Analysing Quantitative Data. Raymond A Kent
data, respondents were asked how important they thought it was to choose a popular well-known brand when deciding to buy each of several different products. The SPSS results are shown in Figure 2.9. If the codes allocated (5 for Very important and so on) can reasonably be treated as calibrations of the degrees of importance, then the nine items can be treated as a summated rating scale and totals calculated for each of the respondents who gave a rating. The maximum total score is 45 (the person thinks choosing popular known brands is Very important for all items). The minimum depends on what the researcher decides to do with the ‘Don’t know’ answers. If given a value of 0 (as in Figure 2.10) this will mean a minimum score of 0 if somebody responds ‘Don’t know’ to each item. Indeed, an individual respondent will achieve a lower total score if any responses are ‘Don’t know’. Alternatively, these answers could be treated as a missing value and ignored in the calculation.
Figure 2.9 The importance of choosing well-known brands
Figure 2.10 Total scores in brand importance
Figure 2.10 shows the frequency of each total score calculated by SPSS. How to do this in SPSS is explained in Box 2.4. Thus two respondents had a score of 0, so they indicated ‘Don’t know’ for each item. One person scored the maximum of 45, but the majority had scores somewhere in the middle. There are various ways in which a distribution like this can be summarized, including creating class intervals as in the previous section, but other ways will be explored in Chapter 4.
Box 2.4 Computing totals in SPSS
To get SPSS to compute the totals that were used to create Figure 2.10 select Transform then Compute Variable. You will obtain the Compute Variable dialog box (Figure 2.11). Notice that there are lots of functions that we could perform on the variables – but all we want to do is add the nine variables together, so highlight Chocolate or sweets and put this into the Numeric Expression box by clicking on the arrow. Now click on the + button and bring over the next variable, then on + again, and so on until you have the nine variables added together. Enter a variable name, something like Totbrand, in the Target Variable box and click on OK. A new variable will appear in your data matrix, giving the total scores for each case. You can now use Recode to group the responses into, say, high-, medium- and low-score categories.
Multiple response questions
There are often questions in a survey that allow respondents to pick more than one answer. The very first question on the alcohol survey, for example, asks respondents whether they have watched television, read a newspaper, read a magazine, listened to the radio or used the Internet in the last seven days. Respondents can reply ‘Yes’ to as many of these that apply. For the purpose of analysis, each medium will need to be treated as a separate variable, each one of which is either selected or not selected (so, it is binary). The five items then need to be analysed together. The results are shown in Figure 2.12. This indicates that there were 3,418 yeses. The 909 who indicated that they watched television constituted 26.6 per cent of the 3,418 yeses and 98.9 per cent of the 920 cases. Box 2.5 explains how to do this in SPSS.
Figure 2.11 The Compute Variable dialog box
Figure 2.12 SPSS multiple response
Box 2.5 Multiple response items in SPSS
To treat the five items relating to media consumption as a multiple response question, select Analyze|Multiple Response|Define sets. Bring the five variables across to the Variables in Set box. Since the code of 1 was entered for those who said ‘Yes’, enter 1 in the Counted Value box. Make sure the Dichotomies radio button is clicked under Variables Are Coded As. You will also need to give the new variable a name, like Media. Click on the Add button to add the name to the Multiple Response Sets box, then on Close. The new variable, however, does not appear in the data matrix. To access it, click on Analyze|Multiple Response and either Frequencies or Crosstabs depending on whether you want univariate or bivariate analysis. To produce Figure 2.12, select Frequencies. Move Media from the Multiple Response Sets box across to the Table(s) for box and click on OK.
Upgrading or downgrading measures
Researchers sometimes upgrade the complexity of the measures achieved by some of their variables in order to apply the more sophisticated statistical techniques that thereby become available. The most usual transformation is for sets of ordered categories to be upgraded to metric measures. There are two main ways in which this may be accomplished. The researcher may allocate numeric codes to ordinal categories in such a way that they can be treated as if they are metric. An example of this is a summated rating scale such as the one illustrated in Figure 1.2. This process, however, assumes that the ‘distances’ between each value are equal so that, for example, the distance between ‘Very important’ and ‘Quite important’ is the ‘same’ as the distance between ‘Quite important’ and ‘Neither important nor unimportant’. Such an assumption may seem reasonable in this example. It also tends to be reasonable for Likert items (see Chapter 1) where respondents are being asked about their degree of agreement or disagreement with a number of statements. However, for levels of satisfaction, where a set of categories like ‘Very satisfied’, ‘Fairly satisfied’ and ‘Dissatisfied’ have been used, this assumption is suspect since the ‘distance’ between ‘Dissatisfied’ and ‘Fairly satisfied’ is probably much greater than the ‘distance’ between ‘Fairly satisfied’ and ‘Very satisfied’. In any event, it would be unwise to treat average scores in any absolute sense. Thus an average score of, say, 4.0 for males and 2.0 for females does not mean that males are ‘twice’ as satisfied, or that they are two ‘units of satisfaction’ above the females. All we can say is that the average of the males is higher than that of the females. However, for measuring change, for example from one week to the next, then changes in the average scores are likely to reflect real changes in people’s level of interest.
The other way to create metric measures is to define categories of an ordered set in terms of counting numbers of instances as a measure of size. Thus a distinction between ‘Small’, ‘Medium’ and ‘Large’ organizations is only an ordinal distinction. However, if the researcher defined ‘Small’ organizations as having fewer than 50 employees, ‘Medium’ as having between 50 and 200 employees, and ‘Large’ as having over 200 employees then a discrete metric variable has been created, the ‘metric’ in this case being size measured by the number of employees. With a larger number of categories, more precisely defined, with upper and lower limits, it becomes possible to calculate an average size. This procedure is fine provided there is accurate information, for example, in the situation above, on the number of employees in each organization of interest. By creating (or assuming the creation of) metric measures, the researcher can now, for example, add up and then calculate average scores, calculate standard deviations and use the variables in ways that will be explained in Chapters 4–6.
There are some circumstances when a researcher may downgrade a measure and treat it as if it were at a less complex level. Thus a metric variable may be treated as ranked by ignoring the distances between categories. A class test out of 100 may be used to create ranks of first, second, third, and so on. This may be undertaken by the researcher either because he or she feels that the assumptions of the original metric are unwarranted, or because