Mostrando recursos 1 - 20 de 42

  1. Empirical Estimation Based On Progressive First Failure Censored Generalized Pareto Data

    Prakash, Gyan
    The Progressive First-Failure (PFF) censoring scheme is considered in the present article for the Empirical Bayes estimation. The approximate confidence intervals and the Bayes estimation for the unknown parameters under the empirical Bayesian technique are obtained for the Generalized Pareto distribution. The improved approximate confidence intervals are discussed also. A simulation technique is applied here for illustrating the methods based on different censoring plans, those are the special cases of PFF censoring scheme.

  2. Divergence Measures Estimation and Its Asymptotic Normality Theory Using Wavelets Empirical Processes II

    Ba, Amadou Diadié; Lo, Gane Samb; Ba, Diam
    In Ba et al. (2017), a general normal asymptotic theory for divergence measures estimators has been provided. These estimators are constructed from the wavelets empirical process and concerned the general $\phi$-divergence measures. In this paper, we first extend the aforementioned results to symmetrized forms of divergence measures. Second, the Tsallis and Renyi divergence measures as well as the Kullback-Leibler measures are investigated in details. The question of the applicability of the results, based on the boundedness assumption is also dealt, leading to future packages.

  3. A negative binomial mixture integer-valued GARCH model

    Diop, Mamadou Lamine; Diop, Aliou; Diongue, Abdou Kâ
    This paper generalizes the negative binomial integer-valued GARCH model (NBINGARCH) to a negative binomial mixture integer-valued GARCH (NB-MINGARCH) for modeling time series of counts with presence of overdispersion. This class of models consists of a mixture of $K$ stationary or non-stationary negative binomial integer-valued GARCH components. The advantage of these models over the NBINGARCH models includes the ability to handle multimodality and non-stationary components. Compared to the MINGARCH models, this class of models is more flexible to describe the greater degrees of overdispersion. The necessary and sufficient first and second order stationarity conditions are investigated. The estimation of parameters is...

  4. Global convergence and ascent property of a cyclic algorithm used for statistical analysis of crash data

    Geraldo, Issa Cherif; N'Gessan, Assi; Gneyou, Kossi Essona
    In this paper, we consider an estimation algorithm called cyclic iterative algorithm (CA) that is used in statistics to estimate the unknown vector parameter of a crash data model. We provide a theoretical proof of the global convergence of the CA that justifies the good numerical results obtained in early numerical studies of this algorithm. We also prove that the CA is an ascent algorithm, what ensures its numerical stability.

  5. Adjusting the Penalized Term for the Regularized Regression Models

    Haggag, Magda M. M.
    More attention has been given to regularization methods in the last two decades as a result of exiting high-dimensional ill-posed data. This paper proposes a new method of introducing the penalized term in regularized regression. The proposed penalty is based on using the least squares estimator's variances of the regression parameters. The proposed method is applied to some penalized estimators like ridge, lasso, and elastic net, which are used to overcome both the multicollinearity problem and selecting variables. Good results are obtained using the average mean squared error criterion (AMSE) for simulated data, also real data are shown best results...

  6. Ruin Probabilities in Perturbed Risk Process with Stochastic Investment and Force of interest

    Oseni, Bamidele Mustapha; Jolayemi, Emmanuel Teju
    This work considers a perturbed risk process with investment, where the investments are either into invested in risky and risk-less assets. A third order differential equation for the ruin probability is derived from the resulting integro-differential equation. This equation is further decomposed into two equations describing the contributions of the claim and oscillation to the ruin probability. These two equations are solved separately using suitable transformations as well as theory of Kummer confluence hypergeometric equations. We further investigated these solutions and were able to conclude that the higher the fraction of investment into risky assets, the lower the ruin probability,...

  7. Box-Jenkins Analysis of Mean Monthly Temperature in Rwanda

    Maniraguha, Jean de Dieu; Gasana, Emelyne Umunoza
    Generally, temperature is a sensation of coldness and hotness and is affected by air and humidity as climate factors in certain areas. The high altitude of Rwanda provides the country with pleasant tropical highland climate. The recent research done on climate changes and global warming found an increase in temperature of 1 to 2 degrees Celsius between year 2000 and year 2050 due to the natural variability and due to the green house gases that trap the infrared radiation,i.e., these gases will cause the temperature of the earth to increases infrared radiation from the earth surface and reflect it back...

