Background: Although depression is prevalent among Chinese international students (CIS), only 4% of CIS seek treatment. Behavioural activation (BA) has been suggested as a culturally sensitive treatment for depression that has the potential to meet the clinical needs of CIS. The current pilot study tested the feasibility, acceptability and themes for future cultural adaptations of a Chinese translated BA treatment (C‐BA) among CIS. Methods: Six CIS with elevated depressive symptoms (Beck Depression Inventory, BDI ≥ 14) completed a six‐session individual C‐BA treatment and assessments at pre‐ and post‐treatment and a 1‐month follow‐up. Primary outcome measures included treatment feasibility, acceptability and qualitative interview data informing future adaption of C‐BA. Exploratory analyses examined group changes in depressive symptoms over time and clinically significant symptom changes on individual levels. Results: All participants found the treatment to be highly feasible and culturally acceptable, and were highly engaged in the treatment. Themes of future cultural adaptions were generated from the qualitative interviews. Significant decreases in depressive symptoms were observed at a one1‐month post‐treatment follow‐up assessment. Conclusions: Preliminary evidence suggests that C‐BA has the potential to be a culturally sensitive treatment for depression among CIS. CIS demonstrated openness to psychotherapy and high treatment engagement.

Design‐based analysis, which accounts for the design features of the study, is commonly used to conduct data analysis in studies with complex survey sampling, such as the Hispanic Community Health Study/Study of Latinos (HCHS/SOL). In this type of longitudinal study, attrition has often been a problem. Although there have been various statistical approaches proposed to handle attrition, such as inverse probability weighting (IPW), non‐response cell weighting (NRCW), multiple imputation (MI), and full information maximum likelihood (FIML) approach, there has not been a systematic assessment of these methods to compare their performance in design‐based analyses. In this article, we perform extensive simulation studies and compare the performance of different missing data methods in linear and generalized linear population models, and under different missing data mechanism. We find that the design‐based analysis is able to produce valid estimation and statistical inference when the missing data are handled appropriately using IPW, NRCW, MI, or FIML approach under missing‐completely‐at‐random or missing‐at‐random missing mechanism and when the missingness model is correctly specified or over‐specified. We also illustrate the use of these methods using data from HCHS/SOL.