“…This method was further extended to allow both group-varying intercept and slopes by Su et al (2016). Several more complicated models have also been proposed with different features, e.g., group-specific time patterns (Bonhomme and Manresa, 2015), time-varying grouped coefficients (Su et al, 2019), and group-varying threshold variables (Miao et al, 2020). Despite the success of those frequentist approaches, limited effort has been made under the Bayesian framework until very recently (Zhang, 2020;Ma et al, 2020;Hu et al, 2021;Geng and Hu, 2021).…”