  8. Jump Resonance in Wind-Felled Plantains

    Asemota, Godwin Norense Osarumwense
    In this paper, jump resonance was applied to wind-felled plantains, which budded on the plantain pseudo-stem side when guyed about $60^{o}$ to the horizontal to obtain the jump function. Duffing's model, describing function and Chebyshev polynomials were used to obtain the best fit of approximants to the developed plantains jump function. Traditionally, wind-damaged plantains and banana pseudo-stems are cut for future vegetative growth, leading to heavy and perennial losses to individuals, households, communities, nations and even regions. The motivation for this study was the possibility of using jump resonance discontinuity as a plantain wind-damaged salvage process. Furthermore, it was to...

  9. Uniform in Bandwidth Law of the Iterated Logarithm for a Transformation Kernel Estimator of Copulas

    Seck, Cheikh Tidiane; Diam, Ba; Lo, Gane Samb
    In this paper, we establish a uniform in bandwidth law of the iterated logarithm for the Transformation kernel estimator of bivariate copulas introduced in Omelka et al. (2009). To this end, we make use of a general empirical process approach inspired by the works in Mason and Swanepoel (2011). We obtain the asymptotic order of the maximal deviation of this estimator from its expectation. Then, we show that the bias converges asymptotically to zero at the same order provided that the second-order partial derivatives of the copula exist and are bounded. We also propose a bandwidth selection method by using...

  10. Multivariate Analysis of Rwanda Economic Indicators using Vector Autoregressive (VAR) Model

    Uwamariya, Denise; Gasana, Emelyne Umunoza
    Rwanda's economy has been growing fast due to important economic and structural reforms over the last decade. Consumer Price Index (CPI), Exchange Rate and Nominal Growth Domestic Product (NGDP) constitute some of the major economic indicators in emerging market economies that require monetary authorities to elaborate tools and policies to prevent high volatility in prices. Thus, understanding CPI, exchange rate and NGDP dynamics is a key to the design of fund programs to help stabilize the economy of a developing country such as Rwanda. In this study, secondary data from the National Bank of Rwanda, depicting quarterly time series of...

  11. R-transform associated with asymptotic negative spectral moments of Jacobi ensemble

    Pielaszkiewicz, Jolanta
    We derive an explicit formula for the R-transform of inverse Jacobi matrix $I+W_1^{-1}W_2$, where $W_1,W_2\sim\mathcal{W}_p(I,n_i)$, $i=1,2$ are independent and $I$ is $p\times p$ dimensional identity matrix using property of asymptotic freeness of Wishart and deterministic matrices. Procedure can be extended to other sets of the asymptotically free independent matrices. Calculations are illustrated with some simulations on fixed size matrices.

  12. Further properties of linear prediction sufficiency and the BLUPs in the linear model with new observations

    Markiewicz, Augustyn; Puntanen, Simo
    A linear statistic $\mathrm{Fy}$ is called linearly sufficient for the estimable parametric function of $\mathrm X_{*} \beta$ under the linear model $\mathscr M = \{ \mathrm y, \mathrm X \beta, \mathrm V \}$ if there exists a matrix $\mathrm A$ such that $\mathrm {AFy}$ is the best linear unbiased estimator, BLUE, for $\mathrm X_{*} \beta$. The concept of linear sufficiency with respect to a predictable random vector is defined in the corresponding way but considering best linear unbiased predictor, BLUP, instead of BLUE. In this paper, we consider the linear sufficiency of $\mathrm{Fy}$ with respect to $\mathrm{y}_{*}$, $\mathrm X_{*} \beta$,...

  13. Spatio-temporal Predictions using Multivariate Singular Spectrum Analysis

    Awichi, Richard
    In this paper, we present a method for utilizing the usually intrinsic spatial information in spatial data sets to improve the quality of temporal predictions within the framework of singular spectrum analysis (SSA) techniques. The SSA-based techniques constitute a model free approach to time series analysis and ordinarily, SSA can be applied to any time series with a notable structure. Indeed it has a wide area of application including social sciences, medical sciences, finance, environmental sciences, mathematics, dynamical systems and economics. SSA has two broad aims: i) To make a decomposition of the original series into a sum of a...

