Bayesian Estimation of an Over-identified Multi-equation Model in the Presence of Multicollinearity

Simple item page
dc.contributor.authorOkewole, Dorcas Modupe
dc.date.accessioned2022-10-10T15:56:45Z
dc.date.available2022-10-10T15:56:45Z
dc.date.issued2013
dc.description.abstractMulti-equation systems have wide applications in modeling Economic issues. The Bayesian approach received very little attention in the past but is now gaining popularity with extensive application to areas hitherto handled by the classical method. The increasing interest is as a result of availability of numerical intensive software capable of solving intractable or complex numerical integration and other mathematical or computational difficulties. Violations of the assumptions underlying the models often arise in actual observed data. Multicollinearily is one of such violations which several researches have shown classical estimation approaches to he sensitive to. Studies on the performance of the Bayesian approach to such violations are however limited. This paper presents a Monte Carlo study of the Bayesian approach to multi-equation models estimation in the presence of multicollinearity. The mean, bias and MSE were used to compare the performance of the Bayesian approach to that of some classical approaches. A number of research scenarios were specified depicting presence and absence of multicollinearity. MSE from the scenario representing absence of multicollinearity was smaller than that from the scenario representing presence of multicollinearity. Results from the Bayesian approach in run 1 (representing presence of multicollinearity) showed that MSE for fir(one of the correlated exogenous variables) are 0.2825, 0.1128, 0.1079 and 0.0649 for sample sizes 20, 40, 60 and 100 respectively, whereas, they were 0.2503, 0.0642, 0.0406 and 0.0414 in the absence of multicollinearity represented by run 2. MSE for fl„from the classical approach were 0.4230, 0.1583, 0,1498 and 0.0897 for sample sizes 20, 40, 60 and 100 respectively, whereas, they were 0.3639, 0.0837, 0.0517 and 0.0540 in run 2. MSE from the Bayesian approach were smaller than those from the classical approach. The results showed that the Bayesian approach is less sensitive to multicollinearity in estimating the coefficients of exogenous variables of over-identified model.en_US
dc.identifier.issn0331-9504
dc.identifier.urihttp://dspace.run.edu.ng:8080/jspui/handle/123456789/3679
dc.language.isoenen_US
dc.publisherJournal of the Nigerian Statistical Associationen_US
dc.relation.ispartofseriesVol 25;
dc.subjectMulti-equation modelen_US
dc.subjectBayesian approachen_US
dc.subjectMulticollinearityen_US
dc.subjectClassical approachen_US
dc.subjectMonte Carloen_US
dc.titleBayesian Estimation of an Over-identified Multi-equation Model in the Presence of Multicollinearityen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Bayesian Estimation of an Over-identified Multi-equation Model.pdf
Size:
3.59 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Department of Mathematical Sciences