The Box-Cox Transformation and Non-Iterative Estimation Methods For Ordinal Log-Linear Models

Eric J. Beh; Thomas B Farver

doi:10.1111/anzs.12007

The Box-Cox Transformation and Non-Iterative Estimation Methods For Ordinal Log-Linear Models

Eric J. Beh, Thomas B Farver

Population Health and Reproduction

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Recently Beh and Farver investigated and evaluated three non-iterative procedures for estimating the linear-by-linear parameter of an ordinal log-linear model. The study demonstrated that these non-iterative techniques provide estimates that are, for most types of contingency tables, statistically indistinguishable from estimates from Newton's unidimensional algorithm. Here we show how two of these techniques are related using the Box-Cox transformation. We also show that by using this transformation, accurate non-iterative estimates are achievable even when a contingency table contains sampling zeros.

Original language	English (US)
Pages (from-to)	475-484
Number of pages	10
Journal	Australian and New Zealand Journal of Statistics
Volume	54
Issue number	4
DOIs	https://doi.org/10.1111/anzs.12007
State	Published - Dec 2012

Keywords

Box-Cox transformation
Linear-by-linear association
Newton's unidimensional method
Ordinal log-linear model

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1111/anzs.12007

Fingerprint Dive into the research topics of 'The Box-Cox Transformation and Non-Iterative Estimation Methods For Ordinal Log-Linear Models'. Together they form a unique fingerprint.

Cite this

@article{bf450766fe8e4ae49f019aac1caccd7e,

title = "The Box-Cox Transformation and Non-Iterative Estimation Methods For Ordinal Log-Linear Models",

abstract = "Recently Beh and Farver investigated and evaluated three non-iterative procedures for estimating the linear-by-linear parameter of an ordinal log-linear model. The study demonstrated that these non-iterative techniques provide estimates that are, for most types of contingency tables, statistically indistinguishable from estimates from Newton's unidimensional algorithm. Here we show how two of these techniques are related using the Box-Cox transformation. We also show that by using this transformation, accurate non-iterative estimates are achievable even when a contingency table contains sampling zeros.",

keywords = "Box-Cox transformation, Linear-by-linear association, Newton's unidimensional method, Ordinal log-linear model",

author = "Beh, {Eric J.} and Farver, {Thomas B}",

year = "2012",

month = dec,

doi = "10.1111/anzs.12007",

language = "English (US)",

volume = "54",

pages = "475--484",

journal = "Australian and New Zealand Journal of Statistics",

issn = "1369-1473",

publisher = "Wiley-Blackwell",

number = "4",

}

TY - JOUR

T1 - The Box-Cox Transformation and Non-Iterative Estimation Methods For Ordinal Log-Linear Models

AU - Beh, Eric J.

AU - Farver, Thomas B

PY - 2012/12

Y1 - 2012/12

N2 - Recently Beh and Farver investigated and evaluated three non-iterative procedures for estimating the linear-by-linear parameter of an ordinal log-linear model. The study demonstrated that these non-iterative techniques provide estimates that are, for most types of contingency tables, statistically indistinguishable from estimates from Newton's unidimensional algorithm. Here we show how two of these techniques are related using the Box-Cox transformation. We also show that by using this transformation, accurate non-iterative estimates are achievable even when a contingency table contains sampling zeros.

AB - Recently Beh and Farver investigated and evaluated three non-iterative procedures for estimating the linear-by-linear parameter of an ordinal log-linear model. The study demonstrated that these non-iterative techniques provide estimates that are, for most types of contingency tables, statistically indistinguishable from estimates from Newton's unidimensional algorithm. Here we show how two of these techniques are related using the Box-Cox transformation. We also show that by using this transformation, accurate non-iterative estimates are achievable even when a contingency table contains sampling zeros.

KW - Box-Cox transformation

KW - Linear-by-linear association

KW - Newton's unidimensional method

KW - Ordinal log-linear model

UR - http://www.scopus.com/inward/record.url?scp=84872706561&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872706561&partnerID=8YFLogxK

U2 - 10.1111/anzs.12007

DO - 10.1111/anzs.12007

M3 - Article

AN - SCOPUS:84872706561

VL - 54

SP - 475

EP - 484

JO - Australian and New Zealand Journal of Statistics

JF - Australian and New Zealand Journal of Statistics

SN - 1369-1473

IS - 4

ER -