Abstract: Intensive longitudinal studies have become increasingly popular in psychological research because they allow researchers to capture within-person variability and examine the temporal dynamics of psychological processes. However, the intensive nature of repeated assessments may place additional burden on participants and increase the likelihood of careless responding (CR), which can undermine data quality and lead to biased research conclusions. The present study focuses on CR in intensive longitudinal study and aims to systematically examine its consequences for data analysis and statistical inference, develop effective approaches for identifying CR by integrating machine learning techniques with behavioral log data recorded during the response process, develop and evaluate strategies for handling CR, and develop a user-friendly tool for CR detection and handling to facilitate data screening and preprocessing in intensive longitudinal studies.

Key words: intensive longitudinal study, data quality, careless responding, insufficient effort responding, data preprocessing