What is the justification for using a sum score instead of an average, specifically when assessing constructs such as workplace incivility or OCBs which consists of various discrete behaviours?
As there is practically no difference in statistical testings, the choice between average and sum score depends on the constructs measured. These choice can also have an influence on the comprehesibility of the interpretation of the results.
E.g. Are you happy? with a scaleing of 0 to 10 is more logic in average values.
The amonut of perceived stress may be better understandable with a sum score.
A list of behaviors (no, yes) is more logic with a sum score.
A practical justification for using average instead of sum scores: if you use sum scores you need to be sure that when comparing the sums all the individuals responded to the same number of questions/items. If you have ten items, a person who answers them all will have probably a higher chance to get a higher score compared to a person who left one or more items blank. With average - other factors being equal - you do not have this problem.
This problem can be resolved calculating the average and multiplicate it with the total number of items.
Yes, but that only an unnecessary extra step that can be easily avoid it. That is why I talked about a practical justification.
Sum is a preferred measure when we just need total value or total items . Better we can say if we need to know the total amount available then we can sum up. Average is more like a statistical measure that is used to summarize the data or when we try to compare among groups where each group has different member counts.
- Badges
- Science topic
- Similar topics
- Medicine
- Physiology
- Biosignals
- Biomedical Signal Processing
- Statistical Analysis