Journal List > Korean J Nutr > v.44(1) > 1043896

TOOLS
Kwon, Kim, Lee, Kwak, Chung, Choi, and Kang: Statistical Approach to Test Construct Validity and Obtain Weights for the Children's Dietary Life Recognition and Practice Index
Research Article
Korean Journal of Nutrition

Korean Journal of Nutrition 2011; 44(1): 41-48.

Published online: 28 February 2011

DOI: https://doi.org/10.4163/kjn.2011.44.1.41

Statistical Approach to Test Construct Validity and Obtain Weights for the Children's Dietary Life Recognition and Practice Index

Sehyug Kwon1, Hye-Young P. Kim2, Jung-Sug Lee3, Tong-Kyung Kwak4, Hae-Rang Chung5, Young-Sun Choi6, Myung-Hee Kang7

1Department of Statistics, Hannam University, Daejon 306-791, Korea.

2Department of Food and Nutrition, Yongin University, Yongin 449-714, Korea.

3FANSA (Food and Nutrition Statistical Analysis), Seoul 153-764, Korea.

4Department of Food and Nutrition, Yonsei University, Seoul 120-749, Korea.

5Nutrition for the Future Inc., Seoul 151-848, Korea.

6Department of Food and Nutrition, Daegu University, Daegu 712-714, Korea.

7Department of Food and Nutrition, Hannam University, Daejon 305-811, Korea.

To whom correspondence should be addressed. (mhkang@hnu.ac.kr)

Received 18 January 2011       Revised 10 February 2011       Accepted 14 February 2011

© 2011 The Korean Nutrition Society

Abstract

Constructs with seven latent evaluation indicators and 18 observable survey questions were developed by food and nutrition experts to calculate a food safety recognition and practice index for children. The purpose of this study was to suggest statistical approaches to test construction validity on the constructs, obtain weights of the evaluation indicators, and develop questionnaires to calculate a children's food recognition and practice index. Survey data of 2,400 elementary fifth grade students were used as empirical results. Test validity was evaluated by exploratory factor analysis and confirmed to be highly significant by confirmatory factor analysis [i.e., linear structural relations (LISREL) analysis]. Standardized path coefficients of the LISREL analysis were suggested based on weights, and the weights were compared using the AHP and Delphi methods.

Keywords: constructs, factor analysis, LISREL, test validity, weight

Figures and Tables

Fig. 1
Path coefficients of LISREL analysis. 1) Path coefficient, *: p < 0.05, **: p <0.01. χ2: 32.8, p: 1.0. GFI: 0.98, AGFI: 0.98, RSMR: 0.032
kjn-44-41-g001
Table 1
Survey questionnaire
kjn-44-41-i001
Table 2
Results of exploratory factor analysis
kjn-44-41-i002
Table 3
Experts based and data based weights
kjn-44-41-i003

1) The weight of experts calculated by AHP and delphi method 2) Each path coefficient of indicators which is divided by sum of all path coefficients

Notes

This work was supported by Hannam University Research Fund of 2010.

References

1. Yi SJ. A study on the contents and legal problems of the children Food preference management system under the 'Special act on children eating habit safety management'. Public Law J. 2009. 10(4):327–350.
crossref
2. Special act on children eating habit safety management. http://www.law.go.kr/.
3. Kang MH. Production and evaluation of safety index for children's dietary life. KFDA report. 2009.
4. Johnson RA, Wichern DW. Applied multivariate statistical analysis. 1992. Prentice Hall.
5. Hair JF, Anderson RE, Tatham RK, Black WC. Multivariate data analysis. 1995. Prentice Hall.
6. Joreskog KG, Sorbom D. LISREL 8: Structural equation modelling with the SIMPLIS command language. 1993. Chicago: Scientific Software International.
7. Wainer H, Braun HIH. Test validity. 1988. lawrence erlbaum associates publishers.
TOOLS
Similar articles