaking, we do expect that you have retained at least the basics of BA-level methodologicalknow-how (as defined by e.g. JPB 283 and 284).
Software: R (+ Excell)
Readings: Primary source is Data Analysis for Social Science, Elena Llaudet and Kosuke Imai, 2022, Princeton University Press
For the qualitative part it is the Gerring Christenson book and one Gerrings paper (link provided).
For the second class on Charts/Tables we will rely on two J.Schwabish papers (link provided) 1) Intro + argumentsa. Organization b. Master thesis and the process of writing - a few tips and tricks c. Types of arguments 2) Few notes on charts and tables (Schwabish 2014, 2020) a. Charts b. Tables https://www.aeaweb.org/articles?id=10.1257/jep.28.1.209 https://www.cambridge.org/core/journals/journal-of-benefit-cost-analysis/article/ten-guidelines-for-better-tables/74C6FD9FEB12038A52A95B9FBCA05A12 3) Intro to R a) Intro to R b) Loading the Data c) Different types of variables/columns d) Computing means and other summary statistics 4) Estimating causal effects with randomized experiments a) logic of Experiments b) Treatment and Outcome variables c) Individual Causal effect d) Average Treatment Effect 5) Inferring Population Characteristics via Survey Research a) Survey research b) Measuring attitudes c) Two-Way frequency and proportion tables d) Variable relations e) Presenting descriptive statistics 6) Predicting Outcomes Using Linear Regression a) Independent vs. dependent variables b) Predicted vs. observed outcomes c) Prediction errors d) Building an LM model e) Understanding the LM model output f) How well does the model fit the data? 7) Estimating Causal Effects With Observational data a) Observational data - a few challenges b) Difference-in-means estimator c) Controlling for confounders - Multiple LM models d) Internal and External validity 8) Probability a) Events and Random variables b) Probability distributions c) Population Parameters vs. Sample statistics 9) Quantifying Uncertainty a) Estimators and their Sampling Distributions b) Confidence intervals c) Hypotheses testing d) Statistical vs. Scientific significance 10) Case study design I. (Gerring Christenson 2017) a. Exploratory vs. diagnostic b. Cross case c. Within case d. Pro and cons 11) Case study design II (Gerring 2007) a. Selecting cases for intensive study from a regression b. Extreme cases b. Deviant cases c. Pathway cases https://journals.sagepub.com/doi/10.1177/1065912907313077
Annotation
The course covers the most important parts of a methodological toolkit for master-level students.
The course focuses on the basics of quant (and to a lesser extent qual) analysis, a strong emphasis is put on gaining the ability to work effectively with R studio.
Given the high ECTS of the course, students should be prepared for a substantial workload.