Methods for comparison of cost data

Xiao Hua Zhou, Catherine A. Melfi, Siu Hui

Research output: Contribution to journalArticle

87 Citations (Scopus)

Abstract

Background: Researchers are increasingly interested in examining costs of care, and large administrative and clinical databases have made relevant data readily available. Because a few patients incur high costs relative to most patients the distribution of cost data is often skewed. How robust are the usual methods of cost analysis against the skewed distribution of cost data? Objective: To determine the methods commonly used for comparing cost data, describe their limitations, and provide an alternate method of analysis. Design: Review of statistical methods used in studies of medical costs published in medical journals between January 1991 and January 1996. Description of a Z-score method for testing the equality of mean costs appropriate between two log-normal samples; and reanalysis of published two- sample comparison results done by using the Z-score method. Results: For two- sample comparisons, three methods were commonly used: the Student t-test on untransformed costs, the Wilcoxon test on untransformed costs, and the Student t-test on log-transformed costs. The t-test on untransformed costs ignores the skewness in cost data, the Wilcoxon test ignores unequal variances, and the t-test on log-transformed costs tests the wrong null hypothesis unless variances in the log-scale are equal. Eleven articles included two-sample tests and had enough information to allow reanalysis of the data using the Z-score method. These articles described a total of 23 Wilcoxon tests and 24 t-tests on untransformed costs. Most results did not change on reanalysis, but six results changed enough to alter conclusions. Specifically reanalysis of data for which one Wilcoxon test had shown statistically significant results showed nonsignificant results; reanalysis of data for which two Wilcoxon tests had shown nonsignificant results showed statistically significant results. In articles that used t-tests on untransformed costs, two statistically significant results became nonsignificant on reanalysis and one nonsignificant result became statistically significant on reanalysis. Conclusions: The methods commonly used to compare costs of two groups have limitations. Some limitations may change some conclusions, and the direction of the change cannot be predicted. The Z-score method is designed to adjust for skewness in cost data and is appropriate for comparing means of log-normally distributed cost data.

Original languageEnglish
Pages (from-to)752-756
Number of pages5
JournalAnnals of Internal Medicine
Volume127
Issue number8 II SUPPL.
StatePublished - 1997

Fingerprint

Costs and Cost Analysis
Students
Research Personnel
Databases

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Zhou, X. H., Melfi, C. A., & Hui, S. (1997). Methods for comparison of cost data. Annals of Internal Medicine, 127(8 II SUPPL.), 752-756.

Methods for comparison of cost data. / Zhou, Xiao Hua; Melfi, Catherine A.; Hui, Siu.

In: Annals of Internal Medicine, Vol. 127, No. 8 II SUPPL., 1997, p. 752-756.

Research output: Contribution to journalArticle

Zhou, XH, Melfi, CA & Hui, S 1997, 'Methods for comparison of cost data', Annals of Internal Medicine, vol. 127, no. 8 II SUPPL., pp. 752-756.
Zhou XH, Melfi CA, Hui S. Methods for comparison of cost data. Annals of Internal Medicine. 1997;127(8 II SUPPL.):752-756.
Zhou, Xiao Hua ; Melfi, Catherine A. ; Hui, Siu. / Methods for comparison of cost data. In: Annals of Internal Medicine. 1997 ; Vol. 127, No. 8 II SUPPL. pp. 752-756.
@article{a1f888e3f0014ab5887cb7a56d5a898f,
title = "Methods for comparison of cost data",
abstract = "Background: Researchers are increasingly interested in examining costs of care, and large administrative and clinical databases have made relevant data readily available. Because a few patients incur high costs relative to most patients the distribution of cost data is often skewed. How robust are the usual methods of cost analysis against the skewed distribution of cost data? Objective: To determine the methods commonly used for comparing cost data, describe their limitations, and provide an alternate method of analysis. Design: Review of statistical methods used in studies of medical costs published in medical journals between January 1991 and January 1996. Description of a Z-score method for testing the equality of mean costs appropriate between two log-normal samples; and reanalysis of published two- sample comparison results done by using the Z-score method. Results: For two- sample comparisons, three methods were commonly used: the Student t-test on untransformed costs, the Wilcoxon test on untransformed costs, and the Student t-test on log-transformed costs. The t-test on untransformed costs ignores the skewness in cost data, the Wilcoxon test ignores unequal variances, and the t-test on log-transformed costs tests the wrong null hypothesis unless variances in the log-scale are equal. Eleven articles included two-sample tests and had enough information to allow reanalysis of the data using the Z-score method. These articles described a total of 23 Wilcoxon tests and 24 t-tests on untransformed costs. Most results did not change on reanalysis, but six results changed enough to alter conclusions. Specifically reanalysis of data for which one Wilcoxon test had shown statistically significant results showed nonsignificant results; reanalysis of data for which two Wilcoxon tests had shown nonsignificant results showed statistically significant results. In articles that used t-tests on untransformed costs, two statistically significant results became nonsignificant on reanalysis and one nonsignificant result became statistically significant on reanalysis. Conclusions: The methods commonly used to compare costs of two groups have limitations. Some limitations may change some conclusions, and the direction of the change cannot be predicted. The Z-score method is designed to adjust for skewness in cost data and is appropriate for comparing means of log-normally distributed cost data.",
author = "Zhou, {Xiao Hua} and Melfi, {Catherine A.} and Siu Hui",
year = "1997",
language = "English",
volume = "127",
pages = "752--756",
journal = "Annals of Internal Medicine",
issn = "0003-4819",
publisher = "American College of Physicians",
number = "8 II SUPPL.",

