Avoiding Boundary Estimates in Hierarchical Linear Models through Weakly Informative Priors [electronic resource] / Yeojin Chung, Sophia Rabe-Hesketh and Andrew Gelman.

Hierarchical or multilevel linear models are widely used for longitudinal or cross-sectional data on students nested in classes and schools, and are particularly important for estimating treatment effects in cluster-randomized trials, multi-site trials, and meta-analyses. The models can allow for va...

Full description

Saved in:
Bibliographic Details
Online Access: Full Text (via ERIC)
Main Authors: Chung, Yeojin, Rabe-Hesketh, S. (Author), Gelman, Andrew (Author), Dorie, Vincent (Author), Liu, Jinchen (Author)
Corporate Author: Society for Research on Educational Effectiveness
Format: Electronic eBook
Language:English
Published: [S.l.] : Distributed by ERIC Clearinghouse, 2012.
Subjects:

MARC

LEADER 00000cam a22000002u 4500
001 b7136649
003 CoU
005 20130204175445.8
006 m o d f
007 cr |||||||||||
008 120101s2012 xx |||| ot ||| | eng d
035 |a (ERIC)ed530566 
035 |a (MvI) 5E000000512438 
040 |a ericd  |c MvI  |d MvI 
099 |a ED530566 
099 |a ED530566 
100 1 |a Chung, Yeojin. 
245 1 0 |a Avoiding Boundary Estimates in Hierarchical Linear Models through Weakly Informative Priors  |h [electronic resource] /  |c Yeojin Chung, Sophia Rabe-Hesketh and Andrew Gelman. 
260 |a [S.l.] :  |b Distributed by ERIC Clearinghouse,  |c 2012. 
300 |a 5 p. 
500 |a Availability: Society for Research on Educational Effectiveness. 2040 Sheridan Road, Evanston, IL 60208. Tel: 202-495-0920; Fax: 202-640-4401; e-mail: inquiries@sree.org; Web site: http://www.sree.org.  |5 ericd. 
500 |a Abstractor: ERIC.  |5 ericd. 
516 |a Text (Reports, Evaluative) 
520 |a Hierarchical or multilevel linear models are widely used for longitudinal or cross-sectional data on students nested in classes and schools, and are particularly important for estimating treatment effects in cluster-randomized trials, multi-site trials, and meta-analyses. The models can allow for variation in treatment effects, as well as examination of the reasons for treatment effect variation. In this paper the authors propose a method that pulls the group-level standard deviation estimate off the boundary while producing estimates that are consistent with the data. The idea is to specify a weakly informative prior distribution for the standard deviation and to maximize the resulting posterior distribution, a method that can also be viewed as penalized maximum likelihood estimation. 
524 |a Society for Research on Educational Effectiveness.  |2 ericd. 
650 0 7 |a Statistical Analysis.  |2 ericd. 
650 0 7 |a Models.  |2 ericd. 
650 0 7 |a Computation.  |2 ericd. 
650 0 7 |a Maximum Likelihood Statistics.  |2 ericd. 
650 0 7 |a Bayesian Statistics.  |2 ericd. 
700 1 |a Rabe-Hesketh, S.,  |e author. 
700 1 |a Gelman, Andrew,  |e author. 
700 1 |a Dorie, Vincent,  |e author. 
700 1 |a Liu, Jinchen,  |e author. 
710 2 |a Society for Research on Educational Effectiveness. 
856 4 0 |u http://files.eric.ed.gov/fulltext/ED530566.pdf  |z Full Text (via ERIC) 
907 |a .b71366490  |b 07-06-22  |c 08-12-12 
998 |a web  |b 08-12-12  |c f  |d m   |e -  |f eng  |g xx   |h 0  |i 1 
956 |a ERIC 
999 f f |i f1cb7e93-fc08-5832-93a8-703ffd8f111c  |s 0b2f2557-ff90-5726-b43a-f1774041988a 
952 f f |p Can circulate  |a University of Colorado Boulder  |b Online  |c Online  |d Online  |e ED530566  |h Other scheme  |i web  |n 1