Each of the reliability estimators has certain advantages and disadvantages. Inter-rater reliability is one of the best ways to estimate reliability when your measure is an observation. However, it requires multiple raters or observers. As an alternative, you could look at the correlation of ratings of the same single observer repeated on two different occasions. For example, let's say you collected videotapes of child-mother interactions and had a rater code the videos for how often the mother smiled at the child. To establish inter-rater reliability you could take a sample of videos and have two raters code them independently. To estimate test-retest reliability you could have a single rater code the same videos on two different occasions. You might use the inter-rater approach especially if you were interested in using a team of raters and you wanted to establish that they yielded consistent results. If you get a suitably high inter-rater reliability you could then justify allowing them to work independently on coding different videos. You might use the test-retest approach when you only have a single rater and don't want to train any others. On the other hand, in some studies it is reasonable to do both to help establish the reliability of the raters or observers.
The parallel forms estimator is typically only used in situations where you intend to use the two forms as alternate measures of the same thing. Both the parallel forms and all of the internal consistency estimators have one major constraint -- you have to have multiple items designed to measure the same construct. This is relatively easy to achieve in certain contexts like achievement testing (it's easy, for instance, to construct lots of similar addition problems for a math test), but for more complex or subjective constructs this can be a real challenge. If you do have lots of items, Cronbach's Alpha tends to be the most frequently used estimate of internal consistency.
The test-retest estimator is especially feasible in most experimental and quasi-experimental designs that use a no-treatment control group. In these designs you always have a control group that is measured on two occasions (pretest and posttest). the main problem with this approach is that you don't have any information about reliability until you collect the posttest and, if the reliability estimate is low, you're pretty much sunk.
Each of the reliability estimators will give a different value for reliability. In general, the test-retest and inter-rater reliability estimates will be lower in value than the parallel forms and internal consistency ones because they involve measuring at different times or with different raters. Since reliability estimates are often used in statistical analyses of quasi-experimental designs (e.g., the analysis of the nonequivalent group design), the fact that different estimates can differ considerably makes the analysis even more complex.
Seminar Statistik STIS - 3 Oktober 2011
5 years ago