• Journal of the Korea Society of Computer and Information
• /
• v.22 no.7
• /
• pp.133-139
• /
• 2017

In this paper, we describe a permutation procedure in which we compute a resampling probability value and empirical quantile limits for Split-Half measure of internal reliability. We use the Split-Half reliability coefficient given by two simple methods, the Spearman-Brown formula and the two-part coefficient alpha. The use of a permutation test for Split-Half reliability coefficient is highlighted as a valuable tool when the sample sizes are small and necessary assumptions cannot be met. The permutation tests for Split-Half reliability coefficient are illustrated with an example analysis of two survey data with a sample size of 15 and 35, respectively, and a hypothetical data with a sample size of 5.

• Journal of Korean Academy of Nursing
• /
• v.35 no.6
• /
• pp.1072-1080
• /
• 2005

Purpose: This paper was conducted to test the reliability and validity of rd-SLS, developed by Podsakoff, et al. (1993) which measured 'substitutes for leadership'. Method: The subjects were 345 nurses in 5 general hospitals. Cronbach's and the Guttman split-half coefficient were used to test the reliability of rd-SLS. Factor analysis, and the correlations of the rv-SLS and SLS with rd-SLS were used for convergent and discriminant validity. Result: Cronbach's data was 0.76 and the Guttman split-half coefficient was 0.52. Twelve factors evolved by factor analysis, which explained $70.4\%$ of the total variance. This result was similar to previous study results. However, 'Indifference toward organizational rewards'-related items were classified two factors. It was not clear t hat the rd-SLS consisted of 13 concepts(factors). The correlations of the rv-SLS and SLS with the rd-SLS were 0.93 and 0.87 respectively. Conclusion: The rd-SLS showed a moderate degree of validity and reliability. Thus, it is recommended to use the rd-SLS in general nursing organizations for screening for leadership substitutes. In addition, it is necessary to clarify the concept of organizational rewards. In a further study, the factor structure of the rd-SLS may be considered.

• Korean Parent-Child Health Journal
• /
• v.4 no.2
• /
• pp.32-42
• /
• 2002

This study was conducted to test the reliability and validity of "What my baby is like(WBL)" that was developed by Pridham et al. for measuring infant temperament. 37 subjects were participated four times-1, 3, 6, and 12months, and 146 cases were analyzed. The construct validity for the scale was tested by factor analysis with four factor loading solution based on the previous study. One item was excluded because total-item correlation was too low, so that the number of total items were eighteen. The analysis yielded four well defined factors: amenability and persistence, activity, reactivity, and adaptability. These four factors explained 57.62% of the variance in the infant temperament. The criterion related Validity was confirmed by the relationship between the infant temperament and HOME, and between the infant temperament maternal confidence in childrearing. The reliability of the scale was determined with Cronbach's alpha coefficient and Guttman split-half coefficient. Cronbach's alpha was .86, for 18 items, and Guttman split-half cofficient was .81. In subscale analysis, Cronbach's alpha was .56~.84. In conclusion, WBL showed a high degree of validity and reliability, suitable in Korean infants for measuring temperament. In the further study, it would be necessary to refine the concept of temperament and to analyze the correlation between WBL and other temperament inventory.

• Korean Parent-Child Health Journal
• /
• v.2
• /
• pp.64-82
• /
• 1999

This study was conducted to test the reliability and validity of Maternal Self-Report Inventory that was developed by Shea and Tronick for measuring maternal self-esteem. The subjects were 154 mothers. The construct validity for the scale was tested by factor analysis with five factor loading solution based on the previous study. One item was excluded because total-item correlation was too low, so that the number of total items were twenty-five, the analysis yielded five well defined factors: confidence on the maternal role, general ability of maternal role, caretaking ability, readiness on maternal role, and feeling on the pregnancy and deli very. These five factors explained 52.38% of the variance in the maternal self-esteem. Maternal self-esteem was not affected by maternal age, educational level, occupation, religion, delivery type, or parity. The reliability of the scale was determined with Cronbach's alpha coefficient and Guttman split-half coefficient. Cronbach's alpha was .82, for 26 items, and .83 if one item was deleted. Guttman split-half cofficient was .75. In subscale analysis, Cronbach's alpha was .63~.84. In conclusion. Maternal Self-Report Inventory showed a high degree of validity and reliability, suitable in Korean mothers for measuring maternal self-esteem. In the further study, it would be necessary to compare the maternal self-esteem between mothers with normal babies and premature babies, for confirming the criterion-related validity of the inventory.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.22 no.6
• /
• pp.554-564
• /
• 2019

Purpose: This study verified the reliability and validity of the Diet Quality Index for Indian children (DQIIC). Methods: The study sample included 100 school going boys and girls (7-9 years). The dietary behavior of children was studied using a questionnaire and 24-hour dietary recall. The DQIIC comprises 21 items which aimed to assess the diet of Indian children on the basis of variety, adequacy of consumption of dietary components, and moderation in the amount of nutrients that are associated with diseases and dietary habits. The reliability of the DQIIC was assessed using the split half method, Cronbach's alpha, and test retest reliability. Content validity was evaluated using content validity ratio (CVR). Results: The intake of iron was found to be less than the recommended dietary allowances. There was frequent consumption of empty calorie packaged foods and higher than the recommended amount of sodium. Reliability of the DQIIC was 0.85 by split half method and the correlation coefficient for test retest reliability was 0.87. Cronbach's alpha was 0.62 and CVR was 0.85 for this index. Most of the children fell in the moderately healthy category. Conclusion: The DQIIC is a reliable and valid tool to assess the diet quality of Indian children between 7-9 years.

