Generalized endpoint-inflated binomial model

Tian, Guo‐Liang; Ma, Huijuan; Zhou, Yong; Deng, Dianliang

doi:10.1016/j.csda.2015.03.009

Cited by 14 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To assess the influence of covariates, we employ both our proposed GLB model and the generalized EIB model to analyze the whitefly data. To facilitate a comparative analysis with the generalized EIB model by [23], we incorporate the following covariates: The EM algorithm's computational procedures outlined in Section 3.2 are utilized to compute the MLEs of the regression coefficients. The results of the regression for both the GLB and EIB models are summarized in Table 8.…”

Section: Likelihood-based Analysis With Glb Regression Modelmentioning

confidence: 99%

See 1 more Smart Citation

Modelling the proportions with excessive endpoints based on a generalized Lindley binomial model

Deng,

Zhang

2024

Preprint

View full text Add to dashboard Cite

This paper presents the generalized Lindley binomial (GLB) distribution, a novel probability distribution designed for the analysis of proportional data with excessive endpoints. The study delves into the probabilistic characteristics of the GLB distribution, including the probability mass function and the rth factorial moment function. Estimation of the distribution parameters in the GLB model, both with and without covariates, is addressed using the Fisher scoring algorithm and the EM algorithm. Furthermore, the paper explores techniques for model diagnosis and evaluates the goodness of fit for the proposed GLB model. To illustrate the performance of the derived EM algorithms in parameter estimation, a limited simulation study is conducted for both cases, with and without covariates, in the GLB model. The practical application of the proposed Lindley binomial regression model is demonstrated using the whitefly dataset.

show abstract

Section: Likelihood-based Analysis With Glb Regression Modelmentioning

confidence: 99%

“…Deng and Zhang [3] explored the zero-one inflated binomial (ZOIB) model to fit proportions with both zero and denominator inflations. Tian et al [23] renamed the ZOIB model as the endpoint-inflated binomial (EIB) model, delving into additional properties and applications.…”

Section: Introductionmentioning

confidence: 99%

Modelling the proportions with excessive endpoints based on a generalized Lindley binomial model

Deng,

Zhang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The primary outcome was the number of surviving whiteflies measured 2 days later, and was analyzed using ZIB models (Hall, 2000) or zero‐inflated overdispersed binomial models (Hall & Berenhaut, 2002) due to the upper bound of the count data. Tian, Ma, Zhou, and Deng (2015) also proposed a generalized endpoint‐inflated binomial model due to the excessive zeros and right endpoints the data exhibit.…”

Section: Case Studiesmentioning

confidence: 99%

Testing inflated zeros in binomial regression models

Tang

Sun

et al. 2020

Biometrical J

View full text Add to dashboard Cite

Binomial regression models are commonly applied to proportion data such as those relating to the mortality and infection rates of diseases. However, it is often the case that the responses may exhibit excessive zeros; in such cases a zero‐inflated binomial (ZIB) regression model can be applied instead. In practice, it is essential to test if there are excessive zeros in the outcome to help choose an appropriate model. The binomial models can yield biased inference if there are excessive zeros, while ZIB models may be unnecessarily complex and hard to interpret, and even face convergence issues, if there are no excessive zeros. In this paper, we develop a new test for testing zero inflation in binomial regression models by directly comparing the amount of observed zeros with what would be expected under the binomial regression model. A closed form of the test statistic, as well as the asymptotic properties of the test, is derived based on estimating equations. Our systematic simulation studies show that the new test performs very well in most cases, and outperforms the classical Wald, likelihood ratio, and score tests, especially in controlling type I errors. Two real data examples are also included for illustrative purpose.

show abstract

“…Therefore, H 0 is accepted, thereby validating equation ( 25). This is depicted by the binomial distribution diagram (Tian et al, 2015;Liu and Hong, 2015) [Figure 9(a)].…”

Section: Linear Regressionmentioning

confidence: 99%

Empirical relation for broken bar determination in SCIM

Sinha

Das

Chatterjee

2018

COMPEL

View full text Add to dashboard Cite

Purpose Condition monitoring of squirrel cage induction motors (SCIMs) is indispensible for achieving fault-free working environment. As broken rotor bars (BRBs) are one of the more frequent faults in a SCIM especially where direct-on-line starting is indispensible, as in underground mines, a priori knowledge of fault severity in terms of the number of BRBs assists in effective fault monitoring. In this regard, this paper aims to propose a unique empirical relation to facilitate the determination of number of BRB. Design/methodology/approach Fast Fourier transform is used to obtain fault sideband amplitudes under varying number of BRBs and load torque for 5.5 kW, 7.5 kW, 10 kW, three-phase, 415 V, 50 Hz SCIMs in MATLAB/Simulink. The nature of variation is decided by an appropriate curve fitting technique for comprehending a unique empirical relation. The proposed empirical relation is validated by bootstrapping and z-test. Furthermore, hardware validation is done using 1 kW laboratory prototype with Labview interface. Findings The analytical study reveals the dependence of lower and upper sideband amplitudes on the number of BRBs, load torque and machine rating. Therefore, fault severity in terms of number of BRBs is accurately calculated using the proposed empirical relation if load torque, machine rating and amplitudes of lower and upper sidebands are known. Originality/value The unique empirical relation proposed in the present work provides accurate knowledge of fault severity in terms of the number of BRBs. This facilitates maintenance scheduling which shall reduce effective downtime and improve production.

show abstract

Generalized endpoint-inflated binomial model

Cited by 14 publications

References 21 publications

Modelling the proportions with excessive endpoints based on a generalized Lindley binomial model

Modelling the proportions with excessive endpoints based on a generalized Lindley binomial model

Testing inflated zeros in binomial regression models

Empirical relation for broken bar determination in SCIM

Contact Info

Product

Resources

About