This Author published in this journals
All Journal Statistika
Claim Missing Document
Check
Articles

Found 9 Documents
Search

Models for Transformation: A Global Optimization Transformation method with Some Extension from Box-Cox Transformation Wan Muhamad Amir Bin W Ahmad; Nyi Nyi Naing; Tengku Mohd Ariff Raja Hussein
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 9, No 1 (2009)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v9i1.987

Abstract

The choice of a transformation has often been made in an ad hoc trial-and-error fashion but in thisresearch paper we deals with the new solution of transformation which is covering all the real numbers.The assumption of normality that gained from the optimization method is much better improvedcompared to Box-Cox transformation through the statistical P value. The biggest values of thestatistical P value (> 0.05) reflect the goodness of the normality achievement. In order to obtain theefficiency status, we will illustrate the application of transformation method with the data that aregetting from Hospital University Science Malaysia (HUSM).
Some Results on Statistical Analysis from Unit of Record, Hospital Universiti Sains Malaysia (HUSM) Wan Muhamad Amir Bin W Ahmad; Nor Azlida Aleng; Zalila Ali
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 10, No 2 (2010)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v10i2.1023

Abstract

Most of the patients which is visiting HUSM for the treatment at the same time suffer with more thanone diseases. Because of that, many of the researchers are trying to find the association of the factorthat contribute to such a case. In this case study we are trying to find the association for a certainhealth factor. It’s contribution will have a major impact in the area of medical statistics.
An Approached of Box-Cox Data Transformation to Biostatistics Experiment Wan Muhamad Amir Bin W Ahmad; Nyi Nyi Naing; Norhayati Rosli
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 6, No 2 (2006)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v6i2.937

Abstract

The Box-Cox family of transformation is a well-known approach to make data behave accordingly toassumption of linear regression and ANOVA. The regression coefficients, as well as theparameter defining the transformation are generally estimated by maximum likelihood, assuminghomoscedastic normal error. In application of ANOVA for hypothesis testing in biostatistics scienceexperiments, the assumption of homogeneity of errors often is violating because of scale effects andthe nature of the measurements. We demonstrate a method of transformation data so that theassumptions of ANOVA are met (or violated to a lesser degree) and apply it in analysis of data frombiostatistics experiments. We will illustrate the use of the Box-Cox method by using MINITABsoftware.
Selection for Parameter  by Using Newton-Raphson Method Wan Muhamad Amir Bin W Ahmad; Nyi Nyi Naing; Mohd Tengku Ariff Raja Hussein
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 7, No 2 (2007)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v7i2.960

Abstract

Many problems in mathematics or statistics involve, at some point or another, solving an equation foran unknown quantity. To solve the problem many of methods are applied as such MaximumLikelihood Method, Least Square Method and Newton-Raphson Method and much more. One of thefamous methods is Newton Method. The Newton-Raphson method or Newton–Fourier method is anefficient algorithm for finding approximations to the zeros (or roots) of a real-valued function. As such,it is an example of a root-finding algorithm. It can also be used to find a minimum or maximum valueof such a function, by finding a zero in the function's first derivative. In this paper, we will work withNewton-Raphson method to estimate the value of for the use of transformation. The value of ,determine the kind of transformation should be done according to the data. These papers emphasizethe Newton Method in finding the value of by using C++ software.
Identification of Time Series Model: An Application Part Wan Muhamad Amir Bin W Ahmad; Norhayati Rosli; Norizan Mohamed; Zalila Binti Ali
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 6, No 1 (2006)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v6i1.931

Abstract

Time series analysis generally referred to any analysis which involved to a time series data. In thisanalysis, any of the continuous observation is commonly dependent. If the continuous observation isdependable, then the values that will come are able to be forecasted from the previous observation(Weir 2006). If the behaviour of coming time series are able to be exactly forecasted based on previoustimes series, so it’s called deterministic time series. The objective of times series can be summarizedas to find the statistical model to describe the behaviour of the time series data and afterwards madeuse of skilled statistical techniques for estimation, forecasting but also the controlling. The use oftime series analysis very much spread in various fields like biology, medical and many more that hada purpose for forecasting. In this paper the recognition of concerning the Autoregressive Processmodel AR (p), Moving Average Process MA (q), Autoregressive Moving Average ARMA (p,q),Autoregressive Integrated Moving Average ARIMA (p,d,q) was given attention through the approach tothe Autocorrelation Function ACF and Partial Autocorrelation Function (PACF) theory plot.
Proportional Hazard Regression Analysis By Using Survival Data Wan Muhamad Amir Bin W Ahmad; Norizan Mohamed; Zurairah Ahmad; Mustafa bin Mamat
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 5, No 1 (2005)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v5i1.913

