• Journal of the Korean School Mathematics Society
• /
• v.10 no.1
• /
• pp.113-127
• /
• 2007

This study explored the possibility of building a statistical model predicting difficulty of mathematics test items through the analysis of nation-wide scholastic ability test results for the past 5 years. Multiple linear regression analysis was conducted in predicting difficulty of mathematics test items. We adopted three major areas for independent variables: the content area, the behavior area, and the test item format area, each of which was categorized into more detailed sub-areas. For the dependent variable, the proportion of correct answer was used to represent the item difficulty. Statistically significant independent variables were included in the regression model based on the stepwise selection method. Several important factors affecting difficulty of mathematics test items for each area were identified. R-squares for the final regression model were fairly high, implying that the regression equation can be used to predict difficulty of test items at an acceptable level. Lastly, the regression model was cross-validated using independently collected data. We believe that this study will provide basic but very critical information for predicting the proportion of correct answer by showing the factors that should be considered for developing mathematics test items for the college entrance examination or high school classroom test.

• Proceedings of the Korea Database Society Conference
• /
• 2008.05a
• /
• pp.87-106
• /
• 2008

This study identified the properties of online game, and analyzed existing studies on the impact of the properties of online game on flow. As a result, graphics, sounds, scenarios, game speed, manipulability, and item difficulty were identified as properties of online game, which were influential factors to flow. As a result, the hypotheses on scenarios, game speed, and item difficulty were adopted as significantly influential factors to flow, Attribute of online game. Meanwhile, the hypotheses on graphics, sounds, and manipulability, which were expected to significantly impact flow, were rejected.

• English Language & Literature Teaching
• /
• v.15 no.4
• /
• pp.75-94
• /
• 2009

This study was designed to assess demotivation factors and compare the factor between two secondary school student groups. It furthermore examined how the factors related to students' L2 proficiency. A 31-item questionnaire was completed by 407 junior (JH) and senior high school (SH) students. Five factors were extracted through the principal axis factoring: Teachers' competence and teaching styles, Dissatisfaction with English classes and grading system, Difficulty of learning English, Lack of motivation and interest in learning English, and Inadequate learning contents. Although both JH and SH students did not perceive their English teacher as a strong attribution of demotivation, Difficulty of learning English and Dissatisfaction with English classes and grading system were the two strongest demotivating factors. When compared the overall mean scores of each factor between JH and SH groups, significant differences were found in all factors except Factor 4, with SH students reporting stronger demotivation. JH students attributed their demotivation to Difficulty of learning English, while SH students attributed that to Dissatisfaction with English classes and grading system. Both groups tended to attribute their demotivation to external forces. The study also showed that several demotivation factors related negatively to L2 proficiency.

• Research in Mathematical Education
• /
• v.7 no.3
• /
• pp.163-189
• /
• 2003

The purpose of this study is to develop a test, which can be used in creative problem solving ability in mathematics of the mathematically gifted and the regular students. This test tool is composed of three categories; fluency (number of responses), flexibility (number of different kinds of responses), and originality (degree of uniqueness of responses) which are the factors of the creativity. After applying to 462 middle school students, this test was analyzed into item analysis. As a results of item analysis, it turned out to be meaningful (reliability: 0.80, validity: item 1(1.05), item 2(1.10), item 3(0.85), item 4(0.90), item 5(1.08), item difficulty: item 1(-0.22), item 2(-0.41), item 3(0.23), item 4(0.40), item 5(-0.01), item discriminating power: item 1(0.73), item 2(0.73), item 3(0.67), item 4(0.51), item 5(0.56), over the level of a standard basis. This means that the test tool was useful in the test process of creative problem solving ability in mathematics

• Journal of the Korean earth science society
• /
• v.24 no.3
• /
• pp.150-159
• /
• 2003

This study suggests methods of assessing scientific creativity and developing items, which can be achieved when both earth science knowledge and general creativity are applied at the same time. According to the results of this study, the cognitive ability gaps between creativity and scientific creativity were clearly defined by the terms' operational definition. Four factors in the Subcategory Of Scientific Creativity-fluency, flexibility, elaboration, and originality-were selected, and the possibility of developing items out of these factors was discovered. The operational definitions of the four factors were given and the criteria for assessment and scoring were set. The validity, reliability, discrimination, and difficulty, which were the conditions required for the assessment instruments, were verified through three field trials of inputting the assessment instruments for scientific creativity. The assessment instruments were composed of 8 items with 2items for each factor. The average item fitness index obtained was 0.99, Cronbach , the item inter-consistency was 0.79,the inter-rater reliability of each item was 0.78, the inter-rater reliability of each factor was 0.75, the item discrimination power was 0.19, and the item difficulty was 0.00. Because the results were within the permitted limit of the conditions required for assessment instruments, the assessment instruments developed for scientific creativity in this study can be said to be very favorable.

