Jiahua Chen Suggested Stat548 Papers for 2025.


Professor Chen’s Research and Supervision

Professor Chen is actively engaged in research areas such as finite mixture models, empirical likelihood, and methods for addressing missing data in sample surveys. He has recently supervised one PhD and one MSc student to completion. He is open to supervising one new PhD student who demonstrates strong technical skills, resilience, and a genuine commitment to hard work.

Candidates interested in joining Professor Chen’s research group should have a solid grasp of statistical theory and its mathematical foundations. A critical perspective on the significance and limitations of existing research, along with the ability to draw meaningful insights, is essential.

Professor Chen recognizes that not every student pursues a PhD in statistics out of pure passion. Nevertheless, he expects his students to be fully committed to their academic journey and to maintain a high level of engagement throughout their studies. Known for giving straightforward feedback, he does not hesitate to provide candid critiques of both research quality and work ethic. Prospective students should be prepared to accept this feedback constructively, focusing on its substance rather than its tone.

Stat 548 Course Project

Professor Chen will provide two papers for students enrolled in Stat 548 who wish to undertake one of five projects under his supervision. To achieve a high grade, students must demonstrate deep expertise in a specific technical aspect of their chosen paper while also showing a comprehensive understanding of the broader context.

While reproducing the key theoretical derivations is expected, students are encouraged to approach the material in their own way. This may include omitting routine but lengthy algebraic steps, assuming intermediate results without detailed proofs, and concentrating on the essential aspects of the paper. A key part of this exercise is learning to identify what is most important, rather than relying on explicit guidance from the supervisor.

A published research paper typically reflects the collaborative efforts of multiple experts and often contains material that requires a broad research background for full comprehension. As a course project, students are advised to selectively focus on one key contribution of the paper rather than attempting to cover every detail.

Professor Chen expects the project report to clearly address the following points:

Students should support their evaluations with concrete evidence—such as technical proofs, simulation experiments, or real data examples—though not necessarily all. Focus on thoroughly understanding and clearly explaining one specific aspect of the paper rather than attempting to cover everything.

In terms of methodology, students are encouraged to develop both concrete and hypothetical scenarios to critically assess the effectiveness of the methods. The report should clearly explain the rationale behind each scenario and outline the insights expected from the resulting simulations.

Plan to complete your report within 1.5 months. Begin by reading the selected paper and noting your initial impressions. Then, create an outline highlighting the topics and level of detail you intend to cover. We can then review your plan together to ensure it is feasible, meaningful, and fits within your available time.




You may obtain a general picture of my research activities in the following google scholar site:
Publications and citations



Recommendations



Nearest Neightbor Imputation for Survey Data. Jiahua Chen and Jun Shao (Journal of Official Statistics, V16, 2000 pp113-1310.


Nearest neighbor imputation is one of the hot deck methods used to compensate for nonresponse in sample surveys. Although it has a long history of application, few theoretical properties of the nearest neighbor imputation method are known prior to the current article. We show that under some conditions, the nearest neighbor imputation method provides asymptotically unbiased and consistent estimators of functions of population means (or totals), population distributions, and population quantiles. We also derive the asymptotic variances for estimators based on nearest neighbor imputation and consistent estimators of these asymptotic variances. Some simulation results show that the estimators based on nearest neighbor imputation and the proposed variance estimators have good performances.

Download the paper from the link provided by google scholar.


Testing homogeneity in a multivariate mixture model
Xiaoqing Niu, Pengfei Li, Peng Zhang. The Canadian Journal of Statistics, 39. 218--238.


Testing homogeneity is a fundamental problem in finite mixture models. It has been investigated by many researchers and most of the existing works have focused on the univariate case. In this article, the authors extend the use of the EM--test for testing homogeneity to multivariate mixture models. They show that the EM--test statistic asymptotically has the same distribution as a certain transformation of a single multivariate normal vector. On the basis of this result, they suggest a resampling procedure to approximate the P--value of the EM--test. Simulation studies show that the EM--test has accurate type I errors and adequate power, and is more powerful and computationally efficient than the bootstrap likelihood ratio test. Two real data sets are analysed to illustrate the application of our theoretical results.
Download the paper from the link provided by google scholar.