Johan Lim



I am a statistician working at Department of Statistics, Seoul National University from 2008. I am a member of MV Stat. Group at SNU. Before join SNU, I worked at Texas A&M University (2003-06) and Yonsei Univeristy (2006-07). Here is my resume.

Research

covariance matrix; fused lasso regression; hidden Markov models; high dimensional multivariate statistics; order related statistical Inference; ranked set sampling.

Contact

Office: Rm 434 at Bldg. 25.
Email: "johanlim at snu.ac.kr" or "yohanlim at gmail.com"
Phone: (02) 880-2625   Fax: (02) 883-6144.

Teaching (2024-Spring)

Desing of Experiment (under), Applied Statistics (grad)

Selected Papers   (complete list)


Hidden Variable Models and Their Applications. (2003) Ph.D. Dissertation, Department of Statistics , Stanford University. (Advisors : Prof. Dembo and Prof. Lai)

Concomitant of Multivariate order statistics with application to judgment post-stratification. (2006) with Wang, X. and Stokes, L. and Chen, M. JASA , 101, 1693-1704.

Forming post-strata via Bayesian treed capture-recapture model. (2006) with Wang, X. and Stokes, L. Biometrika , 93, 861-876.

A nonparametric mean estimator for judgment post-stratified data (2008) with X. Wang and L. Stokes. Biometrics , 64, 355-363.

Estimation of stochastically ordered survival functions by geometric programming. (2009) with Kim, SJ and Wang, X. JCGS, 18(4), 978-994. Supplementary Materials

Covariance adjustemnt in Gaussian mixture compressed domain for noisy image segmentation. (2009) with Pyun K.S. and Gray, R.M. IEEE-TIP., 18, 1385-1394

Regularizing sample estimates of covariance matrices by condition number. (2013) with Won, J.H., Kim, S.J., and Rajaratnam, B. JRSS-B, 75, 427-450.

High-dimensional fused lasso regression using majorization-minimization and parallel processing (2015). with Yu. D. et al. JCGS, 24(1), 121-153.

Asymptotically efficient parameter estimation in hidden Markov spatio-temporal random fields. (2015) with T.Lai. Statistica Sinica, 25, 403-425.

Using ranked set sampling with clustered randomized designs for improved inference on treatment effects. (2016) with X. Wang and L. Stokes, JASA, 111, 1576-1590.

Large-scale structured sparsity via parallel fused lasso on multiple GPU. (2017) with Lee,T. et al., JCGS, 26(4), 851-864.

Fixed support positive-definite modification of covariance matrix estimators via linear shrinkage. (2019) with Choi, Y-G. et al. JMVA,171, 234-249.

Estimating high-dimensional covariance and precision matrices under general missing dependence (2021) with Park, S.O. and Wang, X. Electronic Journal of Statistics, 15 (2), 4868-4915

Multiple testing of one-sided hypotheses under general dependence (2023) with Cho, S-H et al.

Bayesian multiple instance classification based on hierarchical probit regression. (2024) with Xiong. D., Park, S-O, Wang, X. et al. AOAS

New scheme of empirical likelihood method for ranked set sampling: Applications to two one sample problems. (2024) with Ahn, S et al.

l1-norm based Bayesian multivariate IRT model (2024) with Shin, S. and Park, J-H.

Linear shrinkage convexification of penalized linear regression with missing data (2024) with Park, S-O et al.

Talks   (complete list)

l1-ideal point estimation   ECOSTAT 2024, June, 2024, Beijing, China.

Prof. Lai's memorial session at ENAR   ENAR, Mar, 2024, Baltimore, USA.

Data Valuation   KFA and FISA joint symposium, June, 2023, Seoul.

PDness of High Dimensional Covariance Matrix Estimation, BK seminar, Yonsei Univ., July, 2023.

Bayesian IRT for ideal point estimation, ISI-WSC 2023, July, Ottawa, CA.

High dimensional regression, Ecosta 2023, Aug. 2023, Tokyo, Japan.

Links
MV Stat. Group at SNU   Statistics, SNU.   Korean. Stat. Soc.   MySNU   Teaching ETL   Korean Research Foundation   Stat. Journal