This paper reports the results of using a three-layer backpropagation artificial neural network to predict item difficulty in a reading comprehension test. Two network structures were developed, one with and one without a sigmoid function in the output processing unit. The data set, which consisted of a table of coded test items and corresponding item difficulties, was partitioned into a traini...

[Purpose] The purpose of this study was to compare the item difficulty degree between the Pediatric Balance Scale and Fullerton Advanced Balance scale for children with cerebral palsy. [Subjects and Methods] Forty children with cerebral palsy (male=17, female=23) voluntarily participated in the study. Item difficulty was expressed in the Rasch analysis using a logit value, with a higher value i...

This study investigated the utility of all of the above (AOTA) as a test option in multiple-choice items. It aimed at estimating item fit, item difficulty, item discrimination, and guess factor of such a choice. Five reading passages of the Key English Test (KET, 2010) were adapted. The test was reconstructed in 2 parallel forms: Test 1 did not include the abovementioned alternative, whereas Te...

multiple-choice questions are commonly employed for testing languageknowledge. however, since in the recently proposed systematic approach toitem writing, using various item formats is desirable and there is very fewresearches on the possibility of using translation items for giving variety toitems on a test. the present study aims at comparing reliability and itemdifficulty of translation and ...