• 의학교육논단
• /
• 제15권3호
• /
• pp.105-111
• /
• 2013

This paper addressed various issues related to the objectivity of student assessment in medical education. The objectivity of assessment was related to all the steps of test development, administration, and results reporting in terms of reliability and validity. Specifically, the objectivity of item formats, representativeness of test content, standardization of test administration, consistency of scoring procedures, and appropriateness of reporting test results were discussed by comparing performance assessment with traditional paper-and-pencil tests. The conclusions were derived from current measurement theories such as standards-based assessment, evidencebased design, and outcome-based assessment. Further, based on Shepard's propositions (2006), the objectivity of student assessment could be achieved by improving the concordance between educational objectives and assessment components such as item types, test contents, and test administration, scoring, and reporting.

• 아동학회지
• /
• 제12권2호
• /
• pp.78-93
• /
• 1991

The purpose of this study was to develop a rating scale for measuring children's temperament. The subjects were 622(324 boys and 298 girls) 3-to 7-year-old children. The temperament rating scale was composed of 50 items(4-point Liken scales) was based on mother's interview, RITQ and PTQ. The raters were the subjects' mothers. The data were analysed on dimensions of validity, reliability, and item discrimination. Statistical methods were factor analysis, ${\chi}^2$-test, and calculations of Pearson's r Cramer's V and Cronbach's $\alpha$. On validity 5 factors were extracted, which explained 84% of the total common variance. The 5 factors were named 'malleability', 'activity', 'sensitive reactivity', 'eating habits & physical constraints', 'physiological rhythmicity'. Regarding reliability, Cronbach's $\alpha$ appeared between .66 and .81 among the 5 factors. Regarding item discrimination, the degree of discrimination on all 50 items was significant and acceptable.

• Child Studies in Asia-Pacific Contexts
• /
• 제2권1호
• /
• pp.29-43
• /
• 2012

The purpose of the study was to generate the candidate items for the Adolescent Friendship Social Capital Scale. Both inductive and deductive approaches were used to generate the scale items. Halpern's conceptual map of social capital served as the theoretical basis of this scale, and guided the development of items. Semi-structured interviews with adolescents in Sydney, Melbourne and Beijing generated the initial pool of scale items. Twenty-six items were generated for the Adolescent Friendship Social Capital Scale. The items are organised in four theoretical constructs: Bonding Networks, Bridging Norms, Bridging Sanctions, and Linking Networks. Each item is a short statement followed by a five-point Likert scale anchored by 1= "Strongly disagree" and 5= "Strongly agree". The scale has several advantages over previous measures of adolescent friendship networks and friendship social capital. The scale has a strong and clear theoretical structure, the scale items demonstrate initial construct and content validity, and the format of the scale enables the collection of continuous data. However, in order to ensure the validity and reliability of the scale, another two stages of research need to be conducted in the future: scale development and scale evaluation.

• 한국응급구조학회지
• /
• 제28권2호
• /
• pp.7-19
• /
• 2024

Purpose: To adjust item numbers in a national test, this study used item response theory to examine changes in average scores, reliability, difficulty, and discrimination according to the adjustment of item numbers. Methods: We analyzed the dichotomous coding of correct and incorrect answers of 473 examinees in a mock test conducted in 2023. Additionally, as an explanatory pilot study, we used an online questionnaire to survey experts on their perceptions of the appropriate item numbers for each test subject from January 18, 2024, to February 15, 2024. Results: Regarding the item numbers on the national exam, experts preferred to reduce the number of management of emergency patients (33.14±6.09, p<.05) and advanced emergency medical care: subtopics (104.49±11.55, p<.05), and the total number of questions (217.82±20.95, p<.05). In a simulation set in which items with low item fit were removed after fitting a two-parameter item response theory model, reliability was maintained at .910 until the 5th test consisting of 185 questions with little loss of difficulty, discrimination, and average score, and there was no correlation between item numbers and average score. Conclusion: Experts responded that reducing the number of items on the national exam was appropriate. As a result of the item reduction simulation, there was no significant loss in the average score, difficulty, discrimination, or reliability. More reliable results could be obtained if the results were based on a validity analysis and analyzed using actual national exams.

• 대한간호학회지
• /
• 제32권3호
• /
• pp.395-405
• /
• 2002

The purpose of this study was to develop the instrument to measure family functioning for Korean family with a chronic ill child, and to test the validity and reliability of the instrument. Method: The items of instrument were consisted based on researchers' previous study of concept analysis of the Korean family functioning. Twenty six item scale was developed with six domains. In order to test reliability and validity of the scale, data were collected from the 231 families, who have a child with a chronic illness. Data was collected between August and September in 2001 in a General Hospital in Seoul, Korea. Result: The results were as follows: As a result of the item analysis, 24 items were selected from the total of 26 items, excluding items with low correlation with total scale. Six factors were evolved by factor analysis. Six factors explained 61.4% of the total variance. The first factor 'Affective bonding' explained 15.4%, 2nd factor 'External relationship' 11.8%, 3rd factor 'Family norm' 10.5%, 4th factor 'Role and responsibilities' 8.3%, 5th factor ' Communication' 7.9%, and the 6th factor 'Financial resource' explained 7.3%. Cronbach's $\alpha$ coefficient of this scale was .87 and Guttman spilt- half coefficient was .84. Conclusion: The study support the reliability and validity of the scale. There were distinct differences in dimensions of family functioning scales developed in the U. S.

