Latent profiles of multi-dimensionality of self-compassion predict youth psychological adjustment outcomes during the COVID-19: A longitudinal mixture regression analysis

Abstract

The multi-dimensionality of self-compassion and its influence on college students' adjustments have not been widely examined during the COVID-19 pandemic. The current study aims to explore profiles of self-compassion dimensions in Chinese college students and examine the predictive effects of different profiles on students' adjustment outcomes. A longitudinal online survey of college students was conducted in mainland China. In May of 2020, college students (N = 1361) completed Neff's Self-Compassion Scale-Short Form during the home quarantine period. Six months after the baseline assessment, students (N = 717) reported their level of anxiety symptoms, depression symptoms, insomnia symptoms, complex post-traumatic stress (CPTSD) symptoms, post-traumatic growth (PTG), and positive youth development (PYD). A latent profile analysis was adopted to identify profiles of self-compassion dimensions. A longitudinal regression mixture model was used to examine the predictive effects of different self-compassion profiles on college students' adjustment outcomes. Three classes best characterized the self-compassion dimensions of college students: the compassionate group (54.1%), the uncompassionate group (38.6%), and the extremely uncompassionate group (7.3%). College students in the compassionate group scored significantly higher on positive adjustment indicators (PTG and PYD), and significantly lower on negative adjustment indicators (anxiety, depression, insomnia, and CPTSD symptoms) than students in the other two groups. College students in the uncompassionate group scored significantly lower on negative indicators, and higher on PYD scores than students in the extremely uncompassionate group, but did not differ in PTG levels from students in the extremely uncompassionate group. College students in the compassionate group adjusted best across groups. The limitations that using a composite score to represent the relative balance of self-compassion dimensions were highlighted. Intervention programs need to focus on improving the level of positive self-responses in college students.

Keywords: College students; Longitudinal design; Mixture regression analysis; Psychological adjustment; Self-compassion.

Fig. 1

Z scores of self-compassion dimension in the 3-class model