Yeojin Chung

Kookmin University

9Publications

4H-index

170Citations

Publications 9

Newest

#1Yeojin Chung (Kookmin University)H-Index: 4

#1Yeojin Chung (Kookmin University)H-Index: 4

#2Andrew Gelman (Columbia University)H-Index: 79

Last.Vincent Dorie (NYU: New York University)H-Index: 6

view all 5 authors...

When fitting hierarchical regression models, maximum likelihood (ML) estimation has computational (and, for some users, philosophical) advantages compared to full Bayesian inference, but when the number of groups is small, estimates of the covariance matrix (I£) of group-level varying coefficients are often degenerate. One can do better, even from a purely point estimation perspective, by using a prior distribution or penalty function. In this article, we use Bayes modal estimation to obtain pos...

#1Yeojin Chung (Kookmin University)H-Index: 4

#2Bruce G. Lindsay (PSU: Pennsylvania State University)H-Index: 34

Beyond the expectation–maximization (EM) algorithm for vector parameters, the EM for an unknown distribution function is often used in mixture models, density estimation, and signal recovery problems. We prove the convergence of the EM in functional spaces and show the EM likelihoods in this space converge to the global maximum.

#1Yeojin Chung (Kookmin University)H-Index: 4

#2Sophia Rabe-Hesketh (University of California, Berkeley)H-Index: 55

Last.In-Hee Choi (University of California, Berkeley)H-Index: 1

view all 3 authors...

Fixed-effects meta-analysis has been criticized because the assumption of homogeneity is often unrealistic and can result in underestimation of parameter uncertainty. Random-effects meta-analysis and meta-regression are therefore typically used to accommodate explained and unexplained between-study variability. However, it is not unusual to obtain a boundary estimate of zero for the (residual) between-study standard deviation, resulting in fixed-effects estimates of the other parameters and thei...

#1Yeojin Chung (Kookmin University)H-Index: 4

#2Sophia Rabe-Hesketh (University of California, Berkeley)H-Index: 55

Last.Jingchen Liu (Columbia University)H-Index: 14

view all 5 authors...

Group-level variance estimates of zero often arise when fitting multilevel or hierarchical linear models, especially when the number of groups is small. For situations where zero variances are implausible a priori, we propose a maximum penalized likelihood approach to avoid such boundary estimates. This approach is equivalent to estimating variance parameters by their posterior mode, given a weakly informative prior distribution. By choosing the penalty from the log-gamma family with shape param...

#1Yeojin ChungH-Index: 4

#2Sophia Rabe-HeskethH-Index: 55

Last.Jinchen Liu

view all 5 authors...

#1Yeojin ChungH-Index: 4

#2Sophia Rabe-Hesketh (University of California, Berkeley)H-Index: 55

Last.Vincent Dorie (Columbia University)H-Index: 6

view all 5 authors...

Variance parameters in mixed or multilevel models can be difficult to estimate, especially when the number of groups is small. Here we address the problem that the group-level variance estimate is often on the boundary. We propose a maximum penalized likelihood approach which is equivalent to estimating the variance by its marginal posterior mode, given a weakly informative prior distribution. By choosing the prior from the gamma family with at least 1 degree of freedom, we ensure that the prior...

#2Yeojin ChungH-Index: 4

Last.Jinchen Liu

view all 5 authors...

1