A scale combines a teacher’s responses to a number of survey items into one score.Why create scales?
Some questions in a survey are designed to get at a bigger idea or phenomenon than any particular question can tap – like “teacher learning community.” If we asked just one question, we wouldn’t capture varied meanings of the idea nor would we be sure that it had been the right question to ask of a particular teacher. Therefore, we ask a number of questions related to the idea in order to get a more valid and a more reliable measure of the phenomenon.How is a scale created?
We start out by developing a number of questions that we think are getting at the same thing. But they may not be. We can examine this question by looking at teachers’ responses to the question – do they cohere? If they don’t all hang together, then we need to find the smaller set of questions that seem to be tapping the same thing.
Technically, this is done through factor analysis techniques, which use statistical standards to determine how many “factors” or separate scales are suggested by all individuals’ responses to a number of survey items and to assign “weights” to each item on each factor (+ or -). The results let us identify particular items that hang together as a factor.
The scale is defined by a set of two or more survey items that cohere in terms of teachers’ responses. The scale label captures the common meaning among the items; the Alpha coefficient indicates their internal consistency.What is a scale score?
A simple way to create a scale score is to add an individual’s responses to all items in the scale and compute the mean score. A school’s score on a teacher survey scale is the average of teachers’ scale scores.