[Forum SIS] Unimi seminar

[Francesca De Battisti]

Date and time: July3rd, 2018, 12PM 

  

Venue: SeminarRoom, DEMM, via Conservatorio 7, Milano 

  

Presenter: AhmedAlsayed, DEMM, University of Milan 

  

Title:  

Robust estimationand outliers detection with environmental application  

  

Abstract: 

Research on theeffects of energy consumption and economic growth on carbon dioxide (CO2)emissions has received much effort due to the global environmental issue andthe greenhouse effect. Different methods have been used to explain therelationship but the results are conflicting due to the efficiency of thestatistical method. The objective of this experimental study is to model therelationship between CO2, energy consumption and economic growth usingdifferent robust estimators (M, Median, S, and MM-estimator) against OLSestimator in the presence of different types of outliers in the panel data. Themodels are evaluated by using out-of-sample forecasting approach. The paneldata include 20 developing countries. The duration is from 1960 to 2008, whichis split into two sub-periods. The first period is from (1960-2000) which isused to estimate the out-of-sample forecasting models, while the second period(2001-2008) is used to evaluate the performance of the estimated out-of-sampleforecasting models. The findings support that the robust estimators appeared tohave better properties than OLS estimator when the dataset include outliers.The MM-estimator is the best robust estimator could fit the dataset in thepresence of outliers in this study.  
<signatureafterquotedtext>




***********************************************************
Francesca De Battisti
Dipartimento di Economia, Management e Metodi Quantitativi 
(III piano, studio n. 29)
Via Conservatorio 7
20122 - Milano
Tel: 02.50321464
Fax: 02.50321505
***********************************************************</signatureafterquotedtext>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20180621/f69bb73f/attachment.html>