Statistical modeling of enamel rater value data

Takafumi Isogai, Hiroaki Uchida, Susumu Miyama and Sadao Nishiyama

Journal of Applied Statistics, 2008, vol. 35, issue 5, 515-535

Abstract: Enamel rater value (shortly, ERV) of a quick stress test is usually used to evaluate the integrity of an organic coating for the inside of an aluminum (denoted by Al shortly) can. A large positive value of ERV is supposed to indicate the degree of imperfect coating coverage, i.e. the size of an exposed Al area. An Al can filled with some drink, if there is an exposed Al area due to imperfect coating coverage, has Al dissolution brought by corrosion. Thus a smaller value of ERV is desirable to prevent Al dissolution. However, quantitative evaluations of ERV data as well as an accumulated quantity of Al dissolution have never been published, because ERV is involved in complicated anode dissolution of an exposed Al area. Recently our experimental study has found out a relationship between ERV and sizes of exposed Al areas. This relationship enables us to construct a descriptive statistical model for ERV data as well as to evaluate coating effects for Al cans. Furthermore, empirical implications suggest that an instantaneous quantity of Al dissolution is proportional to ERV. Using this fact, we can derive a predictive statistical model for an accumulated quantity of Al dissolution in an Al can.

Keywords: enamel rater value; aluminum cans; corrosion; aluminum dissolution; generalized gamma distribution; new power normal family (search for similar items in EconPapers)
Date: 2008
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.tandfonline.com/doi/abs/10.1080/02664760701835342 (text/html)
Access to full text is restricted to subscribers.

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:taf:japsta:v:35:y:2008:i:5:p:515-535

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/02664760701835342

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().