Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Install this application on your home screen for quick and easy access when you’re on the go.
Just tap then “Add to Home Screen”
Member rate £492.50
Non-Member rate £985.00
Save £45 Loyalty discount applied automatically*
Save 5% on each additional course booked
*If you attended our Methods School in Summer/Winter 2024.
Monday 30 July - Friday 3 August
09:00-10:30 / 11:00-12:30
Please note this is the outline for the 2017 course to give you a guide. The outline will be updated for the 2018 course shortly.
Today, you open a top political science (or any social science) journal and half (if not more) of the articles are littered with tables, numbers, statistical findings. The purpose of this class is to demystify these and make you an informed consumer of quantitative research. In this class you will learn the basics of statistical inference and the most commonly used statistical techniques found in political science research designed to differentiate between groups or to see if there is a difference between two variables. The course is designed to give you an in depth understanding of how these statistical techniques work but minimizing the mathematical burden on the student. While some basic math will be necessary, but if you can add, subtract multiply and divide numbers, you will be fine in this course. The course provides the foundation for multiple regression and is a must for anyone wanting to take that course as long as you are not familiar or comfortable with the topics listed in this outline.
Levente Littvay researches survey and quantitative methodology, twin and family studies and the psychology of radicalism and populism.
He is an award-winning teacher of graduate courses in applied statistics with a topical emphasis in electoral politics, voting behaviour, political psychology and American politics.
He is one of the Academic Convenors of ECPR’s Methods School, and is Associate Editor of Twin Research and Human Genetics and head of the survey team at Team Populism.
This course was designed for people who do not have much prior experience with statsitics or they are not totally comfortable with basic statistical concepts like hypothesis testing, p-values, standard errors, distributions, correlation and etc. It is designed to provide a solid foundation for people who are starting for practically 0 and would like to work up to running multiple regression (which is the most commonly used statistical technique in the social sciences). This one week course offered in the first week will cover the basics people need to take regression in the second week.
Day 1: First we discuss basic distributions with a strong emphasis on the normal distribution (otherwise known as the bell curve) but considering others as well. We cover the types of variables and how central tendency (mean, median, mode) and variability (range, variance and standard deviation) can be measured as these are the essential foundational building blocks of statistical inference.
Day 2: We continue by understanding how standardized scores (such as IQ, SAT, GRE and, most importantly, z-scores) can get us one step closer to comparable statistical estimates used for inference. Then we turn back to the normal distribution to see how the concepts of probability, distributions and standardized scores come together highlighting the power of both the normal distribution and what it can tell us.
Day 3: We explore why it is not even crucial to have normally distributed variables when doing statistical inference. With our newly gained knowledge we learn to leverage statistical properties of group means and learn how to formulate (and even test) simple hypotheses using statistical inference.
Day 4: We leverage the discoveries of an old brewery employee who also revolutionized the world of statistics by allowing us to move from simple hypothesis testing of situations with too many assumptions (z test) to be realistic to testing hypotheses commonly found in the social sciences (t test and ANOVA). We explore both group comparisons, changes over time and comparisons to some gold standard value.
Day 5: We move to testing relationships between variables using correlations and we introduce bivariate regression which provides the foundation of multiple regression analysis. If time allows we explore another class of statistics which make less assumptions about distributions and learn how to answer different types of research questions with this different type of analytical technique (the Chi-Square test).
NONE – REALLY! If you remember how to add, subtract, divide and multiply using both negative and positive numbers, you are ready to take this course. There may be an occasional square and square root that, in this class, we are happy to calculate with a calculator.
Day | Topic | Details |
---|---|---|
Monday | Scales, Distributions, Measures of Central Tendency, Variability |
Ch 1-4 |
Tuesday | Standardization and Probability Theory |
Ch 5-6 |
Wednesday | Central Limit Theorem and Hypothesis Testing |
Ch 7-8 |
Thursday | Multiple Forms of the t-test, Multiple Group Comparisons and Estimation |
Ch 9-12 (13-14 optional) |
Friday | Correlation, Bivariate Regression, Intro to Nonparametric Statistics |
Ch 15-16 |
Day | Readings |
---|---|
Monday |
Ch 1-4 |
Tuesday |
Ch 5-6 |
Wednesday |
Ch 7-8 |
Thursday |
Ch 9-12 (13-14 optional) |
Friday |
Ch 15-16 |
Frederick J Gravetter and Larry B. Wallnau. Essentials of Statistics for the Behavioral Sciences. Current edition is 8th but that is missing the Estimation Chapter (12 – and subsequent numbering is adjusted accordingly). Look for an earlier edition. Does not really matter which. Also note that these authors also wrote the “Statistics for The Behavioral Sciences” without “Essentials”. That is also a great book but its chapters are longer, more in depth and there are more chapters covering additional topics. For this class, it is not a must, but if you prefer, feel free to use that as well. Just cross-reference the broad chapter topics. |
Depending on time, I may show off some of the statistics learned in statistical software. I will use free and open source software so feel free to bring your laptop and follow along on that.
PSPP and/or R
All three works on Mac, Linux and Windows requiring very little resources for basic stats. If your computer can run it, it is good enough for us.
There is a long list of introductory statistics books out there. I selected the textbook that I found to be the most accessible to graduate students with a slight aversion to math and quantitative research. Here are a two more I know to be widely acclaimed.
David Freedman, Robert Pisani and Roger Purves. Statistics, Current edition is 4th 2007 but any edition would be a good book to reference. W. W. Norton & Company
Michael Lewis-Beck (1995) Data Analysis. An Introduction. SAGE
None. This is the first course to take.
Introduction to Regression