Event Date Details:
Refreshments at 3:15 pm.
- Sobel Seminar Room; South Hall 5607F
Jiyoun Myung (UCSB)
Bayesian small area estimation
Small area models handling area level data typically assume normality of random effects and known sampling variances, even though they are estimated. We address small area estimation problems where additional data is provided to model the variance of error term in the area level model.
In this talk, the background of small area estimation from a Bayesian perspective is introduced, then we propose a new small area model with t random effect along with joint modeling of small area means and variances. The results of real data analysis and simulation will be presented.