采样(信号处理)
经验抽样法
计算机科学
心理学
电信
社会心理学
探测器
作者
Jessica Fritz,Marilyn L. Piccirillo,Zachary D. Cohen,Madelyn Frumkin,Olivia J Kirtley,Julia Moeller,Andreas B. Neubauer,Lesley A. Norris,Noémi Katalin Schuurman,Evelien Snippe,Laura F. Bringmann
标识
DOI:10.1177/25152459241267912
摘要
The experience-sampling method (ESM) captures psychological experiences over time and in everyday contexts, thereby offering exciting potential for collecting more temporally fine-grained and ecologically valid data for psychological research. Given that rapid methodological developments make it increasingly difficult for novice ESM researchers to be well informed about standards of ESM research and to identify resources that can serve as useful starting points, we here provide a primer on 10 essential design and implementation considerations for ESM studies. Specifically, we (a) compare ESM with cross-sectional, panel, and cohort approaches and discuss considerations regarding (b) item content and phrasing; (c) choosing and formulating response options; (d) timescale (sampling scheme, sampling frequency, survey length, and study duration); (e) change properties and stationarity; (f) power and effect sizes; (g) missingness, attrition, and compliance; (h) data assessment and administration; (i) reliability; and (j) replicability and generalizability. For all 10 topics, we discuss challenges and—if available—potential solutions and provide literature that can serve as starting points for more in-depth readings. We also share access to a living, web-based resources library with a more extensive catalogue of literature to facilitate further learning about the design and implementation of ESM. Finally, we list topics that although beyond the scope of our article, can be relevant for the success of ESM studies. Taken together, our article highlights the most essential design and implementation considerations for ESM studies, aids the identification of relevant in-depth readings, and can thereby support the quality of future ESM studies.
科研通智能强力驱动
Strongly Powered by AbleSci AI