Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2012 Jul;22(4):409-16.
doi: 10.1038/jes.2012.31. Epub 2012 May 9.

Using multiple imputation to assign pesticide use for non-responders in the follow-up questionnaire in the Agricultural Health Study

Sonya L Heltshe  1 , Jay H Lubin, Stella Koutros, Joseph B Coble, Bu-Tian Ji, Michael C R Alavanja, Aaron Blair, Dale P Sandler, Cynthia J Hines, Kent W Thomas, Joseph Barker, Gabriella Andreotti, Jane A Hoppin, Laura E Beane Freeman
Affiliations

Using multiple imputation to assign pesticide use for non-responders in the follow-up questionnaire in the Agricultural Health Study

Sonya L Heltshe et al. J Expo Sci Environ Epidemiol. 2012 Jul.

Abstract

The Agricultural Health Study (AHS), a large prospective cohort, was designed to elucidate associations between pesticide use and other agricultural exposures and health outcomes. The cohort includes 57,310 pesticide applicators who were enrolled between 1993 and 1997 in Iowa and North Carolina. A follow-up questionnaire administered 5 years later was completed by 36,342 (63%) of the original participants. Missing pesticide use information from participants who did not complete the second questionnaire impedes both long-term pesticide exposure estimation and statistical inference of risk for health outcomes. Logistic regression and stratified sampling were used to impute key variables related to the use of specific pesticides for 20,968 applicators who did not complete the second questionnaire. To assess the imputation procedure, a 20% random sample of participants was withheld for comparison. The observed and imputed prevalence of any pesticide use in the holdout dataset were 85.7% and 85.3%, respectively. The distribution of prevalence and days/year of use for specific pesticides were similar across observed and imputed in the holdout sample. When appropriately implemented, multiple imputation can reduce bias and increase precision and can be more valid than other missing data approaches.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Scatterplot of Brier skill score versus sensitivity + specificity for commonly used pesticides (P>0.05%).
Figure 2
Figure 2
Relative errors of imputed prevalence or percent usage (p) for commonly used pesticides (P>0.05%).
Figure 3
Figure 3
Box plots of observed and imputed days/year use of 2,4-D, alachlor, and diazinon in the holdout subset of the AHS.
Figure 4
Figure 4
Histogram display of the distribution of imputed Phase 2 reference year by true, observed reference year in the holdout dataset of the AHS.
See this image and copyright information in PMC

References

    1. Rubin DB. Multiple Imputation of Nonresponse in Surveys. J.Wiley and Sons; New York, NY: 1987.
    1. Schafer JL, Ezzatti-Rice TM, Johnson W, Khare M, Little RJA, Rubin DB. The NHANES III multiple imputation project. Proc Survey Res Methods Section Am Stat Assoc. 1996:28–37.
    1. Mislevy RJ, Johnson EG, Muraki E. Scaling procedures in NAEP. J Educational Stat. 1992;17:131–154.
    1. Stuart EA, Azur M, Frangakis C, Leaf P. Multiple imputation with large data sets: a case study of the children’s mental health initiative. Am J Epidemiol. 2009;169(9):1133–1139. - PMC - PubMed
    1. Kang T, Kraft P, Gauderman WJ, Thomas D. Multiple imputation methods for longitudinal blood pressure measurements from the Framingham Heart Study. BMC Genet. 2003;4(suppl 1):S43. - PMC - PubMed

Publication types