Czasopismo
Tytuł artykułu
Treść / Zawartość
Pełne teksty:
Warianty tytułu
Języki publikacji
Abstrakty
The distribution of product of two normally distributed variables come from the first part of the XX Century. First works about this issue were [1] and [2] showed that under certain conditions the product could be considered as a normally distributed.
A more recent approach is [3] that studied approximation to density function of the product using three methods: numerical integration, Monte Carlo simulation and analytical approximation to the result using the normal distribution. They showed as the inverse variation coefficient μ/σ increases, the distribution of the product of two independent normal variables tends towards a normal distribution.
Our study is focused in Ware and Lad approaches. The objective was studying which factors have more influence in the presence of normality for the product of two independent normal variables. We have considered two factors: the inverse of the variation coefficient value μ/σ and the combined ratio (product of the two means divided by standard deviation): μ₁μ₂/σ for two normal variables with the same variance.
Our results showed that for low values of the inverse of the variation coefficient (less than 1) normal distribution is not a good approximation for the product. Another one, influence of the combined ratio value is less than influence of the inverse of coefficients of variation value.
A more recent approach is [3] that studied approximation to density function of the product using three methods: numerical integration, Monte Carlo simulation and analytical approximation to the result using the normal distribution. They showed as the inverse variation coefficient μ/σ increases, the distribution of the product of two independent normal variables tends towards a normal distribution.
Our study is focused in Ware and Lad approaches. The objective was studying which factors have more influence in the presence of normality for the product of two independent normal variables. We have considered two factors: the inverse of the variation coefficient value μ/σ and the combined ratio (product of the two means divided by standard deviation): μ₁μ₂/σ for two normal variables with the same variance.
Our results showed that for low values of the inverse of the variation coefficient (less than 1) normal distribution is not a good approximation for the product. Another one, influence of the combined ratio value is less than influence of the inverse of coefficients of variation value.
Kategorie tematyczne
Rocznik
Tom
Numer
Strony
87-99
Opis fizyczny
Daty
wydano
2012
otrzymano
2012-10-29
Twórcy
autor
- University of A Corunha - Spain
autor
- Unversidade Aberta - Portugal Center of Statistics and Applications - University of Lisbon
Bibliografia
- [1] Cecil C. Craig, On the frequency function of xy, Annals of Mathematical Society 7 (1936) 1-15. doi: 10.1214/aoms/1177732541.
- [2] L.A. Aroian, The probability function of a product of two normal distributed variables, Annals of Mathematical Statistics 18 (1947) 256-271. doi: 10.1214/aoms/1177730442.
- [3] R. Ware and F. Lad, Approximating the Distribution for Sums of Product of Normal Variables. Research-Paper 2003-15. Department of Mathematics and Statistics (University of Canterbury - New Zealand, 2003).
- [4] L.A. Aroian, V.S. Taneja and L.W. Cornwell, Mathematical forms of the distribution of the product of two normal variables, Communication in Statistics - Theory and Method 7 (1978) 164-172.
- [5] J. Whisart and M.S.Bartlett, The distribution of second order moment statistics in a normal system, Proceedings of the Cambridge Philosophical Society XXVIII (1932) 455-459. doi: 10.1017/S0305004100010690.
- [6] L.A. Aroian, V.S. Taneja and L.W. Cornwell, Mathematical forms of the distribution of the product of two normal variables, Communications in Statistics. Theoretical Methods A7 (2) (1978) 165-172. doi: 10.1080/03610927808827610.
- [7] S.C. Chapra and R.P. Canale, Numerical Methods for Engineers (McGraw-Hill: New York, 2010).
Typ dokumentu
Bibliografia
Identyfikatory
DOI
Identyfikator YADDA
bwmeta1.element.bwnjournal-article-doi-10_7151_dmps_1146