August 19, 2020

Selected to deliver the Gosset Lecture at WSC 2021

I was selected to deliver the 2021 World Statistics Congress (WSC) Gosset Lecture.

The William Sealy Gosset award is presented by ISBIS in recognition of outstanding statistical work that furthers the mission of ISBIS. Awarded to Bill Meeker in 2015, Vijay Nair in 2017, and David Banks in 2019.

(Screenshot from ISBIS News)

May 19, 2020

Elected as IMS Fellow

From today's press release (announcement on the IMS website and IMS bulletin):

Galit Shmueli, Tsing Hua Distinguished Professor, National Tsing Hua University, has been named Fellow of the Institute of Mathematical Statistics (IMS). Dr. Shmueli received the award for extraordinary contributions to statistical methods for biosurveillance, online commerce, and information quality, and for outstanding dissemination of statistical ideas through journal and textbook publications.

Each Fellow nominee is assessed by a committee of their peers for the award. In 2020, after reviewing 73 nominations, 35 were selected for Fellowship. Created in 1935, the Institute of Mathematical Statistics is a member organization that fosters the development and dissemination of the theory and applications of statistics and probability. The IMS has 3,500 active members throughout the world. Approximately 12% of the current IMS membership has earned the status of fellowship. 

I thank my nominator and letter writers!

May 17, 2020

New COM-Poisson paper pubished at JCGS

Our paper A Tree-Based Semi-Varying Coefficient Model for the COM-Poisson Distribution" is now published online at the Journal of Computational & Graphical Statistics. This was part of Suneel Chatla's PhD dissertation at NTHU (he is now faculty at UT El Paso).

In the paper, we propose a tree-based semi-varying coefficient model for the Conway–Maxwell–Poisson (CMP) distribution. The advantage of tree-based methods is their scalability to high-dimensional data. We develop CMPMOB, an estimation procedure for a semi-varying coefficient model, using model-based recursive partitioning (MOB). The proposed framework is broader than the existing MOB framework as it allows node-invariant effects to be included in the model. To simplify the computational burden of the exhaustive search employed in the original MOB algorithm, a new split point estimation procedure is proposed by borrowing tools from change point estimation methodology. The proposed method uses only the estimated score functions without fitting models for each split point and, therefore, is computationally simpler. Since the tree-based methods only provide a piece-wise constant approximation to the underlying smooth function, we further propose the CMPBoost semi-varying coefficient model which uses the gradient boosting procedure for estimation. The usefulness of the proposed methods are illustrated using simulation studies and a real example from a bike sharing system in Washington, DC.

This link gives 50 free copies to the paper.


May 14, 2020

Appointed as Inaugural EIC of INFORMS Journal on Data Science

"The INFORMS Board of Directors has voted unanimously to appoint Galit Shmueli as the inaugural editor of INFORMS’ newest journal, INFORMS Journal on Data Science (IJDS)."

See the full news announcement on the INFORMS website

March 3, 2020

[POSTPONED] Public talk in Melbourne: Behavioral Big Data and Healthcare Research


On March 23, 2020 I'll deliver a public talk on Behavioral Big Data and Healthcare Research in Melbourne, Australia, for the Australian Research Council Center of Excellence for Mathematical and Statistical Frontiers.

For more details and registration.