In this research we introduce an analyzing procedure using the Kullback-Leibler information criteria (KLIC) as a statistical tool to evaluate and compare the predictive abilities of possibly misspecified density forecast models. The main advantage of this statistical tool is that we use the censored likelihood functions to compute the tail minimum of the KLIC, to compare the performance of a density forecast models in the tails. Use of KLIC is practically attractive as well as convenient, given its equivalent of the widely used LR test. We include an illustrative simulation to compare a set of distributions, including symmetric and asymmetric distribution, and a family of GARCH volatility models. Our results on simulated data show that the choice of the conditional distribution appears to be a more dominant factor in determining the adequacy and accuracy (quality) of density forecasts than the choice of volatility model.
PURPOSE: To evaluate changes in anterior chamber depth (ACD) and intraocular pressure (IOP) after phacoemulsification in eyes with occludable angles and compare the results with those in eyes with normal open angles.
SETTING: Eye Clinic, Ipoh General Hospital, Ipoh, Perak, Malaysia.
METHODS: Patients with nonglaucomatous eyes with open angles or with occludable angles were recruited. Ocular biometric measurements (ACD, axial length [AL], lens thickness and position) and IOP (tonometry) were performed preoperatively and 1 day and 1, 4, 9, and 12 weeks postoperatively.
RESULTS: The open-angle group and occludable-angle group each comprised 35 patients. The occludable-angle group had a shallower ACD, shorter AL, thicker and relatively anterior lens position, and higher IOP preoperatively; postoperatively, there was a significant increase in ACD and a significant reduction in IOP (P
The purpose of this study was to count the number of lymphatic channels present in colorectal adenocarcinoma and correlate it with site, size, and stage of tumor, lymph node metastasis.
A cross-sectional study was undertaken to determine the refractive and biometric status of premature children without Retinopathy of Prematurity (ROP) and full term children. Fifty eight children between the ages of 3 and 7 years (32 children born premature without ROP and another 26 children born full term and normal) were examined. Refractive error, corneal curvature, axial length, anterior chamber depth and crystalline lens thickness were determined. The results revealed that children between the age of 3 and 7 years were emmetropic, irrespective of whether they were born premature without ROP or full term. However, children born premature without ROP had significantly steeper corneas (t = 3.14, p = 0.0349), shorter axial lengths (t = 3.18, p = 0.0313) and thicker crystalline lens (t = 3.31, p = 0.0256) compared to children born full term within the same age group. This study suggests that compensation in ocular parameters can occur to maintain emmetropia, mainly by adjustment of axial length and corneal curvature.
This study investigated the spatial pattern and trends of the daily rainfall data in Peninsular Malaysia based on seasonal rainfall indices. Five rainfall indices which describe the main characteristics of rainfall, the total amount of rainfall, frequency of wet days, rainfall intensity, extreme frequency, and extreme intensity, were employed in this study. The statistics of rainfall indices were calculated in terms of their means for four regions in Peninsular Malaysia for the period 1975 to 2004. The findings indicate that the southwest monsoon had the greatest impact on the western part of the Peninsula, particularly in characterizing the rainfall pattern of the northwest region. During this season, the northwest region could be considered as the wettest region since all rainfall indices tested are higher than in other regions of the Peninsula. Otherwise, the northwest region is denoted as the driest part of the Peninsula during the northeast monsoon period. The northwest region is less influenced by the northeast monsoon because of the existence of the Titiwangsa Range, which blocks the region from receiving heavy rainfall. On the other hand, it is found that the lowlands areas such as the eastern part of the Peninsula are strongly characterized by the northeast monsoonal flow. Based on the results of the Mann-Kendall test, as the trend of the total amount of rainfall and the frequency of wet days during the southwest monsoon decrease at most of the stations, the rainfall intensity increases. In contrast, increasing trends in both the total amount of rainfall and the frequency of wet days were observed at several stations during the northeast monsoon, which give rise to the increasing trend of rainfall intensity. The results for both seasons indicate that there are significantly decreasing trends in the frequency of wet days during the extreme events for most of the stations on the peninsula. However, a smaller number of significant trends was found for extreme intensity.
