IRAQI JOURNAL OF STATISTICAL SCIENCES

One of the most important problems in linear reservoir is the distribution of the storage.The main goal of this paper is to find the distribution of the outflow of linear reservoir and then the storage distribution.This is done by applying a simple technique which is the Fast Fourier Transformation (FFT) Method.

Modeling count variables is a common task in many application areas such as economics, social sciences, and medicine. The classical Poisson regression model for count data is often used and it is limited in these disciplines since count data sets typically exhibit overdispersion, so negative binomial regression can be used. We use a jackknife- after- bootstrap procedure to assess the error in the bootstrap estimated parameters. The method is illustrated through two real examples. The results suggest that the jackknife- after- bootstrap method provides a reliable alternative to traditional methods particularly in small to moderate samples.

Passing the chosen diagnosed candidate model is considered an employed modeled gate and the possibility of data presentation to be used in prediction and control. Also
the research has dealt with different tests for Portmanteau and because the wide spread test in the ready made Programs is the L-B test, and
sicne many studies mentioned that this test suffers from huge differences in variation this led us to deal with the most recent tests like H-M and L-M trying to study its trial empirical power and its statistical specification (mean, variance) and applying some modification through adopting the partial autocorrelation coefficient PACF instead of the autocorrelation coefficients ACF, when calculated and suggesting a new test depending on the mean of the autocorrelation coefficient -rk- that was suggest by Moran 1948 .
To reach this target simulation technique was used to comparieson Portmanteau tests in addition to the suggested test .The study showed that the use of the PACF in portmanteau tests contributed to increase it's empirical power and at the same time decrease it's variance.

Abstract
Support vector machine initially developed to perform binary classification. This paper presents a multi-class support vector machine classifier and ordinal regression to classify the type of bone mineral density. This paper compares the performance of four multi-class approaches, one-against-all, one-against-one, Weston and Watkins, and Crammer and Singer. Results from our real life data conclude that Crammer and Singer may be better approach depending on training error and the percentage of correctly classified test data. Also, we find that the training error becomes more less when the regulization parameter and kernel parameter become large.

Abstract
Three statistical analyses were applied: analysis of variance and then the multistatistical comparisons represented by the test of Newman-Keul, the quality control procedure and the cluster analysis, to compare between the results of their analyses on the data represented a chemical specification by water hardness (ml/l) of Tigris river in Mosul town. The samples were taken from five sites which are: Darnajook, Shouhada'a bridge, Nineveh bridge, Danadan and Yaremjah.
Some matched results were noticed between Newman-Keul test and the quality control procedure, while cluster analysis gave different results.

The subject of relying on forecasting models which depend on time series has become prominent recently especially with the easy using of those models , according to application package,
The search harmonized many of these models and advanced methods for the gaining of accurate forecasting to an important and active indictor for the education in universities this is the average of harmonization , as it is important to know the development of the indictor to build its capacity in that field to
emerge to in the quality and reliance also the research involves other indictors for education at universities like students admission accepting . Then comparison Was made between two various models, the method of index exponential smoothing and Box & Jenkins then select the best of them for forecasting to hose indictors , as Box & Jenkins models excelled relying on the comparison criteria (MSE)

Prediction of time series is the most important and widest spread for researcher nowadays, for it's importance in different approaches ,especially study of natural phenomena .This study deals with the prediction of fuzzing pattern matching models which use three algorithms;(Singh,2001) algorithms ,(Altai,2010) algorithms ,while the third algorithm is an evolution algorithm which combined the two algorithms, in addition we make some correction which leads to give a better results than both algorithms and also the prediction of multiple time series models used which called transfer function models .

These methods were applied on the monthly data of time series for Tigris river in Mosul city for the year 2010, we take five variables represented by Turbidity as an output variable while input variables were represented by PH value , Chemical oxygen demand , Total dissolved solids and Electrical conductivity, and by using prediction criteria of fixed or exact adjustment, The results show that the transfer function models give more exact results than evolution algorithm.

This paper is concerned with fitting some black box models. Some of them are, the outputs error model which contains the autoregressive and autoregressive moving average with additional inputs(ARX and ARMAX).The best model has been chosen which represents the data about the Temperature which is affected by some predictor variables which they were represented by (Brightness, unlike radiation, and evaporation).The parameters of the best model were estimated by the ridge regression method with and without the existence of prior information around the model parameters. The prediction errors of the model which has been estimated by least square and ridge regression when the prior information about the parameters is available were compared.

The research is a comparison of solving some game theory problems by using the genetic algorithm and LINGO software package to define the best one in solving such problems. The research concluded that the least value of the match was accomplished by using genetic algorithm in contrast with solving by LINGO . The time ratio by which every player can use the available strategy to achieve the optimum value of the match was also defined .

The revolutionary technology of digital communications delivered more pressure on many public sector institutions to convert their operations to the world of e-business is known as electronic government, known as e-government as including the integrative effective use for all information and communication technologies to facilitate the administrative processes of daily government sectors. The vital features that can be able to experience the people and between those vital features (fingerprints, face, hand geometry, iris scan). This research aims to use iris scans to identify people through the image of the
irisand the application program using the package (MATLAB) to match the images iris for people as it has matching images with the images stored in the database if the amount of the difference between the two images was equal to zero the number of the compared images that were compared It is compared to all the images were obtained a high percentage of the corresponding images.

The main objective of the statistical methods address the issue of predictability and quality control within the required quality standards and take advantage of the capabilities of computer in the preparation of a computer program to accomplish the tasks of our study, hence this research of a prediction for the testing of water in a Box – Jenkins method for its ability to deal with non-stable time-series and even non-linear and then calculating the rates of the tests, projects and control in Fuzzy logic .