-
Order Statistics from Non-Identical Standard Type II Generalized Logistic Variables and Applications at Moments
Issue:
Volume 4, Issue 1, January 2015
Pages:
1-5
Received:
1 December 2014
Accepted:
28 December 2014
Published:
16 January 2015
Abstract: In this paper the moment generating function of order statistics arising from independent non-identically distributed (INID) Standard type II Generalized logistic (SGLII) variables is established. A recurrence relation for all moments of all order statistics arising from INID SGLII is computed. Special cases for moments are deduced using polygamma function. Some numerical examples are given.
Abstract: In this paper the moment generating function of order statistics arising from independent non-identically distributed (INID) Standard type II Generalized logistic (SGLII) variables is established. A recurrence relation for all moments of all order statistics arising from INID SGLII is computed. Special cases for moments are deduced using polygamma ...
Show More
-
The Design of Experiment Application (DOE) in the Beneficiation of Cashew Chestnut in Northeastern Brazil
Miriam Karla Rocha,
Liane Márcia Freitas Silva,
Alexandre José de Oliveira,
André Lucena Duarte,
Adrícia Fonseca Mendes,
Messias Borges Silva
Issue:
Volume 4, Issue 1, January 2015
Pages:
6-14
Received:
20 December 2014
Accepted:
6 January 2015
Published:
19 January 2015
Abstract: Brazil is one of the world´s leaders in the production and processing of cashew chestnut and 100% of these cashew chestnut processing industries are located in the northeastern region of the country. For the maintenance and enlargement of the cashew chestnut market it is necessary to have a guarantee of the product quality by means of controlling the productive process. In this case, the application of DOE (Design of Experiments) is suggested in the beneficiation process of the cashew chestnut, notably in the stage of decortication, where the chestnuts are being cut in bands, by a mechanical means. For this process, a fractionated factorial experiment planning was used and evaluated response variable in the experiment was the quality of the almond in the final stage of production, measured by the percentage of whole almonds after the separation from the barks. The chosen process factors were the almonds size, the humidification of the environment, the temperature of the environment before the decorticator and the velocity of the decorticator. At the end of the experiment, it was observed that DOE showed to be an applicable tool that indicates which factors showed to be more influential, as well as, their levels of adjustment. It was observed that the variables related to the size of the almonds, the velocity in decortication are the influential factors of production in this process, apart from a strong noise being identified in this process, observed by the strong variance in the experiment data, especially that of the response variable.
Abstract: Brazil is one of the world´s leaders in the production and processing of cashew chestnut and 100% of these cashew chestnut processing industries are located in the northeastern region of the country. For the maintenance and enlargement of the cashew chestnut market it is necessary to have a guarantee of the product quality by means of controlling t...
Show More
-
Forecasting Inflation Rate in Kenya Using SARIMA Model
Susan W. Gikungu,
Anthony G. Waititu,
John M. Kihoro
Issue:
Volume 4, Issue 1, January 2015
Pages:
15-18
Received:
16 December 2014
Accepted:
8 January 2015
Published:
20 January 2015
Abstract: It is the desire of the policy makers in a country is to have access to reliable forecast of inflation rate. This is achievable if an appropriate model with high predictive accuracy is used. In this paper, Seasonal Autoregressive Integrated Moving Average (SARIMA) model is developed to forecast Kenya's inflation rate using quarterly data for the period 1981 to 2013 obtained from KNBS. SARIMA (0,1,0) (0,0,1)4 was identified as the best model. This was achieved by identifying the model with the least Akaike Information Criterion. The parameters were then estimated through the Maximum Likelihood Estimation method. Diagnostic checks using Jarque-Bera Normality Test indicated that they were normally distributed. ACF and PACF plots for the residuals and squared residuals revealed that they followed a white noise process and were homoskedastic respectively. The predictive ability tests RMSE=0.2871, MAPE=3.9456 and MAE= 0.2369 showed that the model was appropriate for forecasting the inflation rate in Kenya.
