This study describes the use of Generalizability Theory (GT) and Many-Facet Rasch Measurement (MFRM) to evaluate and improve the rating procedure in a mathematics creative problem solving test. Results indicate that these two methods agree about the relative degrees of variation among the facets but slightly differ on how to account for the sources of variation. For both the GT and MFRM results, the variance component for the Person by Item interaction is relatively large, indicating significant variability. Results from both methods also indicated that variance due to rater and interactions related with rater were relatively low. The reliability of the mean rating for each examinee based on five items, four raters and four rating criteria using a fully crossed design was 0.58(G-coefficient) and 0.49(phi coefficient). We found the guidelines from the Decision study (D-study) to obtain a more optimal reliability coefficients, it needed at least ten items. Depending on the purpose of a particular study, GT or MFRM may be the appropriate measurement technique to use.

No abstract