Personalized Prediction of Behaviors and Experiences: An Idiographic Person–Situation Test

Abstract

A longstanding goal of psychology is to predict the things that people do and feel, but tools to accurately predict future behaviors and experiences remain elusive. In the present study, we used intensive longitudinal data ( N = 104 college-age adults at a midwestern university; total assessments = 5,971) and three machine-learning approaches to investigate the degree to which three future behaviors and experiences—loneliness, procrastination, and studying—could be predicted from past psychological (i.e., personality and affective states), situational (i.e., objective situations and psychological situation cues), and time (i.e., trends, diurnal cycles, time of day, and day of the week) phenomena from an idiographic, person-specific perspective. Rather than pitting persons against situations, such an approach allows psychological phenomena, situations, and time to jointly predict future behaviors and experiences. We found (a) a striking degree of prediction accuracy across participants, (b) that a majority of participants’ future behaviors are predicted by both person and situation features, and (c) that the most important features vary greatly across people.

Generalizations: The grail and the gremlins.

“…Highlighting the variability in our samples requires nothing more than a good graph placed prominently in the main text (not buried in Supplemental Materials). Better descriptions of behavioral variability will lead to the next—arguably more challenging—step, which is to include in our research measures and tasks expected to relate to the outcome variables of primary interest, thus helping to explain the individual differences we observe (see Beck & Jackson, 2022, for successful application of a person-specific, idiographic approach to prediction of future behaviors and experiences). This requires that we have strong theory (Buzbas et al, 2022) and clear hypotheses—or at least, educated guesses—regarding potential sources of variability.…”

Classification of Lapses in Smokers Attempting to Stop: A Supervised Machine Learning Approach Using Data From a Popular Smoking Cessation Smartphone App

“…Our results add to those from a recent body of work in which supervised machine-learning algorithms have been developed to classify or predict smoking-related events. 12–14 , 17 In addition, we drew on a recent approach taken to train and test individual-level algorithms to predict dietary lapses, 23 alcohol consumption, 31 and loneliness and procrastination, 32 with a view to informing the development of a technology-mediated JITAI. Although useful, individual-level algorithms could only be developed for a minority of participants in the present study.…”

Understanding EMA Data: A Tutorial on Exploring Item Performance in Ecological Momentary Assessment Data

“…Therefore, this section demonstrates ways in which several contextual factors may be associated with response behavior. The question of the extent to which behavior or experiences are stable across different contexts is reminiscent of the well-established person-situation debate in personality psychology (Beck & Jackson, 2022). If EMA data are to advance our understanding of such questions, items that measure constructs that likely vary across different contexts should indeed show such variation.…”

“…Recent methodological innovations extend dynamical structural equation modeling to be able to include person-situation interactions(Castro- Alvarez et al, 2022) Adolf et al (2017). have shown how context-related changes in parameter estimates can be modeled for time series analyses Beck and Jackson (2022). display how information about situations can be leveraged for individual prediction of behaviors and experiences and discuss the relevance of situation information for personality research, whileCloos et al (2022) use the sensitivity to emotionally relevant events as a quality criterion for EMA items.…”