Muutke küpsiste eelistusi

E-raamat: Association Graph and the Multigraph for Loglinear Models

Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 35,80 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

This practical guide teaches nonstatisticians how to analyze and interpret loglinear models using the multigraph

The Association Graph and the Multigraph for Loglinear Models will help students, particularly those studying the analysis of categorical data, to develop the ability to evaluate and unravel even the most complex loglinear models without heavy calculations or statistical software. This supplemental text reviews loglinear models, explains the association graph, and introduces the multigraph to students who may have little prior experience of graphical techniques, but have some familiarity with categorical variable modeling. The author presents logical step-by-step techniques from the point of view of the practitioner, focusing on how the technique is applied to contingency table data and how the results are interpreted.
About the Author vii
Series Editor's Introduction ix
1 Introduction
1(5)
2 Structures of Association
6(8)
2.1 Statistical Independence for Discrete Variables
6(1)
2.2 The Odds Ratio: Two-Way Tables
7(2)
2.3 The Odds Ratio: Three-Way Tables
9(3)
2.4 Model Fitting: Three-Way Tables
12(1)
2.5 Multi-Way Tables
13(1)
3 Loglinear Model Review
14(14)
3.1 Two-Way Contingency Table
14(3)
3.2 Three-Way Contingency Table
17(3)
3.3 Relationships Among the LLMs for a Three-Way Table
20(3)
3.4 LLM and Contingency Table Properties
23(3)
3.5 Multi-Way Tables
26(2)
4 Association Graphs for Loglinear Models
28(17)
4.1 Basic Graph Theory Principles
28(6)
4.2 Association Graphs for Three-Way Tables
34(3)
4.3 Association Graphs for Multi-Way Tables
37(4)
4.4 Decomposable LLMs
41(2)
4.5 Summary
43(2)
5 Collapsibility Conditions and the Association Graph
45(11)
5.1 Collapsing in a Three-Way Contingency Table
45(3)
5.2 The Collapsibility Theorem and the Association Graph
48(4)
5.3 Conclusion
52(4)
6 The Generator Multigraph
56(23)
6.1 Construction of the Multigraph
56(1)
6.2 Multigraphs for Three-Way Tables
56(2)
6.3 Multigraphs for Multi-Way Tables
58(3)
6.4 Maximum Spanning Trees
61(5)
6.5 Decomposability
66(4)
6.6 Factorization of Joint Probabilities for Decomposable LLMs
70(3)
6.7 Fundamental Conditional Independencies in Decomposable LLMs
73(6)
7 Fundamental Conditional Independencies for Nondecomposable Loglinear Models
79(11)
7.1 Edge Cutsets
79(4)
7.2 FCIs for Nondecomposable LLMs
83(5)
7.3 Collapsibility Conditions Using the Multigraph
88(1)
7.4 FCIs: Summary
88(2)
8 Conclusions and Additional Examples
90(23)
8.1 Comparison of the Association Graph and the Multigraph
90(4)
8.2 Additional Real-Data Examples
94(16)
8.3 Final Note
110(3)
Data Sets 113(2)
References 115(4)
Author Index 119(2)
Subject Index 121
Harry J. Khamis is a Professor in the Department of Mathematics & Statistics with a joint appointment in the Boonshoft School of Medicine at Wright State University, Dayton, Ohio.  He received his B.S. degree in mathematics at Santa Clara University, and he received his M.S. degree in mathematics (1976) and his Ph.D. degree in statistics (1980) at Virginia Tech.  He has been at Wright State University since 1980 except for teaching, research, and consulting visiting positions at Uppsala, Umeå, and Dalarna Universities in Sweden.  Dr. Khamis has been Director of the Statistical Consulting Center at Wright State University since 1993.  Specializing in statistical methodology, especially categorical response models, goodness of fit tests, and the Cox regression model, Dr. Khamis has 80 authored or coauthored publications.  In addition to teaching and research, Dr. Khamis also consults extensively with researchers at the university as well as clients external to the university.  Major external clients include Astra-Arcus Pharmaceuticals, B.F. Goodrich, Cancer Prevention Institute, Carnation Co., Center for Election Integrity, Clinical Research Consultants, Community Blood Center, Genentech Inc., Isolab Inc., Kunesh Eye Surgery Center, Mandal Diabetes Research Institute, Nestles, Pharmacia-Upjohn Pharmaceuticals, and Sifo Marketing Research.