Department of Management

A method for additive bias correction in cross-cultural surveys

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearch

Standard

A method for additive bias correction in cross-cultural surveys. / Scholderer, Joachim; Grunert, Klaus G.; Brunsø, Karen.

Proceedings of the 8th Cross Cultural Research Conference. 2001.

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearch

Harvard

Scholderer, J, Grunert, KG & Brunsø, K 2001, A method for additive bias correction in cross-cultural surveys. in Proceedings of the 8th Cross Cultural Research Conference. 8th Cross Cultural Research Conference, Hawaii, 12/12/2001.

APA

Scholderer, J., Grunert, K. G., & Brunsø, K. (2001). A method for additive bias correction in cross-cultural surveys. In Proceedings of the 8th Cross Cultural Research Conference

CBE

Scholderer J, Grunert KG, Brunsø K. 2001. A method for additive bias correction in cross-cultural surveys. In Proceedings of the 8th Cross Cultural Research Conference.

MLA

Vancouver

Scholderer J, Grunert KG, Brunsø K. A method for additive bias correction in cross-cultural surveys. In Proceedings of the 8th Cross Cultural Research Conference. 2001

Author

Bibtex

@inproceedings{c5bd07701bb211db9d04000ea68e967b,
title = "A method for additive bias correction in cross-cultural surveys",
abstract = "Measurement bias in cross-cultural surveys can seriously threaten the validity of hypothesis tests. Direct comparisons of means depend on the assumption that differences in observed variables reflect differences in the underlying constructs, and not an additive bias that may be caused by cultural differences in the understanding of item wording or response category labels. However, experience suggests that additive bias can be found more often than not. Based on the concept of partial measurement invariance (Byrne, Shavelson and Muth{\'e}n, 1989), the present paper develops a procedure for eliminating additive bias from cross-cultural data. The procedure involves four steps: (1) embed a potentially biased item in a factor-analytic measurement model, (2) test for the existence of additive bias between populations, (3) use the factor-analytic model to estimate the magnitude of the bias, and (4) replace differences between observed item means by unbiased estimates of the difference between {"}true{"} population means. Sampling moments are derived for the purpose of hypothesis testing. The procedure is demonstrated in a numerical example. Potential applications include comparisons of means from different cultures, and correction of raw data before use in cross-cultural segmentation studies.",
keywords = "MAPP, Additive bias correction, Tv{\ae}rkulturel unders{\o}gelse, MAPP, Additive bias correction, Cross-cultural survey",
author = "Joachim Scholderer and Grunert, {Klaus G.} and Karen Bruns{\o}",
note = "Haves ikke HH{\AA}",
year = "2001",
language = "English",
booktitle = "Proceedings of the 8th Cross Cultural Research Conference",

}

RIS

TY - GEN

T1 - A method for additive bias correction in cross-cultural surveys

AU - Scholderer, Joachim

AU - Grunert, Klaus G.

AU - Brunsø, Karen

N1 - Haves ikke HHÅ

PY - 2001

Y1 - 2001

N2 - Measurement bias in cross-cultural surveys can seriously threaten the validity of hypothesis tests. Direct comparisons of means depend on the assumption that differences in observed variables reflect differences in the underlying constructs, and not an additive bias that may be caused by cultural differences in the understanding of item wording or response category labels. However, experience suggests that additive bias can be found more often than not. Based on the concept of partial measurement invariance (Byrne, Shavelson and Muthén, 1989), the present paper develops a procedure for eliminating additive bias from cross-cultural data. The procedure involves four steps: (1) embed a potentially biased item in a factor-analytic measurement model, (2) test for the existence of additive bias between populations, (3) use the factor-analytic model to estimate the magnitude of the bias, and (4) replace differences between observed item means by unbiased estimates of the difference between "true" population means. Sampling moments are derived for the purpose of hypothesis testing. The procedure is demonstrated in a numerical example. Potential applications include comparisons of means from different cultures, and correction of raw data before use in cross-cultural segmentation studies.

AB - Measurement bias in cross-cultural surveys can seriously threaten the validity of hypothesis tests. Direct comparisons of means depend on the assumption that differences in observed variables reflect differences in the underlying constructs, and not an additive bias that may be caused by cultural differences in the understanding of item wording or response category labels. However, experience suggests that additive bias can be found more often than not. Based on the concept of partial measurement invariance (Byrne, Shavelson and Muthén, 1989), the present paper develops a procedure for eliminating additive bias from cross-cultural data. The procedure involves four steps: (1) embed a potentially biased item in a factor-analytic measurement model, (2) test for the existence of additive bias between populations, (3) use the factor-analytic model to estimate the magnitude of the bias, and (4) replace differences between observed item means by unbiased estimates of the difference between "true" population means. Sampling moments are derived for the purpose of hypothesis testing. The procedure is demonstrated in a numerical example. Potential applications include comparisons of means from different cultures, and correction of raw data before use in cross-cultural segmentation studies.

KW - MAPP

KW - Additive bias correction

KW - Tværkulturel undersøgelse

KW - MAPP

KW - Additive bias correction

KW - Cross-cultural survey

M3 - Article in proceedings

BT - Proceedings of the 8th Cross Cultural Research Conference

ER -