The course is designed for staff who have no knowledge of statistics but who wish to apply quantitative methods in their own research. The course will be organized into more conceptual lectures in the mornings, and more practical lab sessions in the afternoons, although there will be some overlap between the two.  

Theoretical lectures introduce the basic language for quantitative methods and experimental design, and cover the overarching framework for frequentist methods for exploring and analyzing data. The practical sessions apply this knowledge to statistical computing, where the focus will be on simple data visualization, assumption checking, hypothesis testing, and reporting. For the practical sessions, you will need your own computer, so please bring your laptop along.

Intended learning Outcomes

At the end of the course, students will be able to:

• Identify how to re-formulate humanistic questions into a format that can be answered using quantitative methods
• Understand the need for assumptions in statistical analyses, and apply that understanding when designing and discussing research
• Use statistical software and write own analysis programs (in R)
• Communicate results
• Evaluate others quantitative research

Discovering Statistics Using R

There is currently no textbook which has the perfect balance between accessibility, readability, and usefulness for coding in the R language. However, a recommended text for the course is Andy Field’s Discovering Statistics Using R. This book is chosen because it is high on accessibility and is fairly detailed in it’s coverage of statistics, at least for the purposes for the course. It will be a reference that you will keep returning to through self-study. The book supports the lectures. The statistical sections are better than the R sections, but you will learn how to find your own coding resources through the course.   

What is R

In this course, we’ll be using the statistical programming environment R to explore, visualize, and analyze example datasets. R is a programming language. Programming can have a steep learning curve. However, we will not assume any knowledge of R specifically, or programming generally. The lab material is designed to ease the learning curve a little. However, prior to the course, you must have your computer ready, so that we will not waste time on installing software.

First you need to have R (http://www.r-project.org/) installed and running on your computer.

Second, you need to install Rstudio (http://www.rstudio.com/).

We will try to keep the learning curve as shallow as possible, but it would be best if you’ve tried out a few things in R before the first day, just so it all doesn’t feel entirely new. The best way to do this is to just go through Chapter 3 in Field. It can also help you in installing and setting up R, and in getting you used to writing your own code.   

Readings

The course covers a lot of ground, and so we will cover a lot of what’s in the book. But the focus on practice should make it easier to understand and remember the theory. (Almost) each chapter in Field is divided into a theory section and an R section. In the morning lectures, we will be covering the theoretical parts, and in the afternoon labs we will work through the R part by completing some exercises that I have designed. A good reading strategy would be to read the theoretical sections prior to the course, have a quick browse of the R sections, and then use the R sections of the book as support during the labs. 

Course Structure

The course structure and the readings for each day are as follows:

Monday January 14th – Approaching quantitative research (and R)

-       Chapters 1, 3, & 4

Tuesday January 15th – Basic concepts for statistics

-       Chapters 2 & 5

Wednesday January 16th  – Correlation and regression: Toward the general linear model

-       Chapters 6,7, & 9

Registration is mandatory and is done by sending an email to emi@cc.au.dk