• Physical Therapy Korea
• /
• v.18 no.3
• /
• pp.94-102
• /
• 2011

The purpose of this study was to review existing assessment tools for patients with low back pain and improve them through combination. A total of 314 patients with low back pain participated. Their condition was assessed using the Oswestry Disability Questionnaire (ODQ), the Quebec Back Pain Disability Scale (QBPD), and the Back Pain Functional Scale (BPFS). Rasch analysis was applied to identify inappropriate items, item difficulties, and the separation index. In this study, the 'sex life' item of the ODQ (10 items) and the 'sleeping' item of the BPFS (12 items) showed misfit statistics, whereas all items of the QBPD (20 items) were appropriate. After combining the ODQ, QBPD and BPFS, Rasch analysis was applied. The 'pain intensity', and the 'sex life' item of the ODQ and the 'throw a ball' item of QBPD showed misfit statistics. These 3 items were retained for further analysis. The remaining 42 combined ODQ-QBPD-BPFS items were arranged according to difficulty. For all subjects, the most difficult item was 'pain intensity', whereas the easiest was 'take food out of the refrigerator'. As the separation index of 42 combined ODQ-QBPD-BPFS was higher than that of the three questionnaires separately, difficulty of items varied with some need for rearrangement. The results of this study confirmed the possibility and need for a new back pain disability assessment tool, and produced one. Further study is needed to refine the questionnaire in consideration of psychosocial and occupational factors.

• 재활복지
• /
• v.21 no.2
• /
• pp.169-190
• /
• 2017

The purpose of this study was to investigate item goodness-of-fit of Scale, Rasch rating scale model was applied to 5 dimensions 24 items of the Test of Performance Strategies (TOPS) in a sample of athletes with physical disabilities (n=215). An assumption to test Rasch Model, which is satisfaction of unidimensionality, is regarded through PCAR test, and WINSTEPS 3.65 program is used to test the goodness-of-fit of items. The results of this study were: First, 3-point rating category was appropriate for the TOPS instead of the existing 5-point rating category. Second, as a result of analyzing the goodness-of-fit of the items, 21 items of the TOPS were suitable, but 3 items were not. Third, the item reliability of person separation of the TOPS was acceptable, but the person reliability of item separation was not suitable and it was necessary to adjust the item order considering the difficulty level of the items. Fourth, as a result of comparing the individual attribute score and the difficulty level through the Item-Person Map, the distribution of the item difficulty distribution was shown to be biased in some factors compared to the personal attribute score distribution.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.2
• /
• pp.1240-1252
• /
• 2015

The purpose of this study was to investigate feeding difficulty and its influencing factors of elders with dementia in long-term care facilities. Participants were 158 elders with dementia residing in three nursing facilities. Data were collected from Aug. 18 to Sep. 12 in 2014. The feeding difficulty in dementia scale, Korean version-Activities of Daily Living and Mini-Mental State Exam-Korean version were used as instruments. Data were analyzed using descriptive statistics, t-test, ANOVA, Pearson correlation and stepwise multiple regression by SPSS 17.0. Mean feeding difficulty score was $0.62{\pm}0.43$(range of 0-2). The highest feeding difficulty item was "patient require close supervision while feeding". The variables influencing the feeding difficulty was ADL(${\beta}=.312$), cognitive function(${\beta}=-.172$) which explained about 20.0% of total variance. The results suggest the need of developing feeding difficulty coping strategy according to dietary behavior phase, In addition, the development and testing the educational program for caregivers to help feeding difficulty of the elders with dementia in long-term facility are recommended.

• Physical Therapy Korea
• /
• v.15 no.2
• /
• pp.44-53
• /
• 2008

The purpose of this preliminary study was to develop a measurement for assessing risk factors for falling in community-dwelling elderly persons. Rasch analysis and principal component analysis were performed to examine whether items on the Activities-Specific Balance Confidence (ABC), assessing self-efficacy, and items on the Berg Balance Scale (BBS), assessing balance function, contribute jointly to a unidimensional construct in the elderly. A total of 35 elderly persons (4 men, 31 women) participated. In this study, each item of ABC (16 items) and BBS (14 items) was scored on a 5-point ordinal rating scale from 0 to 4. The initial Rasch and principal component analysis indicated that 3 of the ABC items and 2 of the BBS items were misfit for this study. These 5 items were excluded from further study. After combining ABC and BBS, Rasch and principal component analyses were examined and finally 23 items selected; 12 items from ABC, 11 items from BBS. The 23 combined ABC-BBC items were arranged in order of difficulty. The hardest item was 'walk outside on icy sidewalks' and the easiest item was 'pivot transfer'. Although structural calibration of each 5 rating scale categories was not ordered, the other three essential criteria of Linacre's optimal rating scale were satisfied. Overall, the ABC-BBS showed sound item psychometric properties. Each of the 5 rating scale categories appeared to distinctly identify subjects at different ability levels. The findings of this study support that the new ABC-BBS scale measure balance function and self-efficacy. It will be a clinically useful assessment of risk factors for falling in the elderly. However, the number of subjects was too small to generalize our results. Further study is needed to develop a new assessment considering more risk factors of falling in elderly.

• The Journal of the Korea Contents Association
• /
• v.20 no.5
• /
• pp.344-350
• /
• 2020

The purpose of this study was to investigate the cohesion-related text factors that affected the correct answer rate of the English reading section in the Korean CSAT. To this end, reading passages of the 2014-2018 CSAT and CSAT mock test were collected and analyzed in terms of cohesion. And then, correlation analysis was implemented between the results regarding cohesion and item difficulty. The conclusions were as follows. First, the correct answer rate tended to increase as the linguistic burden of learners was reduced, when specific arguments between sentences were repeated. Second, there was no statistically significant correlation between the 8 sub-area of latent semantic analysis and the correct answer rate. Finally, the pedagogical implications of this study and suggestions for further study were discussed.