Exploratory Data Analysis

Target group and prerequisites: 

• PhD students working (or planning to work) with quantitative data sets. Participants should be familiar with basic concepts in descriptive statistics as, for example, taught in introductory statistics courses

Description of the seminar:

The aim of the seminar is to provide the participants with guidance and examples for an exploratory data analysis that represents an important first step before conducting any empirical research analysis. To correctly understand and interpret empirical results, it is of the essence to have a very good understanding of the quality and the characteristics of the employed data set. During the seminar, methods from descriptive statistics and multivariate data analysis will be presented in a hands-on way to inspire participants to inspect, clean and understand their data.

Content:

1. Measurement scales
2. Missing data (briefly; a separate specific workshop will be offered 2 weeks later)
3. Measures of central tendency
4. Outlier detection and treatment
5. Dispersion parameters, skewness, and kurtosis
6. Graphical inspection of data (uni- and multivariate)
7. Measures of concentration
8. Measures of bivariate association

Learning objectives: 

After attending the seminar, you will be able to:

• use a toolbox of methods to properly examine and portray your data
• select the appropriate graphical method to examine the characteristics of your data or relationships of interest
• identify univariate, bivariate, and multivariate outliers
• test your data for the assumptions underlying the most common estimation techniques
• determine the best method of data transformation given a specific problem

Assignment:

.