컨텐츠 시작
학술대회/행사
초록검색
| 제출번호(No.) | 0618 |
|---|---|
| 분류(Section) | Invited Talk |
| 분과(Session) | Probability / Stochastic Process / Statistics (SS-12) |
| 영문제목 (Title(Eng.)) |
[CANCELED] Bivariate normal-geometric law |
| 저자(Author(s)) |
Debasis Kundu1 Indian Institute of Technology Kanpur1 |
| 초록본문(Abstract) | In this article we introduce a new three parameter bivariate distribution using random summation of normal random variables. We call this distribution as bivariate normal-geometric law. Different properties of this new distribution has been investigated. The marginals and the conditional distributions are also explored. It is observed that the marginal distribution can be obtained as skewed normal distribution, of which normal distribution is a special case. We study different properties of the proposed skewed distribution. The maximum likelihood estimators of the unknown parameters are obtained using EM algorithm. Monte Carlo simulations are performed to see the effectiveness of the proposed method. One data analysis has been performed for illustrative purposes. The proposed bivariate process induces a bivariate Levy process with correlated normal and negative binomial processes. Some properties of this bivariate Levy processes have been explored. |
| 분류기호 (MSC number(s)) |
62H86, 62H12 |
| 키워드(Keyword(s)) | charectaristic function, moment generating function, infinite divisible, maximum likelihood estimators, EM algorithm, Fisher infomation matrix |
| 강연 형태 (Language of Session (Talk)) |
English |