Influence analysis of ranking data

Poon, Wai‐Yin; Chan, Wai

doi:10.1007/bf02294994

Cited by 5 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An influence analysis procedure of ranking data has been developed by Poon and Chan (2002). The building‐blocks of their influence measures are by‐products of the partition maximum likelihood estimation approach of Chan and Bentler (1998), and the measures are developed based on the method of Cook (1986).…”

Section: Discussionmentioning

confidence: 99%

“…Various perturbation schemes can be introduced to perturb a model under different contexts to obtain a comprehensive picture of an analysis. For ranking data, the observations are the frequencies of the n 0 distinct response patterns, and a common area of interest is to identify the influential response patterns through the minor perturbation of the frequencies of the patterns (Poon & Chan, 2002). For the factor analysis model, however, the perturbation of the parameters enables the identification of the parameters to which the model is sensitive (Lee & Wang, 1996; Poon et al , 1999).…”

Section: Local Influence Analysismentioning

confidence: 99%

“…Based on the first‐stage estimates and their covariance matrix, the second stage estimates the parameters that are involved in the covariance structure using the generalized least square method. The work of Poon and Chan (2002) focuses on the influence analysis of the first‐stage estimates by Chan and Bentler (1998), but has not addressed how influence analysis can be conducted for models with covariance structure. The influence analysis procedure proposed in this paper, on the other hand, is applicable to the factor analysis model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Influence analysis for the factor analysis model with ranking data

Poon

Lee

2008

Brit J Math & Statis

Self Cite

View full text Add to dashboard Cite

Influence analysis is an important component of data analysis, and the local influence approach has been widely applied to many statistical models to identify influential observations and assess minor model perturbations since the pioneering work of Cook (1986). The approach is often adopted to develop influence analysis procedures for factor analysis models with ranking data. However, as this well-known approach is based on the observed data likelihood, which involves multidimensional integrals, directly applying it to develop influence analysis procedures for the factor analysis models with ranking data is difficult. To address this difficulty, a Monte Carlo expectation and maximization algorithm (MCEM) is used to obtain the maximum-likelihood estimate of the model parameters, and measures for influence analysis on the basis of the conditional expectation of the complete data log likelihood at the E-step of the MCEM algorithm are then obtained. Very little additional computation is needed to compute the influence measures, because it is possible to make use of the by-products of the estimation procedure. Influence measures that are based on several typical perturbation schemes are discussed in detail, and the proposed method is illustrated with two real examples and an artificial example.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Local Influence Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Influence analysis for the factor analysis model with ranking data

Poon

Lee

2008

Brit J Math & Statis

Self Cite

View full text Add to dashboard Cite

show abstract

“…The issues of leniency and central tendency are well known in psychology: it is often observed that individuals have a tendency to place objects in the middle of the scale and to avoid extreme positions. Similar problems have also been studied by Poon and Chan (2002), Fligner and Verducci (1990), and Yu (2000). The mathematics of these methods has been described by Alvo and Yu (2014), Marden (1995), andCritchlow et al (1991).…”

Section: Introductionmentioning

confidence: 93%

A statistical approach to calibrating the scores of biased reviewers of scientific papers

Kuhlisch

Roos

Rothe

et al. 2015

Metrika

View full text Add to dashboard Cite

Peer reviewing is the key ingredient of evaluating the quality of scientific work. Based on the review scores assigned by individual reviewers to papers, program committees of conferences and journal editors decide which papers to accept for publication and which to reject. A similar procedure is part of the selection process of grant applications and, among other fields, in sports. It is well known that the reviewing process suffers from measurement errors due to a lack of agreement among multiple reviewers of the same paper. And if not all papers are reviewed by all reviewers, the naive approach of averaging the scores is biased. Several statistical methods are proposed for aggregating review scores, which all can be realized by standard statistical software. The simplest method uses the well-known fixed-effects two-way classification with identical variances, while a more advanced method assumes different variances. As alternatives a mixed linear model and a generalized linear model are employed. The application of these methods implies an evaluation of the reviewers, which may help to improve reviewing processes. An application example with real conference data shows the potential of these statistical methods.

show abstract

“…Typical examples are the applications to nonlinear mixed-effects models (Lee & Xu, 2004), growth curve models (Pan, Fang, & Liski, 1996), and principal component analysis (Shi, 1997), among others. At the same time, the local influence approach of Cook (1986) has also received a lot of attention in factor analysis or structural equation models (SEMs); see, for example, Tanaka and Odaka (1989), Lee and Wang (1996), Kwan and Fung (1998), Poon, Wang, and Lee (1999), Poon and Chan (2002), and Lee and Xu (2003a,b), and Song and Lee (2004a,b). However, as far as we know no local influence analysis for NSEMs has been developed, and it is very difficult to apply Cook's (1986) approach because the building blocks in its diagnostic measures involve intractable integrals that are induced by the nonlinearity among latent variables.…”

Section: Introductionmentioning

confidence: 99%