Joint modeling of medical cost and survival in complex sample surveys

Huiping Xu, Joanne Daggy, Danni Yu, Bruce A. Craig, Laura Sands

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Medical cost data are typically highly skewed to the right with a large proportion of zero costs. It is also common for these data to be censored because of incomplete follow-up and death. In the case of censoring due to death, it is important to consider the potential dependence between cost and survival. This association can occur because patients who incur a greater amount of medical cost tend to be frailer and hence are more likely to die. To handle this informative censoring issue, joint modeling of cost and survival with shared random effects has been proposed. In this paper, we extend this joint modeling approach to handle a final feature of many medical cost data sets, i.e., Specifically, the fact that data were obtained via a complex survey design. Specifically, we extend the joint model by incorporating the sample weights when estimating the parameters and using the Taylor series linearization approach when calculating the standard errors. We use a simulation study to compare the joint modeling approach with and without these adjustments. The simulation study shows that parameter estimates can be seriously biased when information about the complex survey design is ignored. It also shows that standard errors based on the Taylor series linearization approach provide satisfactory confidence interval coverage. The proposed joint model is applied to monthly hospital costs obtained from the 2004 National Long Term Care Survey.

Original languageEnglish
Pages (from-to)1509-1523
Number of pages15
JournalStatistics in Medicine
Volume32
Issue number9
DOIs
StatePublished - Apr 30 2013

Fingerprint

Joint Modeling
Sample Survey
Joints
Costs and Cost Analysis
Survival
Costs
Survey Design
Joint Model
Taylor series
Standard error
Linearization
Informative Censoring
Simulation Study
Hospital Costs
Long-Term Care
Censoring
Surveys and Questionnaires
Random Effects
Biased
Confidence interval

Keywords

  • Complex survey
  • Medical cost data
  • Random effects
  • Sample weights
  • Survival analysis

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Joint modeling of medical cost and survival in complex sample surveys. / Xu, Huiping; Daggy, Joanne; Yu, Danni; Craig, Bruce A.; Sands, Laura.

In: Statistics in Medicine, Vol. 32, No. 9, 30.04.2013, p. 1509-1523.

Research output: Contribution to journalArticle

Xu, Huiping ; Daggy, Joanne ; Yu, Danni ; Craig, Bruce A. ; Sands, Laura. / Joint modeling of medical cost and survival in complex sample surveys. In: Statistics in Medicine. 2013 ; Vol. 32, No. 9. pp. 1509-1523.
@article{3ddae3ab9fa74fb1845edfb8ae102411,
title = "Joint modeling of medical cost and survival in complex sample surveys",
abstract = "Medical cost data are typically highly skewed to the right with a large proportion of zero costs. It is also common for these data to be censored because of incomplete follow-up and death. In the case of censoring due to death, it is important to consider the potential dependence between cost and survival. This association can occur because patients who incur a greater amount of medical cost tend to be frailer and hence are more likely to die. To handle this informative censoring issue, joint modeling of cost and survival with shared random effects has been proposed. In this paper, we extend this joint modeling approach to handle a final feature of many medical cost data sets, i.e., Specifically, the fact that data were obtained via a complex survey design. Specifically, we extend the joint model by incorporating the sample weights when estimating the parameters and using the Taylor series linearization approach when calculating the standard errors. We use a simulation study to compare the joint modeling approach with and without these adjustments. The simulation study shows that parameter estimates can be seriously biased when information about the complex survey design is ignored. It also shows that standard errors based on the Taylor series linearization approach provide satisfactory confidence interval coverage. The proposed joint model is applied to monthly hospital costs obtained from the 2004 National Long Term Care Survey.",
keywords = "Complex survey, Medical cost data, Random effects, Sample weights, Survival analysis",
author = "Huiping Xu and Joanne Daggy and Danni Yu and Craig, {Bruce A.} and Laura Sands",
year = "2013",
month = "4",
day = "30",
doi = "10.1002/sim.5617",
language = "English",
volume = "32",
pages = "1509--1523",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "9",

}

TY - JOUR

T1 - Joint modeling of medical cost and survival in complex sample surveys

AU - Xu, Huiping

AU - Daggy, Joanne

AU - Yu, Danni

AU - Craig, Bruce A.

AU - Sands, Laura

PY - 2013/4/30

Y1 - 2013/4/30

N2 - Medical cost data are typically highly skewed to the right with a large proportion of zero costs. It is also common for these data to be censored because of incomplete follow-up and death. In the case of censoring due to death, it is important to consider the potential dependence between cost and survival. This association can occur because patients who incur a greater amount of medical cost tend to be frailer and hence are more likely to die. To handle this informative censoring issue, joint modeling of cost and survival with shared random effects has been proposed. In this paper, we extend this joint modeling approach to handle a final feature of many medical cost data sets, i.e., Specifically, the fact that data were obtained via a complex survey design. Specifically, we extend the joint model by incorporating the sample weights when estimating the parameters and using the Taylor series linearization approach when calculating the standard errors. We use a simulation study to compare the joint modeling approach with and without these adjustments. The simulation study shows that parameter estimates can be seriously biased when information about the complex survey design is ignored. It also shows that standard errors based on the Taylor series linearization approach provide satisfactory confidence interval coverage. The proposed joint model is applied to monthly hospital costs obtained from the 2004 National Long Term Care Survey.

AB - Medical cost data are typically highly skewed to the right with a large proportion of zero costs. It is also common for these data to be censored because of incomplete follow-up and death. In the case of censoring due to death, it is important to consider the potential dependence between cost and survival. This association can occur because patients who incur a greater amount of medical cost tend to be frailer and hence are more likely to die. To handle this informative censoring issue, joint modeling of cost and survival with shared random effects has been proposed. In this paper, we extend this joint modeling approach to handle a final feature of many medical cost data sets, i.e., Specifically, the fact that data were obtained via a complex survey design. Specifically, we extend the joint model by incorporating the sample weights when estimating the parameters and using the Taylor series linearization approach when calculating the standard errors. We use a simulation study to compare the joint modeling approach with and without these adjustments. The simulation study shows that parameter estimates can be seriously biased when information about the complex survey design is ignored. It also shows that standard errors based on the Taylor series linearization approach provide satisfactory confidence interval coverage. The proposed joint model is applied to monthly hospital costs obtained from the 2004 National Long Term Care Survey.

KW - Complex survey

KW - Medical cost data

KW - Random effects

KW - Sample weights

KW - Survival analysis

UR - http://www.scopus.com/inward/record.url?scp=84876336654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876336654&partnerID=8YFLogxK

U2 - 10.1002/sim.5617

DO - 10.1002/sim.5617

M3 - Article

C2 - 23023654

AN - SCOPUS:84876336654

VL - 32

SP - 1509

EP - 1523

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 9

ER -