Abstract

Recently a number of papers have considered both longitudinal changes in a variable and theassociated effect on the length of time to the occurrence of an event (Schork and Remington, 2003).Longitudinal research is performed to study a phenomenon as it is evolving over time. Thephenomenon will generally show changes over time, but it may also show stability. Researchers inpsychology often use longitudinal designs to assess change. Various statistical techniques have beenused to analyze these data, including proportional hazard regression. This paper illustrates the use ofthe SPSS to examine blood data with this technique, as well. The advantages of using a Cox modelapproach to blood pressure analysis are discussed.
A Modification of Box-Cox Transformation Wan Muhamad Amir Bin W Ahmad; Nyi Nyi Naing; Mohd Tengku Ariff Raja Hussein
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 7, No 1 (2007)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v7i1.952

Abstract

Data screening is the most important technique to check the nature of the data. One of the methodsto screen the data is the transformation method. There are a lot of transformations but the famousone is the Box-Cox Transformation. The purpose of this study is to find the alternative way oftransformation by making some modification of the original Box-Cox formula. As we know, the Box-Cox transformation method only transform the data if and only if the data in a positive values. If thevalues in the analysis are negative, the formula of the Box-Cox cannot be used. This problem alwaysoccur when the researcher want to transform the data which the values is negative. In thismethodology section, we will build an alternative method to solve the problem if the data in the studyare negative.
Carta Kawalan XmR Dan Median : Satu Penyelesaian Untuk Data Pencong Norizan Mohamed; Wan Muhamad Amir Bin W Ahmad; Rinner Masli
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 7, No 1 (2007)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v7i1.948

Abstract

Carta kawalan banyak digunakan dalam kawalan mutu berstatistik. Tujuan menggunakan cartakawalan ini adalah untuk memastikan sesuatu proses berada dalam keadaan terkawal dan stabilsepanjang masa secara grafik. Carta kawalan ini terdiri daripada had-had kawalan iaitu, hadkawalan atas, had kawalan tengah dan had kawalan bawah. Untuk mengetahui sesuatu prosestersebut adalah terkawal, kesemua titik yang mewakili variasi dalam sesuatu proses berada di dalamlingkungan had atas dan had bawah. Jika terdapat titik yang terkeluar daripada had kawalan atasmahupun had kawalan bawah, maka proses tersebut dikatakan tidak terkawal dan tidak stabil.Salah satu penggunaan carta kawalan yang meluas ialah carta kawalan XmR iaitu X mewakili nilaiindividu manakala mR mewakili peralihan julat. Untuk memastikan sesuatu proses tersebut beradadalam keadaan terkawal dan stabil, anggapan kenormalan mestilah dipenuhi. Namun demikian,kebanyakan proses pengeluaran menghasilkan data yang pencong dan ini menyebabkan prosestersebut tidak terkawal dan tidak stabil. Oleh itu, satu pendekatan berdasarkan kuasa penjelmaanakan turut dibincangkan dalam kajian ini.
An Application of Alternative Method of Transformation Wan Muhamad Amir Bin W Ahmad; Nyi Nyi Naing; Mohd Tengku Ariff Raja Hussein
STATISTIKA: Forum Teori dan Aplikasi Statistika Vol 7, No 1 (2007)
Publisher : Program Studi Statistika Unisba

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29313/jstat.v7i1.953

Abstract

Data transformation plays a major role when behave of the data do not meet the assumption of linearregression and ANOVA. In this paper we will demonstrate an application of the alternative method oftransformation, so that the assumptions of ANOVA are met (or violated to a lesser degree). These datawere collected from biostatistics experiments. Some of calculation is done by manually and the restby the MINITAB software. The results will be discussed at the end of the paper.