國立虎尾科技大學 |

Graphical models for categorical data

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Graphical models for categorical data/ Alberto Roverato.
作者:	Roverato, Alberto.
出版者:	Cambridge :Cambridge University Press, : 2017.,
面頁冊數:	vii, 152 p. :ill., digital ; : 24 cm.;
附註:	Title from publisher's bibliographic system (viewed on 29 May 2018).
標題:	Graphical modeling (Statistics) -
電子資源:	https://doi.org/10.1017/9781108277495
ISBN:	9781108277495

Graphical models for categorical data
Roverato, Alberto.

Graphical models for categorical data[electronic resource] /Alberto Roverato. - Cambridge :Cambridge University Press,2017. - vii, 152 p. :ill., digital ;24 cm. - SemStat elements. - Cambridge elements..

Title from publisher's bibliographic system (viewed on 29 May 2018).

Machine generated contents note:Introduction --1.

For advanced students of network data science, this compact account covers both well-established methodology and the theory of models recently introduced in the graphical model literature. It focuses on the discrete case where all variables involved are categorical and, in this context, it achieves a unified presentation of classical and recent results.

ISBN: 9781108277495Subjects--Topical Terms:

785858
Graphical modeling (Statistics)

LC Class. No.: QA279 / .R68 2017

Dewey Class. No.: 519.538

Graphical models for categorical data
LDR:03712nam a2200301 a 4500 001 1041065
003 UkCbUP
005 20180829142007.0
006 m d
007 cr nn 008maaau
008 211215s2017 enka o 1 0 eng d
020 $a 9781108277495 $q (electronic bk.)
020 $a 9781108404969 $q (paper)
020 $z 9781108404966
035 $a CR9781108277495
040 $a UkCbUP $b eng $c UkCbUP $d GP
041 0 $a eng
050 4 $a QA279 $b .R68 2017
082 0 4 $a 519.538 $2 23
090 $a QA279 $b .R873 2017
100 1 $a Roverato, Alberto. $3 1340145
245 1 0 $a Graphical models for categorical data $h [electronic resource] / $c Alberto Roverato.
260 $a Cambridge : $b Cambridge University Press, $c 2017.
300 $a vii, 152 p. : $b ill., digital ; $c 24 cm.
490 1 $a SemStat elements
490 1 $a Cambridge elements
500 $a Title from publisher's bibliographic system (viewed on 29 May 2018).
505 0 0 $a Machine generated contents note: $g 1. $t Introduction -- $g 1.1. $t Graphical Models -- $g 1.2. $t Outline of the Book -- $g 1.2.1. $t Discrete Graphical Models and Their Parameterization -- $g 1.2.2. $t Binary vs Non-binary Variables -- $g 2. $t Conditional Independence and Cross-product Ratios -- $g 2.1. $t Notation and Terminology -- $g 2.1.1. $t Cross-classified Tables -- $g 2.2. $t Conditional Independence -- $g 2.3. $t Establishing Independence Relationships -- $g 3. $t Mobius Inversion -- $g 3.1. $t Preliminaries -- $g 3.1.1. $t Notation and Terminology -- $g 3.1.2. $t The Zeta and the Mobius Matrices -- $g 3.2. $t The Mobius Inversion Formula -- $g 3.2.1. $t Two Basic Lemmas -- $g 3.3. $t Mobius Inversion and Partially Ordered Sets -- $g 4. $t Undirected Graph Models -- $g 4.1. $t Graphs -- $g 4.2. $t Markov Properties for Undirected Graphs -- $g 4.3. $t The Log-linear Parameterization -- $g 4.4. $t Hierarchical Log-linear Models -- $g 4.5. $t Log-linear Graphical Models -- $g 4.6. $t Data, Estimation and Testing -- $g 4.7. $t Graph Decomposition and Decomposable Graphs -- $g 4.8. $t Local Computation Properties -- $g 4.9. $t Models for Decomposable Graphs -- $g 4.10. $t Log-linear Models and the Exponential Family -- $g 4.10.1. $t Basic Facts on the Theory of the Exponential Family -- $g 4.10.2. $t The Cross-classified Bernoulli Distribution -- $g 4.10.3. $t Exponential Family Representations of the Saturated Model -- $g 4.10.4. $t Exponential Family Representation of Hierarchical Log-linear Models -- $g 4.11. $t Modular Structure of the Asymptotic Variance of ML Estimates -- $g 4.11.1. $t The Variance Function and the Asymptotic Variance of ML Estimates -- $g 4.11.2. $t Variances in the Saturated Model -- $g 4.11.3. $t Variances in Hierarchical Log-linear Models -- $g 4.11.4. $t Decompositions and Decomposable Models -- $g 5. $t Bidirected Graph Models -- $g 5.1. $t Bidirected Graphs -- $g 5.2. $t Markov Properties for Bidirected Graphs -- $g 5.3. $t The Log-mean Linear Parameterization -- $g 5.4. $t Log-mean Linear Graphical Models -- $g 5.5. $t Example: Symptoms in Psychiatric Patients -- $g 5.6. $t Parsimonious Graphical Modeling -- $g 6. $t Directed Acyclic and Regression Graph Models -- $g 6.1. $t Directed Acyclic Graphs -- $g 6.2. $t Markov Properties for Directed Acyclic Graphs -- $g 6.3. $t Regression Graphs -- $g 6.4. $t Markov Properties for Regression Graphs -- $g 6.5. $t On the Interpretation of Models defined by Regression Graphs -- $g 6.6. $t The Log-hybrid Linear Parameterization -- $g 6.7. $t Log-hybrid Linear Graphical Models -- $g 6.8. $t Inference in Regression Graph Models.
520 $a For advanced students of network data science, this compact account covers both well-established methodology and the theory of models recently introduced in the graphical model literature. It focuses on the discrete case where all variables involved are categorical and, in this context, it achieves a unified presentation of classical and recent results.
650 0 $a Graphical modeling (Statistics) $3 785858
830 0 $a Cambridge elements. $3 1294270
830 0 $a SemStat elements. $3 1340146
856 4 0 $u https://doi.org/10.1017/9781108277495