The caste composition and sex ratio in a mature and an incipient colony of Cryptotermes dudleyi Banks (Isoptera: Kalotermitidae) was studied. Biometric descriptors of both immature and sexual castes were developed. Morphometric analysis revealed that there are four larval instars, a pseudergate, and three nymphal instars in the development of C. dudleyi. To differentiate between the fourth larval instars and the pseudergate, pronotal width and tibial length must be taken into account, because the head width overlaps between the two groups. The number of antennal segments increases in parallel with instar development. The mature colony was headed by a pair of physogastric nymphoid neotenics; the colony also contained multiple pairs of nonphysogastric de-alates and wing-torn alates. The majority of eggs and larvae were confined to galleries that connected to locations where nymphoid neotenics were found, whereas in general only pseudergates and nymphs were found together with de-alates and wing-torn alates. In contrast, the incipient colony contained only a pair of primary reproductives. Nymphs formed a major group in both mature and incipient colonies, as did pseudergates. The sex ratio of the mature colony was slightly but significantly biased in favor of females, whereas it was skewed toward males in the incipient colony. The data also suggested that the soldier caste was female skewed.
To assess the agreement of the optical low-coherence reflectometry (OLCR) device LENSTAR LS900 with partial coherence interferometry (PCI) device IOLMaster and applanation and immersion ultrasound biometry.
Iris-based biometric systems identify individuals based on the characteristics of their iris, since they are proven to remain unique for a long time. An iris recognition system includes four phases, the most important of which is preprocessing in which the iris segmentation is performed. The accuracy of an iris biometric system critically depends on the segmentation system. In this paper, an iris segmentation system using edge detection techniques and Hough transforms is presented. The newly proposed edge detection system enhances the performance of the segmentation in a way that it performs much more efficiently than the other conventional iris segmentation methods.
This study aims to identify the patient-physician communication barriers in the primary healthcare setting in Pulau Penang, Malaysia. A cross-sectional study was designed to attain the objectives of the study. A self-developed 17-item study tool was used to explore respondent's perception about the barriers they have faced while communicating with physician. The reliability scale was applied and internal consistency of the study tool was estimated on the basis of Cronbach's alpha (α = 0.58). The data analysis was conducted using statistical package for social sciences students SPSS 13(®). Chi Square test was used to test the difference between proportions. A total of n = 69 patients responded to this survey. A higher participation was seen by the male respondents, 39 (56.5%). About 52 (76.5%) of the respondents were satisfied with the information provided by the physician. In an effort to identify the patient-physician barriers, a poor understanding among the patients and physician was revealed. 16 (23.5%) respondents disclosed lack of satisfaction from the information provided to them. Overall, it is seen that lack of physician-patient understanding was the main reason that result hindrance in the affective communication. Moreover, there is a possibility that a low level of health literacy among the patients and inability of the physician to affectively listen to patients may be the other factors that result in a deficient communication.
In this paper, a personal verification method using finger vein is presented. Finger vein can be considered more secured compared to other hands based biometric traits such as fingerprint and palm print because the features are inside the human body. In the proposed method, a new texture descriptor called local line binary pattern (LLBP) is utilized as feature extraction technique. The neighbourhood shape in LLBP is a straight line, unlike in local binary pattern (LBP) which is a square shape. Experimental results show that the proposed method using LLBP has better performance than the previous methods using LBP and local derivative pattern (LDP).
This study aimed to develop and examine the validity and reliability of a pregnancy symptoms questionnaire. A total of 214 pregnant women aged 19 to 40 years old were purposive randomly recruited from December 2009 to January 2010 in Antenatal Clinic, Hospital Universiti Sains Malaysia. Pregnant mothers at second and third trimesters were interviewed to complete the Pregnancy Symptoms Questionnaire (PSQ). The PSQ was developed by experts in nutrition, obstetrics and statistics. The PSQ consists of 38 items on frequency and severity of pregnancy symptoms. Factor analysis was done using Promax rotation method to check for construct validity. A total of 16 items which had poor correlation (<0.3) and less important content were removed during the final revise. The 22 remaining items were found to be loaded on the three components (general, constitutional and somatic pain). The overall Cronbach’s alpha coefficient was 0.93 and for each three components ranges from 0.70–0.87. The results suggest that the final PSQ consisting of 22 items is valid and reliable for measuring the frequency and severity of the symptoms experienced during pregnancy. It can be used in nutritional studies related to pregnancy and its outcome.