}

TY - JOUR

T1 - Methods for comparison of cost data

AU - Zhou, Xiao Hua

AU - Melfi, Catherine A.

AU - Hui, Siu

PY - 1997

Y1 - 1997

N2 - Background: Researchers are increasingly interested in examining costs of care, and large administrative and clinical databases have made relevant data readily available. Because a few patients incur high costs relative to most patients the distribution of cost data is often skewed. How robust are the usual methods of cost analysis against the skewed distribution of cost data? Objective: To determine the methods commonly used for comparing cost data, describe their limitations, and provide an alternate method of analysis. Design: Review of statistical methods used in studies of medical costs published in medical journals between January 1991 and January 1996. Description of a Z-score method for testing the equality of mean costs appropriate between two log-normal samples; and reanalysis of published two- sample comparison results done by using the Z-score method. Results: For two- sample comparisons, three methods were commonly used: the Student t-test on untransformed costs, the Wilcoxon test on untransformed costs, and the Student t-test on log-transformed costs. The t-test on untransformed costs ignores the skewness in cost data, the Wilcoxon test ignores unequal variances, and the t-test on log-transformed costs tests the wrong null hypothesis unless variances in the log-scale are equal. Eleven articles included two-sample tests and had enough information to allow reanalysis of the data using the Z-score method. These articles described a total of 23 Wilcoxon tests and 24 t-tests on untransformed costs. Most results did not change on reanalysis, but six results changed enough to alter conclusions. Specifically reanalysis of data for which one Wilcoxon test had shown statistically significant results showed nonsignificant results; reanalysis of data for which two Wilcoxon tests had shown nonsignificant results showed statistically significant results. In articles that used t-tests on untransformed costs, two statistically significant results became nonsignificant on reanalysis and one nonsignificant result became statistically significant on reanalysis. Conclusions: The methods commonly used to compare costs of two groups have limitations. Some limitations may change some conclusions, and the direction of the change cannot be predicted. The Z-score method is designed to adjust for skewness in cost data and is appropriate for comparing means of log-normally distributed cost data.

AB - Background: Researchers are increasingly interested in examining costs of care, and large administrative and clinical databases have made relevant data readily available. Because a few patients incur high costs relative to most patients the distribution of cost data is often skewed. How robust are the usual methods of cost analysis against the skewed distribution of cost data? Objective: To determine the methods commonly used for comparing cost data, describe their limitations, and provide an alternate method of analysis. Design: Review of statistical methods used in studies of medical costs published in medical journals between January 1991 and January 1996. Description of a Z-score method for testing the equality of mean costs appropriate between two log-normal samples; and reanalysis of published two- sample comparison results done by using the Z-score method. Results: For two- sample comparisons, three methods were commonly used: the Student t-test on untransformed costs, the Wilcoxon test on untransformed costs, and the Student t-test on log-transformed costs. The t-test on untransformed costs ignores the skewness in cost data, the Wilcoxon test ignores unequal variances, and the t-test on log-transformed costs tests the wrong null hypothesis unless variances in the log-scale are equal. Eleven articles included two-sample tests and had enough information to allow reanalysis of the data using the Z-score method. These articles described a total of 23 Wilcoxon tests and 24 t-tests on untransformed costs. Most results did not change on reanalysis, but six results changed enough to alter conclusions. Specifically reanalysis of data for which one Wilcoxon test had shown statistically significant results showed nonsignificant results; reanalysis of data for which two Wilcoxon tests had shown nonsignificant results showed statistically significant results. In articles that used t-tests on untransformed costs, two statistically significant results became nonsignificant on reanalysis and one nonsignificant result became statistically significant on reanalysis. Conclusions: The methods commonly used to compare costs of two groups have limitations. Some limitations may change some conclusions, and the direction of the change cannot be predicted. The Z-score method is designed to adjust for skewness in cost data and is appropriate for comparing means of log-normally distributed cost data.

UR - http://www.scopus.com/inward/record.url?scp=0030764819&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030764819&partnerID=8YFLogxK

M3 - Article

VL - 127

SP - 752

EP - 756

JO - Annals of Internal Medicine

JF - Annals of Internal Medicine

SN - 0003-4819

IS - 8 II SUPPL.

ER -