• 대한간호학회지
• /
• 제42권7호
• /
• pp.957-964
• /
• 2012

Purpose: This study was conducted to develop a gambling addictive behavior scale for adolescents. Methods: The process involved construction of a conceptual framework, initial item search, verification of content validity, selection of secondary items, and extraction of final items. The participants were 299 adolescents from two middle schools and four high schools. Item analysis, factor analysis, criterion validity, internal consistency, and ROC curve were used to analyze the data. Results: For the final scale, 25 items were selected, and categorized into 4 factors which accounted for 54.9% of the total variance. The factors were labeled as loss of control, life dysfunction from gambling addiction, gambling experience, and social dysfunction from problem gambling. The scores for the scale were significantly correlated with addictive personality, irrational gambling belief, and adolescent's gambling addictive behavior. Cronbach's alpha coefficient for the 25 items was .94. Scale scores identified adolescents as being in a problem gambling group, a non-problem gambling group, and a non-gambling group by the ROC curve. Conclusion: The above findings indicate that the gambling addictive behavior scale has good validity and reliability and can be used with adolescents in Korea.

• 아동학회지
• /
• 제33권2호
• /
• pp.69-89
• /
• 2012

This study was conducted in order to develop a Children's Playfulness Rating Scale(CPRS) and to analyze it in terms of item discrimination, validity, and reliability. The participants in this study consisted of 861 parents whose children were aged from three to six years old. The item discrimination, determined by comparing the highest and lowest group using ${\chi}^2$, Cramer's V, was found to be satisfactory. The reliability of factors, as measured by Cronbach's ${\alpha}$, ranged from .85 to .95. The results of factor analysis identified 4 factors and 35 items were then selected from the 45 items in the original scale. The four factors identified were as follows; (1) leading participation (2) cognitive flexibility (3) expression of joy (4) voluntary full immersion. Concurrent validity was also established by using correlations between the CPRS and CPS(Children's Playfulness Scale). In conclusion, these results demonstrated that the Children's Playfulness Rating Scale is both reliable and valid.

• 여성건강간호학회지
• /
• 제12권4호
• /
• pp.316-325
• /
• 2006

Purpose: The purpose of this study was to develop a Critical Pathway for Uterine Artery Embolization patients. Method: There were 6 steps that were taken. Step 1 was selecting a diagnosis, and Step 2 was organizing a development team consisting of 7 experts. Step 3 analyzed the medical records, and Step 4 drew up a preliminary Critical Pathway. Step 5 tested the clinical validity of the preliminary Critical Pathway, and Step 6 developed the final Critical Pathway. Result: The contents of the medical practices observed in the medical records were investigated in seven areas: monitoring/assessment, treatment, medication, diet, activity, consults, and education/discharge plan; and a total of 73 items was identified. The validity of the 73 items was examined by a group of specialists. 68 items were adopted, 4 items revised, 1 item removed, and 1 item was added. Using the results, a preliminary Critical Pathway was drawn up. According to the results from examining the clinical validity of the preliminary Critical Pathway with five patients for five weeks, 3 items which showed discrepancy were revised and another 3 items were added. Then, the final Critical Pathway was completed. Conclusion: This Critical Pathway needs to be clinically applied and continuously to measure its effects in terms of the length of stay, cost.effectiveness, and the patients' and staffs' satisfaction.

• 한국간호교육학회지
• /
• 제22권2호
• /
• pp.137-151
• /
• 2016

Purpose: The purpose of this study was to develop and validate a Nurse's Character Scale for Care in Clinical settings (NCS_C). Methods: The NCS_C was developed and validated as follows: Item generation, preliminary test of questionnaire, and tests of validity and reliability. One hundred and thirty six preliminary items were developed through a literature review and in-depth interviews by 10 nurse-experts and five patients. The content validity of the items was verified through an evaluation by five nurses and seven professors in the fields of Korean literature, pedagogy and nursing. Finally, 53 items were confirmed through item analysis, factor analysis and validity tests including convergent, discriminant and concurrent validities. Data were analyzed using factor analysis, Pearson correlation coefficients, and Cronbach's alpha. Results: Thirteen factors evolved from the factor analysis, which explained 63.1% of the total variance. The factors referred to the union of two dimensions: the professional dimension and the interpersonal dimension. The internal consistency, Cronbach's alpha, was .95, and reliability of the subscales ranged from .58 to .87. Conclusion: The results of this study suggest that the NCS_C is a reliable and valid primary scale to measure nurses' or students' character level for better care in clinical settings.

• 대한간호학회지
• /
• 제43권3호
• /
• pp.379-388
• /
• 2013

Purpose: The purpose of this study was to develop a tool to evaluate patient safety culture in nursing homes and to test its validity and reliability. Methods: A preliminary tool was developed through interviews with focus group, content validity tests, and a pilot study. A nationwide survey was conducted from February to April, 2011, using self-report questionnaires. Participants were 982 employees in nursing homes. Data were analyzed using Cronbach's alpha, item analysis, factor analysis, and multitrait/multi-Item analysis. Results: From the results of the analysis, 27 final items were selected from 49 items on the preliminary tool. Items with low correlation with total scale were excluded. The 4 factors sorted by factor analysis contributed 63.4% of the variance in the total scale. The factors were labeled as leadership, organizational system, working attitude, management practice. Cronbach's alpha for internal consistency was .95 and the range for the 4 factors was from .86 to .93. Conclusion: The results of this study indicate that the Korean Patient Safety Culture Scale has reliability and validity and is suitable for evaluation of patient safety culture in Korean nursing homes.