Comparison of time series and case-crossover analyses of air pollution and hospital admission data

被引:75
作者
Fung, KY [1 ]
Krewski, D
Chen, Y
Burnett, R
Cakmak, S
机构
[1] Univ Windsor, Dept Math & Stat, Windsor, ON N9B 3P4, Canada
[2] Univ Ottawa, Inst Populat Hlth, McLaughlin Ctr Populat Hlth Risk Assessment, Ottawa, ON K1N 6N5, Canada
[3] Univ Ottawa, Dept Epidemiol & Community Med, Ottawa, ON K1H 8M5, Canada
[4] Hlth Canada, Hlth Environm & Consumer Safety Branch, Ottawa, ON K1A 0L2, Canada
关键词
time series analysis; case-crossover design; air pollution; hospital admissions; LOESS smoothing; natural splines; computer simulation;
D O I
10.1093/ije/dyg246
中图分类号
R1 [预防医学、卫生学];
学科分类号
1004 ; 120402 ;
摘要
Background Time series analysis is the most commonly used technique for assessing the association between counts of health events over time and exposure to ambient air pollution. Recently, case-crossover analysis has been proposed as an alternative analytical approach. While each technique has its own advantages and disadvantages, there remains considerable uncertainty as to which statistical methodology is preferable for evaluating data of this type. Methods The objective of this paper is to evaluate the performance of different variations of these two procedures using computer simulation. Hospital admission data were generated under realistic models with known parameters permitting estimates based on time series and case-crossover analyses to be compared with these known values. Results While accurate estimates can be achieved with both methods, both methods require some decisions to be made by the researcher during the course of the analysis. With time series analysis, it is necessary to choose the time span in the LOESS smoothing process, or degrees of freedom when using natural cubic splines. For case-crossover studies using either uni- or bi-directional control selection strategies, the choice of time intervals needs to be made. Conclusions We prefer the times series approach because the best estimates of risk that can be obtained with time series analysis are more precise than the best estimates based on case-crossover analysis.
引用
收藏
页码:1064 / 1070
页数:7
相关论文
共 27 条
[1]  
Allison PD, 1995, Survival analysis using sas: A practical guide, V2nd
[2]   Control for seasonal variation and time trend in case crossover studies of acute effects of environmental exposures [J].
Bateson, TF ;
Schwartz, J .
EPIDEMIOLOGY, 1999, 10 (05) :539-544
[3]   COVARIANCE ANALYSIS OF CENSORED SURVIVAL DATA [J].
BRESLOW, N .
BIOMETRICS, 1974, 30 (01) :89-99
[4]   Air pollution effects on hospital admissions: a statistical analysis of parallel time series [J].
Burnett, R. ;
Bartlett, S. ;
Krewski, D. ;
Roberts, G. ;
Raad-Young, M. .
ENVIRONMENTAL AND ECOLOGICAL STATISTICS, 1994, 1 (04) :325-332
[5]   ASSOCIATIONS BETWEEN AMBIENT PARTICULATE SULFATE AND ADMISSIONS TO ONTARIO HOSPITALS FOR CARDIAC AND RESPIRATORY-DISEASES [J].
BURNETT, RT ;
DALES, R ;
KREWSKI, D ;
VINCENT, R ;
DANN, T ;
BROOK, JR .
AMERICAN JOURNAL OF EPIDEMIOLOGY, 1995, 142 (01) :15-22
[6]  
Cakmak S, 1998, J EXPO ANAL ENV EPID, V8, P129
[7]  
CHECKOWAY H, 2000, 99 HLTH EFF I
[8]   On the use of generalized additive models in time-series studies of air pollution and health [J].
Dominici, F ;
McDermott, A ;
Zeger, SL ;
Samet, JM .
AMERICAN JOURNAL OF EPIDEMIOLOGY, 2002, 156 (03) :193-203
[9]   CENSORED-DATA AND THE BOOTSTRAP [J].
EFRON, B .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1981, 76 (374) :312-319
[10]  
HASTIE TJ, 1990, GEN ADDIITIVE MODELS