Posted: January 31st, 2023

What is measurement? Two points need to be reinforced in this context

Measurement:
After reading this chapter, students should understand…
1. The distinction between measuring objects, properties, and indicants of properties.
2. The similarities and differences between the four scale types used in measurement and when each is used.
3. The four major sources of measurement error.
4. The criteria for evaluating good measurement.
What is measurement? Two points need to be reinforced in this context. One is that we do not measure objects, or even properties of objects; rather, we measure indicants of properties of objects. Thus, we measure the profitability of a company (property of an object) by an indicator in the form of the net profit figure for the year, as stated in the company’s annual report. In truth, a look at the company’s accounting records and federal income tax return will probably give two other figures on net profits, and all three are ethically and legally acceptable, although numerically different. The second point which needs emphasis is that measuring involves the process of mapping these indicators from one conceptual domain to another so that we can compare, compile, or statistically manipulate the data to meet our needs. For example, we measure a company’s success in terms of net profits defined in some operational terms (a mapping process). We may then develop an index of investment attractiveness (e.g., ROI) by which we classify various companies into attractive or unattractive investment groups (another mapping). Question 1 is a useful discussion vehicle for this topic.

Reliability and its relation to validity should be made clear. Another way to describe these concepts is in terms of the types of variance they address. A measure could have great bias (systematic variance) and still be reliable if it is consistent in its scoring. High reliability indicates only limited error variance is present, but says nothing about systematic variance. A valid measure is also reliable, but in addition a valid measure has little or no systematic variance as well as not having error variance.
After reading this chapter, students should understand…
1. The nature of attitudes and their relationship to behavior.
2. The critical decisions involved in selecting an appropriate measurement scale.
3. The characteristics and use of rating, ranking, sorting, and other preference scales.
This chapter covers procedures that will help to understand measurement scales, so that you might select or design measures that are appropriate for your research. We concentrate on the problems of measuring more complex constructs, such as attitudes. Conceptually, the process is started by revisiting the research process to understand where the act of scaling fits in the process.
Scales in business research are generally constructed to measure behavior, knowledge, and attitudes. Attitude scales are among the most difficult to construct, so we will use attitudes to develop your understanding of scaling.
For additional material on the various unidimensional scaling methods both the Edwards and Kerlinger books are excellent. The Miller book has a large collection of existing scales that have been developed for social and business research. Usually the background of the scale is given along with information on validity and reliability. The Sage Publications quantitative analysis series contains several fine monographs on various multidimensional techniques.
Questionnaires and Instruments
After reading this chapter, students should understand…< /span>
1. The link forged between the management dilemma and the communication instrument by the management-research question hierarchy.
2. The influence of the communication method on instrument design.
3. The three general classes of information and what each contributes to the instrument.
4. The influence of question content, question wording, response strategy, and preliminary analysis planning on question construction.
5. Each of the numerous question design issues influencing instrument quality, reliability, and validity.
6. Sources for measurement questions.
7. The importance of pretesting questions and instruments.
New researchers often want to draft questions immediately. Their enthusiasm makes them reluctant to go through the preliminaries that make for successful surveys.
Exhibit 13-1 is a suggested flowchart for instrument design. The procedures followed in developing an instrument vary from study to study, but the flowchart suggests three phases. Each phase is discussed in this chapter, starting with a review of the research question hierarchy.
Note: For further reading, the Converse/Presser or Payne book is suggested. Payne is easy to read and a classic. The Dillman book is another that is well worth study. Appendix B of the Selltiz, et al. text has an excellent set of rules on the construction of questions. The Public Opinion Quarterly is suggested for the current literature on questionnaire and survey problems.