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
Review
. 2021 Oct 19;11(1):260-283.
doi: 10.1093/jssam/smab038. eCollection 2023 Feb.

Multiple Imputation with Massive Data: An Application to the Panel Study of Income Dynamics

Yajuan Si  1 , Steve Heeringa  2 , David Johnson  3 , Roderick J A Little  4   5 , Wenshuo Liu  6 , Fabian Pfeffer  7 , Trivellore Raghunathan  8   9
Affiliations
Review

Multiple Imputation with Massive Data: An Application to the Panel Study of Income Dynamics

Yajuan Si et al. J Surv Stat Methodol. .

Abstract

Multiple imputation (MI) is a popular and well-established method for handling missing data in multivariate data sets, but its practicality for use in massive and complex data sets has been questioned. One such data set is the Panel Study of Income Dynamics (PSID), a longstanding and extensive survey of household income and wealth in the United States. Missing data for this survey are currently handled using traditional hot deck methods because of the simple implementation; however, the univariate hot deck results in large random wealth fluctuations. MI is effective but faced with operational challenges. We use a sequential regression/chained-equation approach, using the software IVEware, to multiply impute cross-sectional wealth data in the 2013 PSID, and compare analyses of the resulting imputed data with those from the current hot deck approach. Practical difficulties, such as non-normally distributed variables, skip patterns, categorical variables with many levels, and multicollinearity, are described together with our approaches to overcoming them. We evaluate the imputation quality and validity with internal diagnostics and external benchmarking data. MI produces improvements over the existing hot deck approach by helping preserve correlation structures, such as the associations between PSID wealth components and the relationships between the household net worth and sociodemographic factors, and facilitates completed data analyses with general purposes. MI incorporates highly predictive covariates into imputation models and increases efficiency. We recommend the practical implementation of MI and expect greater gains when the fraction of missing information is large.

Keywords: Diagnostics; Efficiency; Massive Data; Missing Data; Validity.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
Observed (Obs) and Missing (Miss) Patterns of Eighteen Wealth Components of the Cases with Missing Wealth Information in the 2013 Panel Study of Income Dynamics Study.
Figure 2.
Figure 2.
The Distribution and Skewness of Home Values before and after the Cube-Root Transformation.
Figure 3.
Figure 3.
Pairwise Correlation Coefficients between Sixteen Wealth Components.
Figure 4.
Figure 4.
The Bland Altman Plot in the Comparison of Imputed Wealth Values (Cube-Root Transformed) from Multiple Imputation and Hot Deck Imputations. The three dashed lines represent the mean of differences minus two standard deviations, mean of differences and mean of differences plus two standard deviations. The critical difference (i.e., two times the standard deviation of differences) is fifty. Some wealth values are negative because of high debts and low assets.
See this image and copyright information in PMC

References

    1. Altman D. G., Bland J. M. (1983), “Measurement in Medicine: The Analysis of Method Comparison Studies,” The Statistician, 32, 307–317.
    1. Andridge R. R., Little R. J. A. (2010), “A Review of Hot Deck Imputation for Survey Non‐Response,” International Statistical Review, 78, 40–64. - PMC - PubMed
    1. Azur M., Stuart E. A., Frangakis C. M., Leaf P. J. (2011), “Multiple Imputation by Chained Equations: What Is It and How Does It Work?,” International Journal of Methods in Psychiatric Research, 20, 40–49. - PMC - PubMed
    1. Bondarenko I., Raghunathan T. E. (2016), “Graphical and Numerical Diagnostic Tools to Assess Suitability of Multiple Imputations and Imputation Models,” Statistics in Medicine, 35, 3007–3020. - PubMed
    1. Bricker J., Goodman S., Moore K. B., Volz A. H. (2020), “Wealth and Income Concentration in the SCF: 1989–2019”, available at https://www.federalreserve.gov/econres/notes/feds-notes/wealth-and-incom.... Accessed on September 8, 2021.