Keywords: Pregnant mothers; Pregnancy symptoms; Questionnaire; Validation
Study site: Antenatal Clinic, Hospital Universiti Sains Malaysia (HUSM), Kelantan, Malaysia
For the purpose of teaching statistics, lecturers often rely on data from real studies, text book examples or painstakingly created datasets. The process of creating a dataset can be made easier with the utilization of PASW Statistics to generate random values. The objective of this article is to demonstrate the creation of data which are measured on continuous scale, using PASW Statistics menus and syntax.
Response surface methodology (RSM) was used to optimize the concentrations of chitosan and glycerol for coating Berangan banana (Musa sapientum cv. Berangan). The effects of main edible coating components, chitosan (0.5-2.5%, w/w) and glycerol (0-2%, w/w) on weight loss, firmness, total colour difference, total soluble solids content (TSS) and titratable acidity (TA) of coated banana were studied during 10 days of storage at 26±2°C and 40-50% relative humidity. Results showed that the experimental data could be adequately fitted into a second-order polynomial model with coefficient of determination (R 2 ) ranging from 0.745 to 0.930 for all the variables studied. In general, the chitosan concentration appeared to be the most significant (P< 0.1) factor influencing all variables except for TSS. The optimum concentration of chitosan and glycerol were predicted to be 2.02% and 0.18%, respectively. Statistical assessment showed insignificant difference between experimental and predicted values.
Industrial statistics is an important part of the management system in any industry that strives to continuously improve quality and increase productivity and efficiency. That system covers supply chain management, production design and prototyping, production process and marketing. Industrial statisticians, industrial engineers and industrial leaders should work together hand in hand, in the same language, to ensure that the process and products are as expected. The system itself is never complete. Thus, the usefulness, manageability and reliability of all statistical models used in the system are to be considered as first priority, but those skills are not sufficient. Industrial statisticians should also, of course, be able to come and go between the two poles: statistics and industry. This requirement needs a good understanding about the culture of these poles and how to conduct a mutual symbiosis. One of the principal bridges between these cultures is statistical process control (SPC). This paper is to show that modern industry cannot escape from SPC, especially in a multivariate setting. This setting, which characterizes modern industry, consists of two philosophical problems: how to order data and how to measure process variability. Our recent research results sponsored by the Government of Malaysia will be presented to illustrate the challenging statistical problems in modern industry.
As a small-although growing-journal based in Malaysia, the Malaysian Journal of Medical Sciences (MJMS) has faced several challenges in the past, such as promoting our journal as well as making sure our article bank does not go empty. However, we strive to improve ourselves by taking all means necessary to increase the quantity and, most importantly, quality of our publications, as well as to increase our journal's visibility and citability. This editorial will focus on MJMS statistics throughout 2011-where MJMS turned 18-as well as future plans for our journal.
The current study aimed to explore the public views and expectation about a successful communication process between the healthcare providers/physicians and patients in Penang Island, Malaysia. A cross-sectional study was conducted in Penang Island using a 14-item questionnaire. Statistical Package for Social Sciences (SPSS) software version 15.0(®) were used to analyze the collected data. A nonparametric statistics was applied; the Chi-square test was applied to measure the association among the variables. P-values less than 0.05 were considered statistically significant. A total of N (500) respondents have shown willingness to participate in the study with a response rate of 83.3%. The majority 319 (63.9%) have disclosed to communicate with their healthcare providers in the Malay language and about 401 (80.4%) of the respondents were found satisfied with the information provided by the physician. It was a common expectation by the most of the sample to focus more on the patient history before prescribing any medicine. Moreover, about 60.0% of the respondents expected that the healthcare providers must show patience to the patient's queries. The level of satisfaction with the information shared by the healthcare providers was higher among the respondents with a higher education level. Furthermore, patients with higher level of education expect that physician shouldwell understand their views and medical history to prescribe a better therapeutic regimen.
