According to Trochim, scaling is “the branch of measurement that involves the construction of a measure based on associating qualitative judgments about a construct with quantitative metric units” (p. 129). When performing social research, they are incredibly important factors to consider, as they contribute some of the most important data in a qualitative study, forming abstract concepts into measurable figures that can be compared and studied. In this essay, the value of scales in research will be examined.
When applying a scale to objects, there are several issues to consider. For one thing, there must be a reasonable way to measure distance and degree of these abstract objects to a number of figure. Scales are different from response scales in that ordinary scales are applied to objects after they have been collected; response scales are measured while the responses are being collected. Also, scales are not the single instrument to use in a study; they are but one part of the component used to measure results in the sample (e.g. degrees of agreement on a statement in a survey) (Toachim, p. 130).
Scaling is important due to the fact that a hypothesis often needs to be tested by some sort of statistical analysis. Indexes need to be built in order to reasonably compare the results in order to form conclusions based on said results. Constructs are very helpful when represented as one score, which is where scaling comes in; it quantifies the belief of the person you survey, so that there can be no question as to how to interpret the meaning of that statement (Toachim, p. 131).
There are typically two general categories of scales – unidimensional and multidimensional. Unidimensional scales have one dimension, and are very straightforward assignment of objects to numbers. These models are a lot simpler and easier to apply in a straightforward study. Multidimensional concepts, on the other hand, involve more than just one factor and its varying degrees (e.g. levels of academic achievement, of which there can be more than one). These concepts are very useful for creating scales in which more than one factor would more accurately describe the results given by the sample, like degrees of academic achievement. While a person can be good at reading, they can be terrible at math – these two dimensions make up a multidimensional scale (Toachim, p. 132).
In conclusion, a scale makes the unquantifiable quantifiable. While qualitative research can leave a lot of room for interpretation and assumption about the overall value or meaning of an object or statement, placing that within a scale will permit the data to be interpreted in an ordered, organized way that permits it to have the sufficient level of weight required for a qualitative study. Selecting items for a scale is often a difficult process, as the right scale and values must be assessed to provide adequate measure of the data to fit the problem statement. At the same time, scales still are used for the primary purpose of assessing attitudes and beliefs of the people surveyed or sampled (Toachim, p. 140).
References
Cozby, P. C. (2008). Methods in behavioral research. Mountian View: Mayfield Pub. Co.
Creswell, J. W. (2009). Research design: qualitative, quantitative, and mixed methods approaches (3rd ed.). Thousand Oaks: SAGE Publications.
Trochim, W. M. (2001). Research methods knowledge base (2nd ed.). Cincinatti: Atomic Dog Pub.