Applied data analysis for psychology using the open-source software R [Data Analysis using R]

Dozent/in:

Alexander Pastukhov

Angaben:

Seminar, 2 SWS, ECTS: 3

Termine:

Mo, 12:00 - 14:00, M3N/-1.19

Voraussetzungen / Organisatorisches:

No programming background necessary, basic knowledge on statistical analysis is advantages but not strictly necessary. For Ba / Ma Psychology only!

Inhalt:

An introductory hands-on course that shows how to use R to analyze a typical psychophysical and social psychology research data. The course will walk you through all the analysis stages from importing a raw data to compiling a nice looking final report that automatically incorporates all the figures and statistics. If description below looks intimidating, do not despair! R wraps all these steps into simple easy-to-understand procedures.

Learning Goals: This introductory course into R, will teach you everything you need to know; how to import the data, preprocess it, summarize it, plot it, analyze it and create a visually appealing final report. At the end, you will able to preprocess, analyze, and plot data for you Bachelor/Master/PhD thesis.

Course Method: This seminar assumes no prior knowledge on your part. We will start with basic concepts of variables and functions and proceed to advanced topics. The course will introduce different ways to perform typical data analysis tasks. You can bring your own data but you do not have to.

Grading: In the course, you will complete numerous practical exercises. Completing 80% of them is required to pass the course.

Empfohlene Literatur:

Course syllables are available online: https://alexander-pastukhov.github.io/data-analysis-using-r-for-psychology/
"R for Data Science" by Garrett Grolemund and Hadley Wickham available freely at http://r4ds.had.co.nz/

Schlagwörter:

statistical analysis, data science, statistics

Bayesian Statistics [Statistical Rethinking]

Dozent/in:

Alexander Pastukhov

Angaben:

Seminar, 2 SWS, ECTS: 3

Termine:

Mo, 10:00 - 12:00, M3/-1.13

Voraussetzungen / Organisatorisches:

Some Bachelor level knowledge R is beneficial, but no prior knowledge beyond high school algebra is required. For Ba / Ma Psychology only!

Inhalt:

In this seminar, you build your understanding of (Bayesian) statistics from ground up (we start with a concept of probability as counting). It focuses on a linear model design that underpins all classic statistical test: t-test, ANOVA, rm ANOVA, ANCOVA, MANOVA, Pearson correlation, etc. You will learn about their simple common structure, understand how to design such models by hand (much simpler than you think), and, most importantly how to interpret and evaluate these models (much harder than you think) using causal calculus tools and information criteria.

Learning Goals: In this seminar, you will learn how to build a statistical model from the ground up with the goal of being able to build a customized model for any statistical problem and analysis. After this course you will understand that a linear regression, a T-test, an ANOVA, or an ANOCOVA all refer to the same simple linear model that you can build yourself. The aim is to make sure that you will know exactly what your analysis does and why you are doing it in this way.

Course Method: This seminar assumes no prior knowledge on your part. We will start with a basic concept of probability-as-counting and proceed to understanding what statistical models are and how to build them. Over the course of the seminar, we will gradually move forward to more advanced topics learning how to handle various types of data, identify spurious associations, infer causality, evaluate models, or perform power analysis. Forming a book club we will read Statistical Rethinking by Richard McElrath. It is an excellent introductory statistics book that explain even most intimidating topics very clearly, links all seemingly discrepant topics together, and has plenty of examples in R. We will read one chapter every week, practice build models, and discuss the topics and questions during the seminar.

Empfohlene Literatur:

"Statistical Rethinking: A Bayesian Course with Examples in R and Stan" by Richard McElreath https://www.oreilly.com/library/view/statistical-rethinking/9781482253481/

Schlagwörter:

statistics, bayesian statistics

Introduction to Deep Learning for Psychology [Deep Learning]

Dozent/in:

Alexander Pastukhov

Angaben:

Seminar, 2 SWS, ECTS: 3

Termine:

Mi, 12:00 - 14:00, M3N/-1.19

Voraussetzungen / Organisatorisches:

Basic knowledge of Python or R is required. No knowledge of statistics required. Basic school-level algebra knowledge is required.

Inhalt:

Deep learning is a cutting edge approach to data analysis. The aim of the course aim is to gently introduce key concepts of deep learning, showing the simple tricks that make deep learning so powerful, while highlighting its optimal use and its limitations. We start by creatinga single input-single weight-single output linear neural network and learn how to make it learn to predict the output (a processes of gradual iterative adjustment that is called a "stochastic gradient descent"). We then progress in small steps to multi-input and multi-output networks, to non-linear networks, to multi-layer networks, to advanced (convolutional, recurrent, etc.) networks. Our progress will be slow but steady and you will learn that deep neural networks are both simpler and, yet, more powerful and useful for you than you think.

Empfohlene Literatur:

"Grokking deep learning" by Andrew W. Trask https://learning.oreilly.com/library/view/-/9781617293702/?ar

Python for social and experimental psychology

Dozent/in:

Alexander Pastukhov

Angaben:

Seminar, ECTS: 3

Termine:

Mo, 8:00 - 10:00, M3N/-1.19

Voraussetzungen / Organisatorisches:

No prior programming skills required. For Ba / Ma Psychology only!

Inhalt:

An introductory hands-on course that teaches how to use Python to create experimental programs. No prior knowledge is required, as we will start with introduction to programming in Python by writing games (because psychological experiments are merely boring games). We will progress from basic text based interaction to using graphics and sound using PsychoPy library.

Learning Goal: This course is especially tailored to your needs as a student in the humanities. The aim of the course is to develop good programming habits and skills to write a clear and concise code. You will learn all necessary material starting from basic variables and functions, proceeding to conditional statements, list, and dictionaries, and further to more advanced topics of using classes and object-oriented programming. By the end of the seminar, you will be able to program a custom experiment with all necessary components including settings files, custom stimuli, data logging, dynamic feedback, etc.

Course Method: Together we will program games (because as I told you, psychological experiments are merely boring games), including familiar favorites such as "Snake", "Memory", "Space invaders", or "Guitar Hero" using field-standard PsychoPy library.

Grading: In the course, you will complete numerous practical exercises. Completing 80% of them is required to pass the course.

Empfohlene Literatur:

The course material is available online at https://alexander-pastukhov.github.io/python-for-experimental-psychology/