Statistical classification remains the most useful statistical tool for forensic chemists to assess the relationships between samples. Many clustering techniques such as principal component analysis and hierarchical cluster analysis have been employed to analyze chemical data for pattern recognition. Due to the feeble foundation of this statistics knowledge among novice drug chemists, a tetrahedron method was designed to simulate how advanced chemometrics operates. In this paper, the development of the graphical tetrahedron and computational matrices derived from the possible tetrahedrons are discussed. The tetrahedron method was applied to four selected parameters obtained from nine illicit heroin samples. Pattern analysis and mathematical computation of the differences in areas for assessing the dissimilarity between the nine tetrahedrons were found to be user-convenient and straightforward for novice cluster analysts.
This is the first population based study on ocular biometric measurements (OBMs) conducted in Malaysia. Its objective is to measure and compare among children of different ethnicity who have myopia and emmetropia. Subsets of children aged between 7 and 8 years old who participated in a larger population based refractive error study had their axial length, anterior chamber depth, lens thickness and vitreous depth measured using A scan and vertical and horizontal corneal curvature measured using an autokeratorefractometer. Eighty eight of the 870 children (10.1%) examined had myopia. Boys, Chinese and children with myopia had significantly longer axial length and vitreous depth compared to girls, Malay and Indian and children who were emmetropic respectively. Girls and children with myopia had steeper corneal curvature. The baseline OBMs in Malaysian children of different ethnicity are valuable for studies in myopia progression. Like other studies, children with myopia have longer axial length (P <0.001). and vitreous depth (P <0.001) compared to children who are emmetropia (without myopia).
It is possible that different techniques used to measure axial length (AL) and anterior chamber depth (ACD) is the cause of discrepancy in refractive outcomes of cataract surgery. This study evaluated the agreement and repeatability of AL and ACD measurements using immersion and contact A-scan biometry techniques and compared the refractive outcomes from both techniques. Twenty four patients were evaluated for agreement and repeatability of AL and ACD measurements using the two different methods. The results were analyzed using Bland and Altman plots. Another 60 patients with age-related cataract were selected to compare the refractive outcomes between both methods. The IOL power was calculated using Sanders- Retzlaff- Kraff- Theoretical (SRK-T) equation. Refraction was determined between four to six weeks postoperatively and the results were analyzed using paired t-test. The results of this study showed good agreement between both techniques was noted with no significant difference detected between measurements (p > 0.05). Significant correlation was found in all parameters (AL: r = 0.99; p < 0.01, r = 0.99; p < 0.01) ACD: r = 0.91; p < 0.01, r = 0.97; p < 0.01). No significant difference in refractive outcomes of post cataract surgery was detected between the two techniques (p = 0.07). This study concludes that contact A-scan biometry and immersion techniques provide reliable results and should not be the cause of discrepancy in the refractive planned and outcome of cataract surgery.
Rainfalls data have been broadly used in researches including in hydrological and meteorological areas. Two common ways in extracting observations from hourly rainfalls data are the window-based analysis (WBA) and storm-event analysis (SEA) approach. However, the differences in the qualitative and quantitative properties of both methods are still vaguely discussed. The aim of studying these dissimilarities is to understand the effects of each approach in modelling and analysis. The qualitative difference is due to the way the two analyses define the accumulated rainfalls for observations which are referred to as rainfall and storm depths, respectively. The repetitiveness of rainfall depths provide nested structure while the storm depths are considered independent. The quantitative comparisons include their statistical and scaling properties that are linked by the self-similarity concept from simple scaling characteristics. If self-similarity concept
holds, then the rainfall or storm depths follow simple scaling and the analysis would be simplified. The rainfall depths showed clearer simple scaling characteristics compared to the storm depths. Though the storm depths do not yield self-similarity for a large range of storm duration but the characteristics of simple scaling can be observed for a reduced range of the considered duration. In general, the context of the research and the region of the time interval and duration will be an important aspects to consider in choosing which method is best to use for analyzing the data.