A Box-Cox semiparametric multiplicative error model
Xuehai Zhang (xuehai@mail.uni-paderborn.de)
Additional contact information
Xuehai Zhang: Paderborn University
No 125, Working Papers CIE from Paderborn University, CIE Center for International Economics
Abstract:
A general class of SemiMEM (semiparametric multiplicative error) models is proposed by introducing a scale function into a MEM (multiplicative error) class model to analyze the non-negative observations. The estimation of the scale function is not limited by any parametric models specification and the moments condition is also reduced via the Box- Cox transformation. For the purpose, an equivalent scale function is applied in a local linear approach and converted to the scale function under weak moment conditions. The equivalent scale function estimation and the bandwidth, the constant factor in the asymp- totic variance and the power transformation parameters estimation are proposed based on the iterative plug-in (IPI) algorithms. In the power transformation estimation, the maximum likelihood estimation (MLE), the normality test and the the quantile-quantile regression (QQr) are employed and simulation algorithms for the confidence interval of estimated power transformation parameter are also developed by the block bootstrap method. The algorithms fit the selected real data well.
Pages: 34 pages
Date: 2019-08
References: Add references at CitEc
Citations: View citations in EconPapers (2)
Downloads: (external link)
http://groups.uni-paderborn.de/wp-wiwi/RePEc/pdf/ciepap/WP125.pdf (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:pdn:ciepap:125
Access Statistics for this paper
More papers in Working Papers CIE from Paderborn University, CIE Center for International Economics Contact information at EDIRC.
Bibliographic data for series maintained by WP-WiWi-Info (sarahf@mail.upb.de this e-mail address is bad, please contact repec@repec.org) and (sebastian.letmathe@uni-paderborn.de this e-mail address is bad, please contact repec@repec.org).