Open AccessNumerical approach nonminimaly supported design for two parameters generalized exponential model and its efficiency
Author(s) -
Tatik Widiharih,
Mustafid Mustafid,
S. Sudarno,
Alan Prahutama
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1943/1/012145
Subject(s) - construct (python library) , exponential function , matrix (chemical analysis) , design matrix , optimal design , nonlinear system , mathematical optimization , fisher information , mathematics , function (biology) , computer science , statistics , mathematical analysis , linear model , biology , materials science , physics , quantum mechanics , evolutionary biology , composite material , programming language
Nonminimally supported designs is a design that the number of supported design is greater than the number of parameters of the model. We construct nonminimally supported design with the number of the supported designs is the number of parameters plus one and it has uniform weight. We use two methods to construct nonminimally supported design, first we create the formula of determinant information matrix then miximized it, second by adding one supported design from minimally supported design. The formula to determine the supported design is a complicated nonlinear function, so we use numerically approach. Furthermore we conclude the best of nonminimally supported design based on the highest value of determinant information matrix. Efficiency of nonminimally supported design to minimally supported design is ratio of determinant information matrix nonminimally supported design and determinant information matrix minimally supported design.