| 電子情報通信学会 研究会発表申込システム 講演論文 詳細 |
技報閲覧サービス [ログイン] 技報アーカイブ |
| トップに戻る | 前のページに戻る | [Japanese] / [English] |
| 講演抄録／キーワード | ||
| 講演名 | 2014-08-13 10:00 ［チュートリアル講演］Fitting linear mixed models using JAGS and Stan: A tutorial ○Shravan Vasishth・Tanner Sorensen（Univ. of Potsdam）  TL2014-28 |
|
| 抄録 | （和） | Psycholinguists routinely use linear mixed models (LMMs) for statistical inference. The most widely used tool for this purpose is the lmer function in the R library lme4. Although lmer has the advantage that models can be fit relatively quickly, one issue with this tool is that, when a full variance-covariance structure for variance components is defined, the model either fails to converge, or returns estimates of the correlation parameters that do not reflect the true underlying parameter values. LMMs fit using a Bayesian framework have several advantages over this conventional method: A full variance-covariance matrix for random effects can be defined even in cases where lmer would fail to converge or return nonsensical estimates; the underlying generative model can be flexibly changed; and, perhaps most importantly, a direct answer to the research question can be obtained by examining the posterior distribution given data. One major barrier to using Bayesian LMMs is that it is not obvious how to use the software available for Bayesian modeling. Although several good introductory books exist for Bayesian modeling in general, linear mixed modeling is typically treated in a fairly general way, and the more complex models that are used in psycholinguistics are usually not discussed. This tutorial provide a guide to allow researchers to quickly get started in fitting such models using the programming languages JAGS and Stan. |
| （英） | Psycholinguists routinely use linear mixed models (LMMs) for statistical inference. The most widely used tool for this purpose is the lmer function in the R library lme4. Although lmer has the advantage that models can be fit relatively quickly, one issue with this tool is that, when a full variance-covariance structure for variance components is defined, the model either fails to converge, or returns estimates of the correlation parameters that do not reflect the true underlying parameter values. LMMs fit using a Bayesian framework have several advantages over this conventional method: A full variance-covariance matrix for random effects can be defined even in cases where lmer would fail to converge or return nonsensical estimates; the underlying generative model can be flexibly changed; and, perhaps most importantly, a direct answer to the research question can be obtained by examining the posterior distribution given data. One major barrier to using Bayesian LMMs is that it is not obvious how to use the software available for Bayesian modeling. Although several good introductory books exist for Bayesian modeling in general, linear mixed modeling is typically treated in a fairly general way, and the more complex models that are used in psycholinguistics are usually not discussed. This tutorial provide a guide to allow researchers to quickly get started in fitting such models using the programming languages JAGS and Stan. |
|
| キーワード | （和） | Linear mixed models / Bayes Theorem / JAGS / Stan / / / / |
| （英） | Linear mixed models / Bayes Theorem / JAGS / Stan / / / / | |
| 文献情報 | 信学技報, vol. 114, no. 176, TL2014-28, pp. 95-96, 2014年8月. | |
| 資料番号 | TL2014-28 | |
| 発行日 | 2014-08-05 (TL) | |
| ISSN | Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 | |
| 著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します．(許諾番号：10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) | |
| PDFダウンロード | TL2014-28 |
|
| 研究会情報 | |
| 研究会 | TL |
| 開催期間 | 2014-08-12 - 2014-08-13 |
| 開催地（和） | 東京大学 駒場キャンパス １８号館ホール |
| 開催地（英） | The University of Tokyo (Komaba) 18 Bldg. Hall |
| テーマ（和） | 人間の言語の処理・学習 |
| テーマ（英） | Mental Architecture for Processing and Learning of Language |
| 講演論文情報の詳細 | |
| 申込み研究会 | TL |
| 会議コード | 2014-08-TL |
| 本文の言語 | 英語 |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | Fitting linear mixed models using JAGS and Stan: A tutorial |
| サブタイトル（英） | |
| キーワード(1)（和/英） | Linear mixed models / Linear mixed models |
| キーワード(2)（和/英） | Bayes Theorem / Bayes Theorem |
| キーワード(3)（和/英） | JAGS / JAGS |
| キーワード(4)（和/英） | Stan / Stan |
| キーワード(5)（和/英） | / |
| キーワード(6)（和/英） | / |
| キーワード(7)（和/英） | / |
| キーワード(8)（和/英） | / |
| 第1著者 氏名（和/英/ヨミ） | Shravan Vasishth / Shravan Vasishth / |
| 第1著者 所属（和/英） | University of Potsdam (略称： Univ. of Potsdam) University of Potsdam (略称： Univ. of Potsdam) |
| 第2著者 氏名（和/英/ヨミ） | Tanner Sorensen / Tanner Sorensen / |
| 第2著者 所属（和/英） | University of Potsdam (略称： Univ. of Potsdam) University of Potsdam (略称： Univ. of Potsdam) |
| 講演者 | 第1著者 |
| 発表日時 | 2014-08-13 10:00:00 |
| 発表時間 | 60分 |
| 申込先研究会 | TL |
| 資料番号 | TL2014-28 |
| 巻番号（vol） | vol.114 |
| 号番号（no） | no.176 |
| ページ範囲 | pp.95-96 |
| ページ数 | 2 |
| 発行日 | 2014-08-05 (TL) |
[研究会発表申込システムのトップページに戻る]