Multiple imputation for continuous variables using a Bayesian principal component analysis†

By Vincent Audigier, François Husson, Julie Josse. 2014

84 citations recorded by the source corpus.

ABSTRACT We propose a multiple imputation method based on principal component analysis (PCA) to deal with incomplete continuous data. To reflect the uncertainty of the parameters from one imputation to the next, we use a Bayesian treatment of the PCA model. Using a simulation study and real data sets, the method is compared to two classical approaches: multiple imputation based on joint modelling and on fully conditional modelling. Contrary to the others, the proposed method can be easily used on data sets where the number of individuals is less than the number of variables and when the variables are highly correlated. In addition, it provides unbiased point estimates of quantities of interest, such as an expectation, a regression coefficient or a correlation coefficient, with a smaller mean squared error. Furthermore, the widths of the confidence intervals built for the quantities of interest are often smaller whilst ensuring a valid coverage.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/896609a6401cbe96d87500cdf89f87d458acc321

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

Citations in the corpus

missMDA: A Package for Handling Missing Values in Multivariate Data Analysis (2016, methodology): “Audigier et al. (2016a) compared imputation quality of the regularized iterative FAMD algorithm to the one using the algorithm of Stekhoven and Bühlmann (2012) and highlighted the performance of the former approach when imputing continuous, categorical and mixed data.”
MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets (2019, background): “Little & Rubin, 2002, Chapters 11 & 12), with potentially low-rank constraints (e.g. Audigier et al., 2016).”
Understanding generative AI output with embedding models (2025, unknown): “We collected titles of scientific papers from the arXiv ( 55 ), recording pairs of scientific abstracts, each containing one from the arXiv and one generated by LLaMa-2 70B. Figure 3A shows that across five subject areas, the shift in the PC coordinates between the real abstracts and those…”
Understanding Generative AI Content with Embedding Models (2024, methodology): “Real [74]: We propose a multiple imputation method based on principal component analysis (PCA) to deal with incomplete continuous data.”