Abstract
The paper at hand provides a brief review of the tests and scales applied to data measurement in social science. One touches upon the most widely-used approaches, as well as, the basic principles of reliability and validity measurement. A particular focus is put on the health science and the scales that are typically employed in this field.
Introduction
The analysis of any phenomenon in social science requires the measurement of particular concepts that are frequently too complex to be measured with the help of single indicators. Thus, one has to apply indexes and scales that allow combining the assessments made on the basis of different criteria.
The solution of numerous health science problems requires a careful selection of appropriate tests and scales that are not only valid but also applicable to the relevant population.
Test Scales in Social Science
Linkert Scaling
One of the most effective scaling methods aimed at measuring people’s attitude is Linkert Scaling. According to Frankfort-Nachmias and Nachmias, the relevant scale is constructed in several steps. One begins with compiling a list of the targeted items. The items are, then, administered to the respondents. As soon as the total score for each respondent is computed, it is necessary to determine the contribution of all the items, select the scale items and test the reliability (Frankfort-Nachmias, & Nachmias, 2008). The following method is widely applied in social science due to its simplicity and validity.
Guttman Scaling
The following method is also called a cumulative scaling or scalogram analysis. As a rule, it is performed in three stages: focus definition, items’ development, and items’ rating. The relevant method is normally applied to empirical tests.
CRT and SRT
In spite of a common assumption that criterion-referenced tests (CRT) are used for education purposes only, in fact, the relevant testing method has a beneficial application potential. The following tests can be implemented in any field in order to measure a professional competence level.
Whereas, CRT is aimed at measuring one’s knowledge in a particular area, its subtype, standards-referenced test (SRT) helps to estimate whether one’s competence fits the requirement of a certain standard (Criterion- and Standards-Referenced Tests, 2007).
Reliability and Validity Measurement
It is particularly important that an applied test or scale fit the necessary reliability and validity requirements. In order to pass the validity test, the relevant method is to show secure consistent results on a regular basis. The reliability is determined by an extent to which the method succeeds in describing the object of measurement (Weiner, 2007). One might also apply such technologies as SRSS in order to estimate the data’s relevance (Green, & Salkind, 2014).
Tests and Scales in Health Science
The measurement of some health science concepts requires the implement of particular scales that is determined by the special functions the scales are to perform. Thus, one mainly applies tests and scales in order to assess potential health outcomes. In this case, each level of measurement (ordinal, interval or ratio) will imply a proper scale (Roach, 2006).
As well as in any other field, the selection of a scale depends on the general research design and the methodology base (Creswell, 2009).
Composite Scales and Paired Comparison
One of the most frequently applied scales in health science is a composite scale. It is a reliable measurement approach that implies multiple indicators and is commonly used to address any statistical analysis that makes it applicable to other social sciences (Panagiotakos, 2009).
Paired comparison is another valid measurement method employed when dealing with several subjective scales. As well as composite scales, it can be applied to any field or population (Cheung, Chiu, & Kwan, 2004).
Conclusion
The analysis of different tests and scales used in social science shows that the following measuring methods can be successfully applied to the health care field as well. Meanwhile, it is important that the selected measurement approach fits the structure and the general design of one’s research.
Reference List
Cheung, W., Chiu, L.L., & Kwan, Y.K. (2004). Construction of Health Indices Using Paired Comparison. Social Indicators Research, 67(1), 353-373.
Criterion- and Standards-Referenced Tests. (2007). Web.
Creswell, J.W., (2009). Research design: Qualitative, quantitative, and mixed methods approach. Thousand Oaks, California: Sage Publications.
Frankfort-Nachmias, C., & Nachmias, D. (2008). Study Guide for Research Methods in the Social Sciences. New York, New York: Worth Publishers.
Green, S.B., & Salkind, N.J. (2014). Using SPSS for Windows and Macintosh: Analyzing and understanding data. Upper Saddle River, New Jersey: Pearson.
Panagiotakos, D. (2009). Health Measurement Scales: Methodological Issues. Open Cardiovascular Medicine Journal, 3(1), 160-165.
Roach, K.E. (2006). Measurement of Health Outcomes: Reliability, Validity and Responsiveness. Journal of Prosthetics and Orthotics, 18(18), 8-12.
Weiner, J. (2007). Measurement: Reliability and Validity Measures. Web.