Novel Approaches for Improving data Quality from Self-Administered Questionnaires

Abstract

Self-administered questionnaires permit relatively quick and inexpensive data collection from large, diverse, and representative respondent samples However, many marketing scholars have scrutinized and then questioned the quality of survey data derived in this way. One ongoing issue is self-reports submitted by inattentive, disengaged, or mischievous respondents. Poor-quality data resulting from such self-reports remains problematic for marketing scholars and research practitioners. Even a low percentage of untrustworthy survey data may significantly bias statistical findings. Misleading data can yield results that hinder scientific progress or lead to misguided business actions that could harm companies , increase survey costs and create reputational damage for research practitioners. Some conventional wisdom about survey data collection, cleaning, and transformation may need revisiting, as many seminal research texts were largely or completely written during the pre-internet, pre-social media, and pre-Millennials era. Marketing researchers require new approaches to ensure high-quality survey data collected across various technological platforms. In this vein, an upcoming special issue of International Journal of Market Research will be dedicated to new approaches for improving survey data quality. The diverse topics suitable for this special issue include, but are not limited to, the following possibilities: • • Novel and creative ways to improve survey respondents' attentiveness, engagement, interest, and response accuracy via: | | Survey design innovations (e.g., modular survey design supplementing survey data via multi-method research designs) | | Questionnaire design innovations (e.g., improved manipulation checks and warnings better presentation of questionnaire instructions interactive and non-interactive entertainment breaks novel question formats, gamification • • Novel approaches for post-collection data handling (e.g., identifying and deleting careless responses, purging data submitted by mischievous respondents, identifying novel data quality indicators for post-hoc data cleaning developing composite data quality indices ; improving data imputation techniques) • • Recruitment techniques that eliminate undesirable respondents prior to data collection (e.g., screening based on personality traits or demographic characteristics) | | Unusual incentives for survey participation based on cooperation norms or other forms of motivation (e.g., charity/political cause donation)