Browsing by Author "Zalila Ali"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Applications Of Zero Inflated Model For Health Sciences Data
    (Journal of Advances Scientific Research, 2015) Wan Muhamad Amir W. Ahmad; Siti Aisyah Abdullah; Kasypi Mokhtar; Nor azlida Aleng; Nurfadhlina Abdul Halim; Zalila Ali
    Pneumonia is an infection of one or both lungs which is usually caused by bacteria, viruses, or fungi. Each year, pneumonia attack kills about 1.4 million people in the world, especially among children who are also the main sufferers of the disease. The aim of this study was to examine the factors that are associated directly or indirectly in pneumonia patients among the children. In this present paper, we have considered several regressions model to fit the count data that encounter in the field of Health Sciences. We have fitted Poisson, Negative Binomial (NB), Zero-Inflated Poisson (ZIP) and Zero-Inflated Negative Binomial (ZINB) regressions to pneumonia data. To compare the performance of these models, we analysed data with moderate to high percentage of zero counts. Because the variances were almost two times greater than the means, it appeared that both NB and ZINB models performed better than Poisson and ZIP models for the zero inflated and overdispersed count data. From the results of the ZINB regression can overcome overdispersion so it was better than the Poisson regression model
  • Thumbnail Image
    Item
    Box-Cox Transfromation and Bootstrapping Approach to One Sample T-Test
    (World Applied Sciences Journal, 2015) Wan Muhamad Amir W Ahmad; Syerrina Binti Zakaria; Nor Azlida Aleng; Nurfadhlina Abdul Halim; Zalila Ali
    One sample t-test is one of the most popular collections of statistical technique for analyzing data. Before we perform one sample T-Test the first thing that we should check is normality assumption. In this paper, we combine Box-Cox and bootstrapping idea in one algorithm. The purpose of Box-Cox is to ensure the data is normally distributed before the analysis. This combination is very useful for the modelling with an advanced analysis and perhaps can be an alternative method for modelling options in applied statistics scope. Through this combining method, we are capable to handle the case of non-normal data and small and limited sample size data by bootstrapping the original data set to generate new ones. In our case, the term “bootstrap” actually is referring to the use of the original data set to generate new ones. In this research paper, from a small and limited sample size data, we performed bootstrapping method in order to generate a new data set with a bigger sample size. After getting a new sample size, we then perform one sample T-Test using standard procedures and modified procedure. Results from both analyses will be compared with others to know the efficiency of the modified procedure. We also provided some example of application of the method discussed by using SAS language computer software.