Large-scale health surveys provide a wealth of information for addressing problems in health sciences research. Designed for multiple purposes, these surveys frequently have large sample sizes and extensive measurements of demographic and socioeconomic characteristics, risk factors, disease outcomes and health care service use and costs. Complex features of the sampling design typically employed to select the survey sample, coupled with the vast amount of information available from the survey database, underlie issues that must be addressed during data processing and analysis. Numerous articles in the literature have focused on the debate of whether or not, and how, to control for features of the sample design during data analysis. Traditional statistical methods for simple random samples and the software that accompanies them have historically not had the capacity to account for the survey design. Recent advancements in statistical methodology for survey data analysis have greatly expanded the analytical tools available to the survey analyst. Commercial software packages that incorporate these methods offer the analyst convenient ways for applying such tools to large survey databases in an easy and efficient manner. We present an overview of analysis strategies for survey data and illustrate their application via the SUDAAN software system. Examples for analyses are provided through data from two large US health surveys, the National Health Interview Survey and the Longitudinal Study of Aging. Questions of both a cross-sectional and longitudinal nature are addressed. The examples involve logistic regression, time-to- event analysis, and repeated measures analysis.
Get full access to this article
View all access options for this article.
References
1.
Shah BV, Barnwell BG, Hunt PN, LaVange LM. SUDAAN user's manual (release 5.50). Research Triangle Park, NC: Research Triangle Institute, 1991.
2.
McDowell A., Engel A., Massey JT, Maurer K.Plan and operation of the Second Health and Nutrition Examination Survey 1976-80 . Vital and Health Statistics1981; 1(15).
3.
National Center for Health Statistics.Design and estimation for the National Health Interview Survey, 1985-94. Vital and Health Statistics1989; 2(110).
4.
Kovar MG, Chyba M., Fitti JEThe Longitudinal Study of Aging: 1984-1990. Vital and Health Statistics1992; 1(28).
5.
Harlan WR, Landis JR, Schmouder RL, Goldstein NH, Harlan LCBlood lead and blood pressure. Journal of theAmerican Medical Association1985; 253: 530-34.
6.
Jones DY, Schatzkin A., Green SB et al. Dietary fat and breast cancer in NHANES I Epidemiologic Follow-up Study. Journal of theNational Cancer Institute1987; 79: 465-71.
7.
Stevens RG, Jones DY, Micozzi MS, Taylor PRBody iron stores and the risk of cancer. New England Journal of Medicine1988; 319: 1047-62.
8.
Yip R., Williamson DFBody iron stores and risk of cancer [To the Editor]. New England Journal of Medicine1989; 320: 1012.
9.
Korn EL and Graubard BIEpidemiologic studies utilizing surveys: accounting for the sampling design . American Journal of Public Health1991; 81: 1166-73.
10.
Plan and operation of the Hispanic Health and Nutrition Examination Survey 1982-84. Vital and Health Statistics1985; 1(19).
11.
Kish L.Survey Sampling. New York: John Wiley, 1965.
12.
Cochran WGSampling Techniques, 3rd edn. New York: John Wiley, 1977.
13.
Horvitz DG, Thompson DJA generalization of sampling without replacement from a finite universe. Journal of the American Statistical Association1952; 47: 663-85.
14.
Woodruff RSA simple method for approximating the variance of a complicated estimate. Journal of the American Statistical Association1971; 66: 411-14.
15.
Kish L., Frankel MRInference from complex samples (with discussion). Journal of the Royal Statistical Society Series B 1974; 36: 1-37.
16.
Kish L., Frankel MRBalanced repeated replications for standard errors. Journal of the American Statistical Association1970; 65: 1071-94.
17.
Bean J., Schnack GAAn application of balanced repeated replication to the estimation of variance components. Proceedings of the Section on Social Statistics Part II. Washington, DC: American Statistical Association, 1977; 938-42.
18.
Wolter KMIntroduction to Variance Estimation. New York: Springer, 1985.
19.
Koch GG, Freeman DH, Freeman JLStrategies in the multivariate analysis of data from complex surveys. International Statistical Review1975; 43: 59-78.
20.
Fuller WARegression analysis for sample surveys. Sankhya Series C 1975; 37: 117-32.
21.
Shah BV, Holt MM, Folsom REInference about regression models from sample survey data. Bulletin of the International Statistical Institute1977; 47: 43-57.
22.
Freeman DH, Freeman JL, Brock DB, Koch GGStrategies in the multivariate analysis of data from complex surveys. II. An application to the United States Health Interview Survey. International Statistical Review1976; 44(3): 317-30.
23.
Landis JR, Lepkowski JM, Eklund SA, Stehouwer SAA statistical methodology for analyzing data from a complex survey: the first National Health and Nutrition Examination Survey. Vital and Health Statistics1982; 2(92).
24.
Binder DAOn the variances of asymptotically normal estimators from complex surveys . International Statistical Review1983; 51: 279-92.
25.
Shah BV, Folsom RE, Harrell FE, Dillard CNSurvey data analysis software for logistic regression. Research Triangle Park, NC: Research Triangle Institute , 1984.
26.
LaVange LM, Iannachione VG, Garfinkel SGAn application of logistic regression methods to survey data: predicting high cost users of medical care. Proceedings of the Section on Survey Research Methods. Washington, DC: American Statistical Association, 1986.
Chambless LE , Boyle KEMaximum likelihood methods for complex sample data: logistic regression and discrete proportional hazards models. Communications in Statistics, Theory and Methods1985; 14: 1377-92.
