TY - CONF T1 - Construction of Gratitude Scale Using Polytomous Item Response Theory Model T2 - IACAT 2017 Conference Y1 - 2017 A1 - Nurul Arbiyah KW - Gratitude Scale KW - polytomous items AB -

Various studies have shown that gratitude is essential to increase the happiness and quality of life of every individual. Unfortunately, research on gratitude still received little attention, and there is no standardized measurement for it. Gratitude measurement scale was developed overseas, and has not adapted to the Indonesian culture context. Moreover, the scale development is generally performed with classical theory approach, which has some drawbacks. This research will develop a gratitude scale using polytomous Item Response Theory model (IRT) by applying the Partial Credit Model (PCM).

The pilot study results showed that the gratitude scale (with 44 items) is a reliable measure (α = 0.944) and valid (meet both convergent and discriminant validity requirements). The pilot study results also showed that the gratitude scale satisfies unidimensionality assumptions.

The test results using the PCM model showed that the gratitude scale had a fit model. Of 44 items, there was one item that does not fit, so it was eliminated. Second test results for the remaining 43 items showed that they fit the model, and all items were fit to measure gratitude. Analysis using Differential Item Functioning (DIF) showed four items have a response bias based on gender. Thus, there are 39 items remaining in the scale.

Session Video 

JF - IACAT 2017 Conference PB - Niigata Seiryo University CY - Niigata, Japan UR - https://drive.google.com/open?id=1pHhO4cq2-wh24ht3nBAoXNHv7234_mjH ER - TY - JOUR T1 - Applying Bayesian item selection approaches to adaptive tests using polytomous items JF - Applied Measurement in Education Y1 - 2006 A1 - Penfield, R. D. KW - adaptive tests KW - Bayesian item selection KW - computer adaptive testing KW - maximum expected information KW - polytomous items KW - posterior weighted information AB - This study applied the maximum expected information (MEI) and the maximum posterior- weighted information (MPI) approaches of computer adaptive testing item selection to the case of a test using polytomous items following the partial credit model. The MEI and MPI approaches are described. A simulation study compared the efficiency of ability estimation using the MEI and MPI approaches to the traditional maximal item information (MII) approach. The results of the simulation study indicated that the MEI and MPI approaches led to a superior efficiency of ability estimation compared with the MII approach. The superiority of the MEI and MPI approaches over the MII approach was greatest when the bank contained items having a relatively peaked information function. (PsycINFO Database Record (c) 2007 APA, all rights reserved) PB - Lawrence Erlbaum: US VL - 19 SN - 0895-7347 (Print); 1532-4818 (Electronic) ER -