The Monetary Choice Questionnaire (MCQ) is a widely used behavioral task that measures the rate of delay discounting (i.e., k), the degree to which a delayed reward loses its present value as a function of the time to its receipt. Both 21- and 27-item MCQs have been extensively validated and proven valuable in research. Different methods have been developed to streamline MCQ scoring. However, existing scoring methods have yet to tackle the issue of missing responses or provide clear guidance on imputing such data. Due to this lack of knowledge, the present study developed and compared three imputation approaches that leverage the MCQ's structure and prioritize ease of implementation. Additionally, their performance was compared with mode imputation. A Monte Carlo simulation was conducted to evaluate the performance of these approaches in handling various missing responses in each observation across two datasets from prior studies that employed the 21- and 27-item MCQs. One of the three approaches consistently outperformed mode imputation across all performance measures. This approach involves imputing missing values using congruent non-missing responses to the items corresponding to the same k value or introducing random responses when congruent answers are unavailable. This investigation unveils a straightforward method for imputing missing data in the MCQ while ensuring unbiased estimates. Along with the investigation, an R tool was developed for researchers to implement this strategy while streamlining the MCQ scoring process.
Copyright: © 2023 Yeh et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.