Skinner CJ, Holt D, Smith TMF eds. Analysis of complex surveys. New York: John Wiley, 1989.
31.
Rao Jnk, Bellhouse DRThe history and development of the theoretical foundations of survey based estimation and statistical analysis. In: Proceedings of the American Statistical Association Sesquicentennial Invited Paper Sessions , Gail MH, Johnson NL eds. Alexandria, VA: American Statistical Association, 1989.
32.
Koch GG, Gillings DB, Stokes MEBiostatistical implications of design, sampling and measurement to the analysis of health science data. Annual Review of PublicHealth1980; 1: 163-225.
33.
Koch GG, Gillings DBInference, design based vs model based. In: Encyclopedia of statistical sciences, Johnson NL, Kotz S eds. New York: John Wiley, 1983; 4: 84-8.
34.
Koch GG, Beck JDStatistical methodologies useful for the analysis of data from risk assessment studies. Journal of Public Health Dentistry1992; 52(3): 146-67.
35.
Pfeffermann D., Holmes DJRobustness considerations in the choice of a method of inference for regression analysis of survey data. Journal of the Royal Statistical Society Series A 1985; 148: 268-78.
36.
Pfeffermann D. , Smith Tmf.Regression models for grouped populations in cross-section surveys. International Statistical Review1985; 53: 37-59.
37.
Sarndall CEDesign-based and model-based inference in survey sampling. Scandinavian Journal of Statistics1978; 5: 27-52.
38.
Korn EL, Graubard BIAnalysis of large health surveys: accounting for the sampling design. Journal of the Royal Statistical Society Series A 1995; 158(2): 263-95.
39.
Liang K-Y.,Zeger SLLongitudinal data analysis using generalized linear models. Biometrika1986; 73: 13-22.
40.
Zeger SL, Liang K-Y.Longitudinal data analysis for discrete and continuous outcomes. Biometrics1986; 42: 121-30.
41.
Zeger SL, Liang K-Y.,Albert PSModels for longitudinal data: a generalized estimating equation approach. Biometrics1988; 44: 1049-60.
42.
LaVange LM, Keyes LL, Koch GG, Margolis PAApplication of sample survey methods for modeling ratios to incidence densities . Statistics in Medicine1994; 13: 343-55.
43.
Graubard, BI , Korn ELRegression analysis with clustered data. Statistics in Medicine1994; 13: 509-22.
44.
Koch GG, Paquette DWDesign and statistical considerations in periodontal clinical trials. Journal of Periodontal Research1996; 1(1).
45.
Fuller WA, Kennedy W., Schnell D., Sullivan G., Park HJPC-CARP. Ames, IA: Statistical Laboratory, Iowa State University, 1986.
46.
Rust K.Variance estimation for complex estimators in sample surveys. Journal of Official Statistics1985; 1: 381-97.
47.
Fay REA jackknifed chi-squared test for complex samples. Journal of the American Statistical Association1985; 80: 148-57.
48.
Fay RECPLX: Contingency table analysis for complex designs, program documentation . US Bureau of the Census, 1989.
49.
LaVange LM, Shah BV, Barnwell BG, Killinger JFSUDAAN: a comprehensive package for survey data analysis. In: Liepins GL, Uppuluri VRR eds. Data quality control. New York : Marcel Dekker, 1991.
50.
Shah BV, Barnwell BG, Bieler GSSUDAAN user's manual (release 7.0). Research Triangle Park, NC: Research Triangle Institute, 1996.
51.
Shah BV, Folsom RE, LaVange LM, Boyle KE, Wheeless SC, Williams RLStatistical methods and mathematical algorithms used in SUDAAN. Research Triangle Park, NC: Research Triangle Institute , 1993.
52.
Thomas DA, Rao Jnk.A Monte-Carlo study of exact levels of goodness-of-fit statistics under cluster sampling. Proceedings of the Section on Survey Research Methods. Washington, DC: American Statistical Association, 1984.
53.
Korn EL, Graubard BISimultaneous testing of regression coefficients with complex survey data: use of Bonferroni t statistics. American Statistician1990; 44: 270-76.
54.
LaVange LM, Koch GGAnalysis of repeated measures studies with multiple regression methods for sample surveys. Manuscript presented at the Drug Information Association annual meeting, Washington, DC , June, 1994.
55.
US Department of Health and Human Services , Bureau of Health Professions, Office of Data Analysis and Management. Area resource file (ARF) system: information for health resources planning and research. Washington, DC: US Government Printing Office, ODAM4-87, 1989.
56.
Lafata JE, Koch GG, Weissert WGEstimating activity limitation in the noninstitutionalized population: a method for small areas. American Journal of Public Health1994; 84(11): 1813-17
57.
Bilgrad R.National death index user's manual. Hyattsville, MD: Public Health Service, 1990.
58.
Graubard BI , Korn ELSurvey inference for subpopulations. American Journal of Epidemiology1996; 144: 102-6.
59.
Pfeffermann D. , LaVange LMRegression models for stratified multi-stage cluster samples. In: Skinner CJ, Holt D, Smith TMF eds. Analysis of complex surveys. New York: John Wiley, 1989: 237-60.
60.
Pfeffermann D.The role of sampling weights when modeling survey data. International Statistical Review1993; 61(2): 317-37.
61.
Graubard BI , Korn ELModelling the sampling design in the analysis of health surveys. Statistical Methods in Medical Research1996; 5: 263-81.
