Jiwoo Kim

Jiwoo Kim

Social scientist learning causal inference

Talks and presentations

Causal Approach for Careless Responding

July 23, 2026

Paper presentation, International Meeting of the Psychometric Society, Seoul, South Korea

In this study, I use a causal graphical framework to characterize careless-response generation mechanisms and distinguish them from detection and handling decisions. Similar observed response patterns can arise from different mechanisms, with different implications for whether responses should be retained, removed, or adjusted. Through simulations, I examine how imperfect detection and handling strategies that do not match the data-generating process contribute to bias. This work clarifies why removing respondents flagged as careless does not necessarily eliminate bias and provides a framework for evaluating the assumptions underlying common handling practices. This study was selected to receive the Psychometric Society Travel Award sponsored by ACS Ventures.

A Systematic Literature Review of Causal Mediation Analysis in Social Psychology

July 01, 2026

Paper presentation, European Association of Social Psychology General Meeting, Strasbourg, France

This study was presented by Felix Thoemmes. In this study, I systematically review the use of causal mediation analysis in social psychology, focusing on how researchers connect statistical analyses to claims about psychological mechanisms. I examine research designs, analytic approaches, and the assumptions needed to interpret mediation effects causally. By distinguishing statistical mediation from causal identification, this review evaluates how methodological practices support causal interpretations and highlights considerations for designing, analyzing, and reporting mediation studies in social psychology.

Graphical Criteria of Recoverability under Not Missing at Random Case

July 11, 2025

Paper presentation, International Conference on Education Research, Seoul, South Korea

In this study, I suggested a causal graphical approach using m-DAG to check the possible bias in either in intercept and slope under the list-wise deletion situation. By doing so, this paper proposes general criteria for identifying which parameters are recoverable without bias under NMAR. Also, using m-DAGs with distinct notations for conditioning and controlling, this paper clarifies mechanisms behind bias in NMAR models. This approach allows researchers to assess recoverability of means and slopes (e.g., treatment effects), even under listwise deletion.

Graphical Criteria of Recoverability under Not Missing at Random Case

May 15, 2025

Poster presentation, American Causal Inference Conference, Detroit, MI, USA

In this study, I suggested a causal graphical approach using m-DAG to check the possible bias in either in intercept and slope under the list-wise deletion situation. By doing so, this paper proposes general criteria for identifying which parameters are recoverable without bias under NMAR. Also, using m-DAGs with distinct notations for conditioning and controlling, this paper clarifies mechanisms behind bias in NMAR models. This approach allows researchers to assess recoverability of means and slopes (e.g., treatment effects), even under listwise deletion.

Development and Validation of the Pre-service Teacher Competency Scale in an Online Learning Environment using the Scenario Method

April 26, 2025

Paper presentation, American Educational Research Association, Denver, CO, USA

This study uses the scenario method to develop and validate a scale measuring pre-service teacher competency in an online learning environment. After conducting a comprehensive literature review, this study constructed seven competencies of pre-service teacher in online learning environments: design/planning competency, social competency, instructive competency, technological competency, management competency, positive teacher attitude competency, and learning competency. We developed the Pre-service Teacher Competency in Online Learning Environment scale with 11 scenarios and 34 items after revising and improving it based on a focus group interview with six pre-service teachers and five in-service teachers to review face and content validity. We conducted confirmatory factor analyses and reliability analyses with 579 pre-service teachers. As a result, the scale showed good construct validity and reliability.

Credible Evidence of Gender Discrimination Using Instrumental Inequality

May 15, 2024

Poster presentation, American Causal Inference Conference, Seattle, WA, USA

In this study, I suggested a new method to specify the existence of gender discrimination, using instrumental inequality. Causal graphical model was used to conceptualize the definition of gender discrimination.

Table 2 Fallacy in Latent Class Analysis

July 01, 2022

Poster presentation, 22nd International Conference on Educational Research (ICER), Seoul, Korea

This talk is about the possibility of table 2 fallacy in latent class analysis when putting multiple predictors for latent class.