Abstract: It is the desire of the policy makers in a country is to have access to reliable forecast of inflation rate. This is achievable if an appropriate model with high predictive accuracy is used. In this paper, Seasonal Autoregressive Integrated Moving Average (SARIMA) model is developed to forecast Kenya's inflation rate using quarterly data for the pe...
Show More
-
Multilevel Modeling of Determinants of Fertility Status of Married Women in Ethiopia
Issue:
Volume 4, Issue 1, January 2015
Pages:
19-25
Received:
21 December 2014
Accepted:
11 January 2015
Published:
21 January 2015
Abstract: The main objective of this study is to investigate the determinant factors of fertility status of married women in Ethiopia and to examine the reasons for variations of fertility across regions of Ethiopia based on data on 7052 married women obtained from Ethiopian Demographic and Health Survey (EDHS, 2011). Multilevel binary logistic regression models on fertility status of married women were employed. This study revealed that the random intercept and fixed slope model fits the data significantly better than the other multilevel logistic regression models. The results confirmed that woman’s education level, sex of household head, being visited by family planning worker last twelve months, child loss experience, woman’s occupation, religion and age of woman at first birth were found to be significant determinants and also contributing factors for variation in fertility status of married women among the regions of Ethiopia. In random intercept model the overall variance of constant term was found to be statistically significant implies that women with the same characteristics in two different regions have different fertility status: that is, there is a clear region effect. In this study multilevel model best fit the data as compared to single level model.
Abstract: The main objective of this study is to investigate the determinant factors of fertility status of married women in Ethiopia and to examine the reasons for variations of fertility across regions of Ethiopia based on data on 7052 married women obtained from Ethiopian Demographic and Health Survey (EDHS, 2011). Multilevel binary logistic regression mo...
Show More
-
Bayesian Estimation Based on Record Values from Exponentiated Weibull Distribution: An Markov Chain Monte Carlo Approach
Rashad Mohamed El-Sagheer
Issue:
Volume 4, Issue 1, January 2015
Pages:
26-32
Received:
10 January 2015
Accepted:
13 January 2015
Published:
23 January 2015
Abstract: In this paper, we consider the Bayes estimators of the unknown parameters of the exponentiated Weibull distribution (EWD) under the assumptions of gamma priors on both shape parameters. Point estimation and confidence intervals based on maximum likelihood and bootstrap methods are proposed. The Bayes estimators cannot be obtained in explicit forms. So we propose Markov chain Monte Carlo (MCMC) techniques to generate samples from the posterior distributions and in turn computing the Bayes estimators. The approximate Bayes estimators obtained under the assumptions of non-informative priors are compared with the maximum likelihood estimators using Monte Carlo simulations. A numerical example is also presented for illustrative purposes.
Abstract: In this paper, we consider the Bayes estimators of the unknown parameters of the exponentiated Weibull distribution (EWD) under the assumptions of gamma priors on both shape parameters. Point estimation and confidence intervals based on maximum likelihood and bootstrap methods are proposed. The Bayes estimators cannot be obtained in explicit forms....
Show More
-
Prediction Intervals for Future Order Statistics from Two Independent Sequences
M. M. Mohie El-Din,
M. S. Kotb,
W. S. Emam
Issue:
Volume 4, Issue 1, January 2015
Pages:
33-40
Received:
23 December 2014
Accepted:
6 January 2015
Published:
2 February 2015
Abstract: In this article, based on observed X-sequence of independent and identically distribution (iid) continuous random variables, we discuss the problem of predicting future order statistics from a Y-sequence of iid continuous random variables from the same distribution. Specifically, distribution-free prediction intervals (PIs) for an order statistic observation based on either progressive Type-II right censoring, or order data from the past X-sequence, as well as outer and inner PIs are derived based on order statistics observations. Such these intervals are exact and do not depend on the sampling distribution. Finally, a real life time data set that given to breakdown of an insulating fluid between electrodes is used to illustrate the proposed procedures.
Abstract: In this article, based on observed X-sequence of independent and identically distribution (iid) continuous random variables, we discuss the problem of predicting future order statistics from a Y-sequence of iid continuous random variables from the same distribution. Specifically, distribution-free prediction intervals (PIs) for an order statistic o...
Show More