Measurement Scales That Are Used

¶ … measurement scales that are used in collecting and organizing research data. The scales discussed in this text are: nominal; ordinal' interval' and ratio. The differences between the measurement scales determine how data can be manipulated and studied and which kinds of conclusions can be reached using the data. Nominal scales are the simplest of the measuring devices. These scales only measure the classification of items. Either the data does or does not fit the scheme. An example of this is gender.

When you ask for a respondent's gender on a survey form, this is a nominal question. There are only two answers, and the only arithmetic you can use on the data is to count how many of each kind are in each classification. Ordinal scales include the classification involved in nominal scales, but they can also measure preferential order. In addition to classifying popcorn, for example, as air-popped or oil-popped, the respondent can also rank the different flavors of popcorn in order of best to worst.

The limitation of using ordinal scales is that there is no uniform interval between the rankings. The difference between "highest" and "high" isn't necessarily the same in the respondent's mind between "lowest" and "low." Interval scales take care of the problem with ordinal scales, as they allow for classification, order and an equality of difference between rankings. The difference between 1 and 2 is the same as the difference between 4 and 5, for example. The data is relatively symmetrical and researchers can do operations like plotting a standard deviation and finding the mean.

Intervals can be used to find averages, which is not possible with ordinal rankings. Ratio scales are the most complicated and can be the most useful. They include all the qualities of nominal, ordinal, and interval scales, plus the provision for an absolute zero. Measurements like distance, volume, length, money, population counts, etc. are all measured on a scale that begins at zero. Ratios are most useful with data that can be definitively measured and they are more useful in the hard sciences than behavioral sciences.

Choosing a measurement scale inherently involves looking at white kind of information is needed when the analysis is finished. If your data only needs to be classified into two areas, using a nominal scale is the easiest. There is no reason to get too complicated if all you need to know is if people are part of one organization or another. Question 2 -- 150 words The choice of which measurement tool to use when collecting data depends almost entirely on the intended use of the data.

Several ways of measuring data -- measurement scales -- are available. Nominal scales measure classification only, where something fits into a category. Ordinal scales measure classification as well as ranking order, from either best to worst or lesser to greater value. Interval scales combine all of the above measurements but with the added feature of having the intervals between all of the choices be equal. A ratio measurement scale includes, again, all of the qualities of the previous scales plus a definitive natural origin.

A percentage, for example, is a ratio measurement because the lowest possible percentage is 0% and all of the intervals between percentage points are equal. To choose a measurement scale, first decide what you plan to do with the data and then decide what scale to use. The primary measurement scales in.