  14. Editorial Paper of the Special Issue 13 (1) of Afrika Statistika on Selected papers presented to EACSAM 2017

    Singull, Martin; Rachdi, Mustapha; Lo, Gane Samb
    We briefly introduce to this special issue of Afrika Statistika devoted to selected Papers presented at the First East African Conference of Statistical Mathematics with Applications (EACSMA-2017).

  15. Comparison between two bivariate Poisson distributions through the phi-divergence

    Nganga, Prévot C. Batsindila; Bidounga, Rufin; Mizère, Dominique; Kokonendji, Célestin C.
    In the literature, there are two probabilistic models of bivariate Poisson : the model according to Holgate and the model according to Berkhout and Plug. These two models express themselves by their probability mass function. The model of Holgate puts in evidence a strictly positive correlation, which is not always realistic. To remedy this problem, Berkhout and Plug proposed a bivariate Poisson distribution accepting the correlation as well negative, equal to zero, that positive. In this paper, we show that these models are nearly everywhere asymptotically equal. From this survey that the $\phi$-divergence converges toward zero, both models are therefore...

  16. Comparison between two bivariate Poisson distributions through the phi-divergence

    Nganga, Prévot C. Batsindila; Bidounga, Rufin; Mizère, Dominique; Kokonendji, Célestin C.
    In the literature, there are two probabilistic models of bivariate Poisson : the model according to Holgate and the model according to Berkhout and Plug. These two models express themselves by their probability mass function. The model of Holgate puts in evidence a strictly positive correlation, which is not always realistic. To remedy this problem, Berkhout and Plug proposed a bivariate Poisson distribution accepting the correlation as well negative, equal to zero, that positive. In this paper, we show that these models are nearly everywhere asymptotically equal. From this survey that the $\phi$-divergence converges toward zero, both models are therefore...

  17. Bayesian Inference of C-AR(1) Time Series Model with Structural Break

    Kumar, Jitendra; Kumar, Ashok; Agiwal, Varun; Shangodoyin, Dahud Kehinde
    A variable may be affected by some associated variables which may influence the estimation and testing procedures and also not much important to model separately, such types of variables are called covariates. The present paper dealt the covariate autoregressive (C-AR(1)) time series model with structural break in mean and variance under Bayesian framework. Parameters of the model have been estimated considering appropriate prior assumptions and compared with maximum likelihood estimator. A simulation study has been carried out to validate the theoretical results, and then the same implemented on the monthly REER time series of SAARC countries. Both studies, empirical and...

  18. Bayesian Inference of C-AR(1) Time Series Model with Structural Break

    Kumar, Jitendra; Kumar, Ashok; Agiwal, Varun; Shangodoyin, Dahud Kehinde
    A variable may be affected by some associated variables which may influence the estimation and testing procedures and also not much important to model separately, such types of variables are called covariates. The present paper dealt the covariate autoregressive (C-AR(1)) time series model with structural break in mean and variance under Bayesian framework. Parameters of the model have been estimated considering appropriate prior assumptions and compared with maximum likelihood estimator. A simulation study has been carried out to validate the theoretical results, and then the same implemented on the monthly REER time series of SAARC countries. Both studies, empirical and...

  19. Generalized Stacy-Lindley Mixture Distribution

    Radakumari, Maya; Irshad, Muhammed Rasheed
    In this paper, we introduce a five parameter extension of mixture of two Stacy gamma distributions called generalized Stacy-Lindley mixture distribution. Several statistical properties are derived. Two types of estimation techniques are used for estimating the parameters. Asymptotic confidence interval is also calculated for these parameters. Finally, a real data application illustrates the performance of our proposed distribution.

  20. Generalized Stacy-Lindley Mixture Distribution

    Radakumari, Maya; Irshad, Muhammed Rasheed
    In this paper, we introduce a five parameter extension of mixture of two Stacy gamma distributions called generalized Stacy-Lindley mixture distribution. Several statistical properties are derived. Two types of estimation techniques are used for estimating the parameters. Asymptotic confidence interval is also calculated for these parameters. Finally, a real data application illustrates the performance of our proposed distribution.

Aviso de cookies: Usamos cookies propias y de terceros para mejorar nuestros servicios, para análisis estadístico y para mostrarle publicidad. Si continua navegando consideramos que acepta su uso en los términos establecidos en la Política de cookies.