Detection of outliers in mixed regressive-spatial autoregressive models

Jin, Libin; Dai, Xianhua; Shi, Anqi; Shi, Lei

doi:10.1080/03610926.2014.941493

Cited by 14 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There exist outliers for some outliers in the data. Here we have tried to accommodate outliers by building spatial panel model (Cerioli & Riani, 1999;Jin et al, 2015;Mastuti et al, 2019). However, we have run spatial panel regression eliminating some of the outliers.…”

Section: Econometric Analysis: Using Spatial Panel Data Regression Mo...mentioning

confidence: 99%

Determinants of Crime Against Women in India: A Spatial Panel Data Regression Analysis

2021

View full text Add to dashboard Cite

Gender discrimination has been an important socio-economic and cultural issue in Indian backdrop; though India is one of the fastest-growing nations in the world but she has ranked 108th (out of 144 countries) in 2016 on the global gender gap index. In order to explore the determinants of crimes (such as dowry death, rape, molestation and torture) in India, we consider 24 states and five time points (over 1995–2015). Rank correlation over time clearly suggests that states exhibiting higher incidence of molestation experience higher incidence of rape; we get similar results in case of torture and dowry death as well. We employ both global and local Moran’s indices for dowry death, which has the least reporting bias, and observe that space as well as neighbourhood effect does matter; on the contrary, we find that other types of crimes vary randomly. Specifically, spatial panel regression results on dowry death clearly show that space along with neighbourhood effect does matter towards variations of dowry death; only two variables namely female work force participation and police station significantly reduce the incidence of dowry death.

show abstract

Section: Econometric Analysis: Using Spatial Panel Data Regression Mo...mentioning

confidence: 99%

Determinants of Crime Against Women in India: A Spatial Panel Data Regression Analysis

2021

View full text Add to dashboard Cite

show abstract

“…We identify these influential observations using the proposed methodology in the previous sections to illustrate the efficiency of our results. The data generation models are similar to that of Jin et al (2015), which is given by…”

Section: Analysis Of Simulation Datamentioning

confidence: 99%

“…We assume that the spatial weight matrix W 1 = W 2 = W and W is generated based on the following setup (see Jin et al 2015):…”

Section: Analysis Of Simulation Datamentioning

confidence: 99%

Local influence analysis in general spatial models

et al. 2015

Self Cite

View full text Add to dashboard Cite

We study the local influence in the general spatial model which includes the spatial autoregressive model and the spatial error model as two special cases. The stepwise local influence procedure is employed in our diagnostic analysis. We derive the local diagnostic measures in the general spatial model under three perturbation schemes, namely, the variance perturbation, dependent variable perturbation and explanatory variable perturbation schemes. A simulation example and two realdata examples are analysed in detail and they show that the stepwise local influence analysis is effective in identifying influential observations and is a powerful tool for uncovering masking effects.

show abstract

“…Statistical diagnostics including the detection of outlier and influential observations for spatial econometric models have been paid attention recently. For example, Jin et al (2016) and Dai et al (2016) studied detection of outliers in the mixed regressive-spatial autoregressive models (SAR) and general spatial models, respectively. Dai et al (2016) proposed a local influence method to detecting influential observations in general spatial models.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Local Influence for Spatial Autoregressive Models with Heteroscedasticity

et al. 2017

Self Cite

View full text Add to dashboard Cite

This paper studies Bayesian local influence analysis for the spatial autoregressive models with heteroscedasticity (heteroscedastic SAR models). Two local diagnostic procedures using curvature-based and slope-based methods are proposed in the framework of Bayesian perspective. The curvature-based diagnostic are obtained by maximizing the normal curvature of an influence graph based on Kullback-Leibler divergence measure and slope-based diagnostic use the first order derivative of Bayesian factor defined for perturbation. Three perturbation schemes under the heteroscedastic SAR models are suggested and the diagnostic measures are derived respectively. The computations for the proposed diagnostic measures can be easily obtained using Markov Chain Monte Carlo sampler. The proposed methodologies are illustrated using two real examples.

show abstract

Detection of outliers in mixed regressive-spatial autoregressive models

Cited by 14 publications

References 11 publications

Determinants of Crime Against Women in India: A Spatial Panel Data Regression Analysis

Determinants of Crime Against Women in India: A Spatial Panel Data Regression Analysis

Local influence analysis in general spatial models

Bayesian Local Influence for Spatial Autoregressive Models with Heteroscedasticity

Contact Info

Product

Resources

About