Probability Density Functions for Prediction Using Normal and Exponential Distribution
Journal of Advances in Mathematics and Computer Science,
Page 4052
DOI:
10.9734/jamcs/2021/v36i1030410
Abstract
When data are found to be realizations of a specific distribution, constructing the probability density function based on this distribution may not lead to the best prediction result. In this study, numerical simulations are conducted using data that follow a normal distribution, and we examine whether probability density functions that have shapes different from that of the normal distribution can yield larger loglikelihoods than the normal distribution in the light of future data. The results indicate that fitting realizations of the normal distribution to a different probability density function produces better results from the perspective of predictive ability. Similarly, a set of simulations using the exponential distribution shows that better predictions are obtained when the corresponding realizations are fitted to a probability density function that is slightly different from the exponential distribution. These observations demonstrate that when the form of the probability density function that generates the data is known, the use of another form of the probability density function may achieve more desirable results from the standpoint of prediction.
Keywords:
 Exponential distribution
 future data
 loglikelihood
 normal distribution
 predictive estimator
 probability density function
How to Cite
References
Bickel PJ, Doksum KA. Mathematical Statistics: Basic Ideas and Selected Topics, Vol. I. 2nd ed. Upper Saddle River, USA: Prentice Hall; 2000.
Takezawa K. A Revision of AIC for Normal Error Models. Open J Stat. 2012;2(3):30912.
Takezawa K. Learning regression analysis by simulation. Tokyo, Japan: Springer; 2014.
Ogasawara H. A family of the adjusted estimators maximizing the asymptotic predictive expected loglikelihood. Behaviormetrika. 2017;44:5795.
Ogasawara H. Predictive estimation of a covariance matrix and its structural parameters. J Jpn Soc Comput Stat. 2017;30:4563.
Konishi S, Kitagawa G. Information Criteria and Statistical Modeling. Springer, New York; 2008.
Takezawa K. Introduction to Nonparametric Regression. Hoboken, USA: Wiley; 2005.
Takezawa K. Estimation of the exponential distribution in the light of future data. Br J Math Comput Sci. 2015;5(1):12832.
Basu B, Tiwari D, Kundu D, Prasad R. Is Weibull Distribution the Most Appropriate Statistical Strength Distribution for Brittle Materials?. Ceramics International. 2009;35:237 246.
Marshall AW, Meza JC, and Olkin I. Can data recognize its parent distribution?. Journal of Computational and Graphical Statistics. 2001;10:555580.
Raqab MZ, AlAwadhi SA, Kundu D. Discriminating among Weibull, lognormal and loglogistic distributions. Communication in Statistics  Simulation and Computation 2017;47(8):13971419.
Upadhyay SK, Peshwani M. Choice between Weibull and lognormal models: a simulation based bayesian study. Communications in Statistics  Theory and Methods. 2003;32(2):381405.
Yu HF. The effect of misspecification between the lognormal and Weibull distributions on the interval estimation of a quantile for complete data. Communications in Statistics  Theory and Methods. 2012;41(9):16171635.
Mukha VS, Kako NF. The integrals and integral transformations connected with the joint vector Gaussian distribution. Proceedings of the National Academy of Sciences of Belarus. Physics and Mathematics series. 2021;57(2):206216.
Mukha VS, Kako NF. Integrals and integral transformations related to the vector Gaussian distribution. Proceedings of the National Academy of Sciences of Belarus. ?Qhysics and Mathematics series. 2019;55(4):457466.
Mukha VS, Kako NF. Total probability formula for vector gaussian distributions. Doklady BGUIR. 2021;19(2):5864.

Abstract View: 95 times
PDF Download: 36 times