Open Access Open Access  Restricted Access Subscription or Fee Access

Outliers Detection Methods in Panel Data Regression: An Application to Environment Science

Ahmed R. M. Al Sayed, Zaidi Isa, Sek Siok Kun

Abstract


The existence of outliers in panel data may violate the assumption of classical OLS estimator. They may lead to misestimating the relationship between variables. The main objective of this study is to detect the outliers, leverages and the influence points by using different diagnostic methods. The other objective is to measure the effects of outliers on OLS estimator by comparing the results of using the sample with outliers and the samples after removing the outliers. The analyses are applied to the environmental science data on modelling the relationship between CO2 emissions, energy consumption and economic growth for two groups of countries, i.e. the developed versus the developing countries. The data take the range between1960 to 2010. Our results reveal that the Robust Mahalanobis distance method outperforms the other methods in identifying the outliers as it uses the robust mean and robust variance estimation. Besides, the estimated model after excluding the outliers from the analysis could provide a more accurate estimation. Comparing the results between two groups of countries, our results show that developing countries group has lower CO2 emissions by 0.80 unit in compare to the developed countries group.

Keywords


Outlier detection, Robust Mahalanobis distance, CO2 emissions.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.