Introduction
- What is it like to be a woman in a male-dominated company?
- Why do social revolutions occur?
- Why do some people vote Conservative?
The aim of the social sciences is to describe and explain problems like these. One of the key tasks within empirical research is to collect information that might be used to shed light upon the research question. Such information, or the raw data, can be collected by means of many different research designs. For example, if the aim of the research is to describe what it is like to be a Turk in Germany, one might follow the example of Günter Wallraff, who dressed up and lived like the Turk Ali Levent for two years. In this way he observed, and experienced for himself, what it was like to be a Turk in Germany. Another strategy might be to interview some people in this group, or to distribute a questionnaire to a sample of Turks living in Germany.
In quantitative research, for example survey research, the researcher collects comparable information about many objects of a certain kind. The information is placed in a matrix and expressed as numbers, for example 0=male, 1=female1. Finally, statistical techniques are used to analyse patterns in the data.
A data matrix could be described as a table where each row represents one unit, and each column represents one characteristic of the units. An extract from a matrix with survey data could look like this:
| Respondent number | Gender* | Year of Birth | Etc |
|---|---|---|---|
| 1 | 1 | 1973 | |
| 2 | 0 | 1980 | |
| 3 | 1 | 1979 | |
| etc |
*) 0=male, 1=female
The units, or cases, in this matrix are individuals2. Each respondent is uniquely identified by the numerical code in the first column. In the next two columns, Gender and Year of Birth, there is information about the individual cases. This information is not the same for each respondent; some of them are men and others are women. This is why the term "variable" is used to describe them. Each cell in the matrix provides information about one particular unit. Respondent number 1 is a woman born in 1973. "Woman" is a value on the variable Gender, and "1973" is a value on the variable Year of Birth.
In the following sections we will very briefly illustrate how a data matrix can be explored and analysed online using Nesstar WebView. We will use the following variables from the ESS survey:
- Gender (0 = male, 1 = female)
- Personal use of internet/e-mail (0 = No access, 1 = Never use, 2 = Less than once a month, 3 = Once a month, 4 = Several times a week, 5 = Every day)
- Extent of interest in politics (1 = Very interested, 2 = Quite interested, 3 = Hardly interested, 4 = Not at all interested)
- Age in number of years 2002 (20, 21 etc.)
Footnotes
- [1] When the values on the variables are represented by numbers instead of text, it is easier to analyse the material using statistical techniques. We need numbers to do calculations. You must be aware that there are several types of variables. Please see the following text on the level of measurement.
- [2] Of course, it is possible to collect and structure information about types of units other than individuals, for example countries, municipalities, companies, sheep, politicians, etc. The unit shows what, or who, your data contains information about. A variable provides information about the units, and the units have different values on the variables.