Analysing Quantitative Data. Raymond A Kent
were created because, for example, each brand of alcohol drunk last time was listed as either drunk or not drunk and recorded as a separate binary variable. For this text, two datasets were created from the original, one for a selection of 61 properties recorded as variables and another for a selection of those properties recorded as set memberships. Table 1.1, presented earlier in this chapter, lists the variables, the range of values used for each variable and the type of measure. Table 1.2 lists the set memberships, whether they are crisp or fuzzy and whether they are being used as conditions or outcomes.
Table 1.2
The properties of the 920 cases are a mixture of demographic, behavioural and cognitive characteristics which play a range of different roles as descriptors, as potentially causal factors or as outcomes. All 61 properties may be used as descriptors and some, like drink status, may be seen either as an outcome or as a potentially causal factor. Many of the properties are measured directly, for example ‘Read a newspaper in the last seven days’. Some, like total importance of brands, are derived. Social class is measured indirectly from the occupation of the chief income earner (CIE) in the household.
Potentially there are many sources of error in the dataset, particularly from non-response (we do not know how many households refused their consent) and from response error (there is considerable scope for exaggeration or minimization of drinking behaviours). Some errors, for example from poor questionnaire design, can be addressed through recoding or transforming properties in ways that are considered in Chapter 2.
Chapter summary
This chapter has shown that data are a deliberate and thoughtful construction by researchers or other individuals rather than simply ‘collected’ and they result from a process of systematic record-keeping. Records are created in a social, economic and political context and for purposes specific to individuals within organizations. Data may be qualitative or quantitative; the former consist of words, phrases, narrative, text and visual images, while quantitative data arise as numbers that result from the systematic capture of classified, ordered, ranked, counted or calibrated characteristics of a specified set of cases. All quantitative data have a structure that consists of cases, properties and values. Cases are the entities under investigation in a particular piece of research. The number used in any particular analysis will be known and will relate either to the population of cases or to some subset of them. In some research projects, there may be more than one set of cases, sometimes arranged hierarchically as sets within sets, or sets at different points of time. Properties are the characteristics of cases that the researcher has chosen to observe or measure and then record. They may be demographic, behavioural or cognitive and they may play one or more roles in a research project as descriptors, causes or effects. Values are what researchers actually record as a result of the process of assessing properties. Such records may relate either to variables or to set memberships. The values of variables assess cases relative to one another; sets define memberships or degrees of membership in absolute terms according to generally agreed external standards or based on a combination of theoretical knowledge and practical experience of cases.
The values of variables may be recorded into different types of measure which have in this text been classified into binary, nominal, ordered category, ranked, discrete metric and continuous metric. Properties that relate to set memberships may be crisp or fuzzy. The distinction between types of measure is not always clear-cut and may be open to interpretation. The creation of measures, furthermore, is subject to many kinds of error in data construction. Errors can often be reduced by devoting extra resources to their minimization, but usually at extra cost in time and money.
Exercises and questions for discussion
1 Are all data ‘manufactured’ in some way or are there some data that we can accept as ‘given’?
2 If a social researcher wanted to measure the extent to which individuals are ‘religious’, suggest how this could be achieved in a way that is (a) direct, (b) indirect, (c) derived or (d) multidimensional.
3 Make a list of variables that (a) are naturally binary, (b) can sensibly be made binary and (c) would be unwise to convert into binary.
4 What type of measure would you use for each of the following?Degree of satisfaction or dissatisfaction with the services offered by the local social services department.Attitudes towards the BBC’s Radio 2.The degree of local support for the creation of a ‘free’ school in an area of urban deprivation.
5 Examine Table 1.1 and consider which variables are demographic, which ones are behavioural and which ones are cognitive. Also consider which ones have been measured directly, which ones indirectly and which ones are derived.
6 Explain the type of measure indicated in Table 1.1 for each of the variables in the alcohol marketing study.
Further reading
DeVellis, R.F. (2011) Scale Development: Theory and Applications, 3rd edn. London: Sage.
A classic text on scale development, presenting complex concepts in a way that helps students to understand the logic underlying the creation, use and evaluation of measurement instruments and to develop a more intuitive feel for how scales work.
Diamantopoulos, A. and Schlegelmilch, B. (1997) Taking the Fear Out of Data Analysis. London: Dryden Press. Republished by Cengage Learning, 2000.
This book does what it says on the tin, all written in a jokey style. Part I considers what are data, the process of sampling and measurement. Succinct and well worth a read.
Gordon, R., Harris, F., Mackintosh, A.M. and Moodie, C. (2010a) ‘Assessing the cumulative impact of alcohol marketing on young people’s drinking: cross-section data findings’, Addiction Research and Theory, Early Online, 1–10, Informa UK.
This article presents the initial results of the survey on alcohol marketing which is used throughout this text.
Kent, R. (2007) Marketing Research: Approaches, Methods and Applications in Europe. London: Thomson Learning (now Cengage, Andover).
This is an earlier text by the author, but it focuses on marketing research. Chapter 5 covers much of the material in this chapter.
Ragin, C. and Becker, H. (eds) (1992) What Is a Case? Exploring the Foundations of Social Inquiry. Cambridge: Cambridge University Press.
This is a seminal book on the role of cases in social research. In particular, have a look at the introductory chapter by Ragin, which reviews the many different ways in which the concept of ‘case’ has been used, and Chapter 10, also by Ragin, on the process of ‘casing’ in social inquiry. Also have a look at the chapter by Abbott, ‘What do cases do? Some notes on activity in sociological analysis’.
Suggested answers to the exercises and questions for discussion can be found at the end of this text, pp. 293–321, and on the companion website, (https://study.sagepub.com/kent), which also give links to relevant free online Sage journal articles, PowerPoint slides, an overview of data analysis packages, an introduction to SPSS and weblinks to alternative datasets.
2 Data Preparation
Learning objectives
In this chapter you will learn:
how datasets are prepared, ready for the next stages of data analysis;
that all data need to be checked, edited, coded and assembled before any further processes can