Abstract

The multiple indicator cluster survey (MICS) is a household survey tool designed to obtain internationally comparable, statistically rigorous data of standardized indicators related to the health situation of children and women. Missing data in a large number of categorical variables are a serious concern for MICS, following complex dependency structures and inconsistency problems that impose severe challenges to the investigators. Despite the popularity of multiple imputation of missing data, its acceptance and application still lag in large-scale studies with complicated data sets such as MICS. We propose interdependent hybrid multiple imputation (HMI) techniques which combines features of existing MI approaches to handle complex missing data in large scale household surveys. The iterative HMI approach is observed to be a good competitor to the existing approaches, with often smaller root mean square errors, empirical standard errors and standard errors. Regardless of any combination, the iterative HMI method is markedly superior to the existing MI methods in terms of computational efficiency. Results from household data example support the capacity of proposed method to handle complex missing data.

摘要

多指标类集调查（MICS）是一种家庭调查工具，旨在获取与儿童和妇女的健康状况相关的国际标准化指标的统计上严格的国际可比数据。大量的分类变量中的数据丢失对于MICS来说是一个严重的问题，其原因是复杂的依存关系结构和不一致的问题给研究人员带来了严峻的挑战。尽管丢失数据的多重插补很流行，但在具有复杂数据集（例如MICS）的大规模研究中，其接受和应用仍然落后。我们提出了相互依赖的混合多重插补（HMI）技术，该技术结合了现有MI方法的功能来处理大规模家庭调查中的复杂缺失数据。HMI迭代方法被认为是现有方法的良好竞争者，其均方根误差，经验标准误差和标准误差通常较小。无论采用哪种组合，迭代HMI方法在计算效率方面都明显优于现有的MI方法。家庭数据示例的结果支持所提出的方法处理复杂缺失数据的能力。