Missing values are a common issue in quantitative social researches. One of the ways to handle missing data is by data imputation. This article outlines the challenges of traditional data imputation methods, which often introduce biases, and presents an advanced approach that features integration of paradata—auxiliary information collected during surveys—into the imputation process, using the European Social Survey (ESS) as its dataset. It is proposed that the usage of paradata could enhance predictive models used for imputation. It discusses the practical applications of data imputation, particularly through the lens of sensitive topics such as LGBT issues in socially conservative countries, where missingness could be heavily skewed due to social inacceptability of certain answers. To evaluate the effectiveness of the proposed approach towards imputation, the research employs the approach of using the 'ideal dataset', which is a subset of the original dataset with no missing vales, and then introduces artificial missing values that are not MCAR (Missing Completely at Random) to simulate the real case of missing data. Having artificial missingness allows for evaluation of the imputation procedure by comparing it with the original dataset. The study uses a novel approach towards creation of realistic missing data patterns through clustering based on response patterns. The research uses advanced statistical methods to handle missing data, and incorporates paradata from the survey process to improve the accuracy of predictive models. By comparing statistical metrics such as RMSE, MAE, and R-squared, the article evaluates the effectiveness of these methods in mimicking the original dataset's variability.
Read full abstract