Rohayu Mohd Salleh

SPC in service industry: Case in teaching and learning process variability monitoring

Statistical Process Control (SPC) technique have long been developed and implemented for quality improvements in manufacturing process. However, it is not so developed in service industry and particularly in teaching and learning process. On the other hand, it is easier to monitor manufacturing industrial process than monitoring teaching and learning process. In the former, the sub-group size is small and constant while in the latter, it is large and nonconstant. In this paper we focus on analyzing the disparity of teaching and learning process variability among classes in a Sekolah Menengah Kebangsaan using the improved generalized variance chart. For that purpose, the appropriate control limits will be developed such that it can be used for general sampling design. The result will be used to monitor the variability of teaching and learning process. A diagnostic tool will also be delivered to understand why, if any, a class is out-of-control.

Bursa Malaysia performance: Evidence from the minimum spanning tree

Malaysia is a highly open, upper-middle income with the diversified economic sector as recognized by The World Bank. Due to some critical issues happened, the economy getting uptight and depressed dramatically, especially the values of Bursa Malaysia. It becomes unstable and the system of the stock market seems to become more complicated. Hence, it is difficult to identify the most dominant stock in the market. In order to investigate the behaviors among stocks, minimum spanning tree was applied to filter the essential information which contained in the topological structure of the stock market. To construct the taxonomy structure of stocks, Kruskal’s algorithm, Prim’s algorithm and Forest of all possible MSTs were used. By comparing these three algorithms, the robust and optimal structure of Bursa Malaysia was obtained as well as the behaviors among the stocks was determined. The analysis of MST is presented and discussed to illustrate the intentions of the study.Malaysia is a highly open, upper-middle income with the diversified economic sector as recognized by The World Bank. Due to some critical issues happened, the economy getting uptight and depressed dramatically, especially the values of Bursa Malaysia. It becomes unstable and the system of the stock market seems to become more complicated. Hence, it is difficult to identify the most dominant stock in the market. In order to investigate the behaviors among stocks, minimum spanning tree was applied to filter the essential information which contained in the topological structure of the stock market. To construct the taxonomy structure of stocks, Kruskal’s algorithm, Prim’s algorithm and Forest of all possible MSTs were used. By comparing these three algorithms, the robust and optimal structure of Bursa Malaysia was obtained as well as the behaviors among the stocks was determined. The analysis of MST is presented and discussed to illustrate the intentions of the study.

Parameter estimation of Monod model by the Least-Squares method for microalgae Botryococcus Braunii sp

This research aims to estimate the parameters of Monod model of microalgae Botryococcus Braunii sp growth by the Least-Squares method. Monod equation is a non-linear equation which can be transformed into a linear equation form and it is solved by implementing the Least-Squares linear regression method. Meanwhile, Gauss-Newton method is an alternative method to solve the non-linear Least-Squares problem with the aim to obtain the parameters value of Monod model by minimizing the sum of square error ( SSE). As the result, the parameters of the Monod model for microalgae Botryococcus Braunii sp can be estimated by the Least-Squares method. However, the estimated parameters value obtained by the non-linear Least-Squares method are more accurate compared to the linear Least-Squares method since the SSE of the non-linear Least-Squares method is less than the linear Least-Squares method.

Autocorrelated process control: Geometric Brownian Motion approach versus Box-Jenkins approach

Existing of autocorrelation will bring a significant effect on the performance and accuracy of process control if the problem does not handle carefully. When dealing with autocorrelated process, Box-Jenkins method will be preferred because of the popularity. However, the computation of Box-Jenkins method is too complicated and challenging which cause of time-consuming. Therefore, an alternative method which known as Geometric Brownian Motion (GBM) is introduced to monitor the autocorrelated process. One real case of furnace temperature data is conducted to compare the performance of Box-Jenkins and GBM methods in monitoring autocorrelation process. Both methods give the same results in terms of model accuracy and monitoring process control. Yet, GBM is superior compared to Box-Jenkins method due to its simplicity and practically with shorter computational time.

An Application of Robust Method in Multiple Linear Regression Model toward Credit Card Debt

Credit card is a convenient alternative replaced cash or cheque, and it is essential component for electronic and internet commerce. In this study, the researchers attempt to determine the relationship and significance variables between credit card debt and demographic variables such as age, household income, education level, years with current employer, years at current address, debt to income ratio and other debt. The provided data covers 850 customers information. There are three methods that applied to the credit card debt data which are multiple linear regression (MLR) models, MLR models with least quartile difference (LQD) method and MLR models with mean absolute deviation method. After comparing among three methods, it is found that MLR model with LQD method became the best model with the lowest value of mean square error (MSE). According to the final model, it shows that the years with current employer, years at current address, household income in thousands and debt to income ratio are positively associated with the amount of credit debt. Meanwhile variables for age, level of education and other debt are negatively associated with amount of credit debt. This study may serve as a reference for the bank company by using robust methods, so that they could better understand their options and choice that is best aligned with their goals for inference regarding to the credit card debt.

On the reliability of Shewhart-type control charts for multivariate process variability

We show that in the current practice of multivariate process variability monitoring, the reliability of Shewhart-type control charts cannot be measured except when the sub-group size n tends to infinity. However, the requirement of large n is meaningless not only in manufacturing industry where n is small but also in service industry where n is moderate. In this paper, we introduce a new definition of control limits in the two most appreciated control charts in the literature, i.e., the improved generalized variance chart (IGV-chart) and vector variance chart (VV-chart). With the new definition of control limits, the reliability of the control charts can be determined. Some important properties of new control limits will be derived and the computational technique of probability of false alarm will be delivered.

Robust start up stage for beltline moulding process variability monitoring using vector variance

One of the primary problems encountered in monitoring the variability of beltline moulding process in an automotive industry is the estimation of parameters in the start-up stage. This problem becomes more interesting because the process is in multivariate setting and must be monitored based on individual observations, i.e., the sample size of each subgroup is 1. This paper deals with a robust estimation of location and scale during the start-up stage. For this purpose, we use Mahalanobis distance in data ordering process. But, in data concentration process, we use vector variance (VV). This method is highly robust and computationally efficient. Its advantage in monitoring the variability of beltline moulding process will be compared with the non-robust method.

Robust monitoring of process mean vector in female shrouded connector production: An experience in Malaysia

We present a robust approach in monitoring the process mean vector of female shrouded connector production experienced in a company in Malaysia. First, we propose a new stopping rule in data concentration process of FMCD to reduce its computational complexity and then use it in Phase I to estimate the process parameter needed during Phase II operations. Interesting result such as based on multivariate capability index CpM will be reported.

A high breakdown point robust Phase I operation of process variability monitoring based on individual observations

This paper presents an improvement of data concentration process in FMCD algorithm in order to increase its computational efficiency. A simulation study indicates that the improved algorithm is promising in reducing the running time. This advantage will allow the users to use more efficiently that algorithm in multivariate analysis including in the development of a high breakdown point robust Phase I operation in monitoring manufacturing process quality based on individual observations. A real example in Phase I operation of process variability will be presented and discussed to illustrate the advantage of the proposed improved algorithm.