Statistics: Power from Data!
4 Data exploration

At many steps of the process of producing statistical information, it can be useful to explore the data. It can be when evaluating if a source of data meets your needs, when you receive the raw data and want to decide what data processing steps will be needed to be able to use it or before proceeding with more advanced statistical analyses. No matter what the source of the data is, it is important to understand the data and identify limitations. For this purpose, you can ask yourself the following questions:

• What metadata is available for this data set? Are the descriptions of variables provided?
• What are the observed population, the observation unit and the reference period?
• Is it microdata or aggregate data?
• What are the types of the variables in the file?
• What are the frequency distributions of these variables? What are the measures of central tendency and dispersion?

This section starts with the presentation of some software applications that are useful for data exploration. Then the different types of variables are presented, followed by the descriptive statistics used to explore data, such as frequency tables and measures of central tendency and dispersion.