Item Difficulty and Item Discrimination Coefficient for School and College Ability Tests (SCAT) Advanced Form in Classical Test Theory (CTT) and Item Response Theory (IRT) and the Correlation among Them Mohammad moqasqas Haifa T. Albokai Assistant Professor of Measurement and Evaluation Associate Professor of Measurement and Evaluation College of Education, Taibah University The aim of this study was to study the item difficulty and item discrimination of the SCAT (advance form) with CTT, and IRT, and to study the correlation among them. To do this, the researchers used the data of their previous study, which conducted in (2011). It consisted of (3943) subject. Then, they used two-statistical programs (TAP, Bilog-MG-3) to obtain the item difficulty and item discrimination coefficient in CTT and IRT. The results revealed a good item difficulty and item discrimination coefficient. Additionally, it showed a significant correlation between CTT and IRT in item difficulty and item discrimination. The researchers recommended of using any of these two theories to obtain the item difficulty and item discrimination for the tests and to do extended studies for the SCAT.
Item Difficulty and Item Discrimination Coefficient for School and College Ability Tests (SCAT) Advanced Form in Classical Test Theory (CTT) and Item Response Theory (IRT) and the Correlation among Them
Difficulty
the Correlation
(SCAT)
Discrimination
Coefficient
Publication Date
Thu Aug 01 2019
Journal Name
Journal Of Economics And Administrative Sciences
مقارنة مقدرات بيز لدالة المعولية لتوزيع باريتو من النوع الاول باستعمال دوال معلوماتية مضاعفة مختلفة
Pareto type I distribution
reliability function
bayes method
double prior distributions (chi-gamma square distribution. gamma- erlang distribution
erlang exponential distribution
the squared error loss function.
توزيع باريتو من النوع الاول
دالة المعولية
طريقة بيز
الدوال المعلوماتية المضاعفة : توزيع مربع كاي- كاما
توزيع كاما - ارلنك
التوزيع ارلنك- الاسي
دالة الخسارة التربيعية.
The comparison of double informative priors which are assumed for the reliability function of Pareto type I distribution. To estimate the reliability function of Pareto type I distribution by using Bayes estimation, will be used two different kind of information in the Bayes estimation; two different priors have been selected for the parameter of Pareto type I distribution . Assuming distribution of three double prior’s chi- gamma squared distribution, gamma - erlang distribution, and erlang- exponential distribution as double priors. The results of the derivaties of these estimators under the squared error loss function with two different double priors. Using the simulation technique, to compare the performance for
... Show More