• Journal of Korean Academy of Nursing
• /
• v.29 no.2
• /
• pp.304-313
• /
• 1999

The purpose of this study is to test the reliability and validity test of PWI to utility of PWI. this newly developed by Sejin Jang which measures stress. The subject were 186 workers in service area. Cronbach's a and Guttman split-half coefficient is used to test the reliability of PWI. Factor analysis and the correlation of the GHQ-60. GHQ-30, GHQ-28, GHQ-20, and GHQ-12 with the PWI is used to convergent validity and discriminant validity. The important results of this study are as follows : Cronbach's $\alpha$ coefficient of data was 0.894 and Guttman split-half coefficient was 0.7097. The PWI was classified as 13 principle component (eigenvalue＞1.0). After exploring 4 factor structure according to previous study result, 4 factors was explained 40.5% out of the total variance. The factor 1 was explained 15.9% and then the rest three factor was 24.6%. Factor 2 and 4 showed good agreement but factor 1 and 3 did not. Depression-related items were classified two factors. Anxiety and depression-related items were loaded unifactor. It was not clear that the PWI was consist of 4 concepts(factors). The correlation of the GHQ-60, GHQ-30, GHQ-28, GHQ-20, and GHQ-12 with the PWI were 0.744~0.905. According to findings of this study. the PWI showed a high degree of validity and reliability. Thus it is recommended to use the PWI in general setting for screening for stress. In addition, it is necessary to clarify the concept of depression and anxiety. In the further study. it my be considered to the factor structure of PWI and studied to two or unidimensional factor structure.

• Journal of East-West Nursing Research
• /
• v.25 no.1
• /
• pp.26-32
• /
• 2019

Purpose: The purpose of this methodological study was to examine the validity and reliability of a translated Korean version of Templer's death anxiety scale among older adults. Methods: The translated Korean scale was administered to 203 older people who aged over 65 years. Exploratory factor analysis was utilized to assess the factor structure of the scale. Internal consistency of the scale was determined using Cronbach's ${\alpha}$ and Guttman's split-half coefficient. Results: Factor loadings of the scale ranged from .43 to .86. The scale showed good internal consistencies of both total scale (13 items, ${\alpha}=.83$) and three sub-scales: meaning of death (6 items, ${\alpha}=.77$), death-related event (5 items, ${\alpha}=.72$), and time of death (2 items, ${\alpha}=.80$). The concurrent validity compare with Fear of Death Scale was significant. The Cronbach's alpha and Guttman's split-half coefficient were .83 and .80, respectively. Conclusion: The findings of this study demonstrate that the Korean version of Templer's death anxiety scale had satisfactory validity and reliability to measure death anxiety among Korean older people.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.17 no.1
• /
• pp.120-128
• /
• 2011

Purpose: The purpose of this study was to test the validity and reliability of a life respect instrument for elementary school students. Method: The study was conducted as follows: identification of the tentative content domains, items generation, test of content validity, and data collecting with a preliminary questionnaire. Descriptive statistics, factor analysis, Cronbach's alpha, Guttman split-half, and Pearson correlation coefficients were used to analyze the data. Results: Two factors were extracted through factor analysis: 'Value about life respect', and 'Attitude about life respect.' These factors explained 58.82% of all factors. A total of 16 items belonging to 2 domains were generated. Cronbach's alpha and Guttman split-half coefficient were .82, and .84 respectively. Conclusion: The life respect instrument modified in this study will be useful for evaluating the effect of life respect education for elementary school students.

• Korean Journal of Adult Nursing
• /
• v.13 no.3
• /
• pp.486-495
• /
• 2001

The purpose of this study was to develop a Quality of Life(QOL) scale for breast cancer patients in Korea and to test the validity and reliability of the instrument. To achieve the purpose of the study, a questionnaire was developed to interview 10 breast cancer patients and distributed to 155 patients with breast cancer in Korea. For data analysis, SPSS WIN 8.0/PC were used. Item analysis and factor analysis were carried out to test validity of the QOL scale. Cronbach's ${\alpha}$ and Guttman split half coefficient were used to test reliability of the scale. The results were as follows; As a result of the item analysis, 27 items were selected from the total of 34 items. 6 factors were selected by factor analysis. Six factors were labeled as 'response to cancer diagnosis and treatment', 'family well-being', 'physical concerns', 'psychological well-being', 'spiritual well-being', and 'economic concerns'. Six factors were explained by 72.236% out of the total variance. The first factor explained 20.738% and the second factor explained 16.593%, which were major factors for Korean breast cancer patients. Chronbach's ${\alpha}$ coefficient of the tool was .9120, and Guttman split-half coefficient was .8148. The scale was identified to be a tool with a high degree of reliability and validity. Therefore, this scale can be effectively utilized for assessment of Quality of Life of patients with breast cancer in Korea.

• Child Health Nursing Research
• /
• v.18 no.2
• /
• pp.76-84
• /
• 2012

Purpose: This study was done to develop a cell phone addiction scale for Korean children. Methods: The process included construction of a conceptual framework, generation of initial items, verification of content validity, selection of secondary items, preliminary study, and extraction of final items. The participants were 268 children from grades 4 to 6 in two urban elementary schools. Construct validity, internal consistence reliability, and split-half reliability were used to analyze the data. Results: Nine items were categorized into 2 factors explaining 61.29% of total variance. The factors were labeled as obsessive compulsion (6 items) and dependency (3 items). Cronbach's alpha coefficient for the 9 items was .87, and Spearman-Brown coefficient was .83. Scale scores identified children as high risk users, at risk users, or average users by standard scores. Conclusion: The above findings indicate that the cell phone addiction scale for children has good validity and reliability when used with Korean children.