I am a visiting scholar at UCSD political science department for Fall 2025 - Summer 2026 (sabbatical).
You can find my research on Google Scholar page .

Select Research

Missing Data and Causal Inference

• Melody Huang, Naijia Liu. 2026+ Missing Data in Confounders

  We propose a new estimator to deal with confounders missing at random, in observational causal inference settings.

• Naijia Liu, Sooahn Shin and Soichiro Yamauchi. 2026+ Synthetic Control Methods with Missing Pre-treatment Outcomes

  We decompose bias in synthetic control methods with missing control-unit data and develop a sensitivity tool for bias calibration.

Algorithms and LLMs

• Naijia Liu and Ze Han. 2026+ Measuring Ideological Bias in Large Language Models

  We conduct a large-scale experiment to measure ideological biases in major commercial large language models.

• Naijia Liu, Xinlan Emily Hu, Yasemin Savas, Brandon M. Stewart and et al. 2025 Short-term exposure to filter-bubble recommendation systems has limited polarization effects: Naturalistic experiments on YouTube PNAS

  Using an experimental design that mimics the YouTube interface, we demonstrate that presenting people with more partisan video recommendations has no detectable polarizing effects on users’ attitudes in the short term.

Text as Data

• Ze Han, Rory Truex and Naijia Liu. 2025 Word Association Test using Chinese data. Public Opinion Quarterly.

  We propose a new method for measuring public opinion in sensitive survey contexts and validate it using data from mainland China and Hong Kong.