Displaying all 12 publications

Abstract:
Sort:
  1. Wan Rozita, W.M., Rasimah, A., Mazrura, S., Lim, K.H., Thana, S.
    MyJurnal
    Analysis of count event data such as mortality cases, were often modelled using Poisson regression model. Maximum likelihood procedures were used by using SAS software to estimate the model parameters of a Poisson regression model. However, the Negative Binomial distribution has been widely suggested as the alternative to the Poisson when there is proof of overdispersion phenomenon. We modelled the mortality cases as the dependent variable using Poisson and Negative Binomial regression and compare both of the models. The procedures were done in SAS by using the function PROC GENMOD. The results showed that the mortality data in Poisson regression exhibit large ratio values between deviance to degree of freedom which indicate model misspecification or overdispersion. This large ratio was found to be reduced in Negative Binomial regression. The Normal probability plot of Pearson residual confirmed that the Negative Binomial regression is a better model than Poisson regression in modelling the mortality data. The objective of this study is to compare the goodness of fit of Poisson regression model and Negative Binomial regression model in the application of air pollution epidemiologic time series study by using SAS software.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  2. Nur Hanim Mohd Salleh, Husna Hasan
    MyJurnal
    Annual air temperature data obtained from twenty-two meteorological stations across Malaysia are modeled using multiple regression. A correlation test was conducted to find statistical relationship between each of the dependent variables: annual maximum and annual average air temperature and predictor variables: longitude, latitude, elevation and wind speed. Regression models using least square estimation method were developed relating the dependent variables to independent variables and the adequacy of the models is determined by the coefficient of determination. The result shows that the longitude and wind speed factors have a significant influence on the annual air temperature in Malaysia.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  3. Rubayah Yakob, Zulkornain Yusop, Alias Radam, Noriszura Ismail
    Sains Malaysiana, 2014;43:1439-1450.
    The objective of this study was to identify the exogenous variables of risk and investment management efficiency by using a two-stage data envelopment analysis (DEA) method. The first stage involves obtaining the efficiency scores of risk and investment management via DEA that requires only the traditional inputs and outputs. In the second stage, the Tobit regression analysis is conducted in which the efficiency score obtained from the first stage is treated as a dependent variable, while the exogenous factors are considered to be independent variables. The exogenous factors consist of operating systems, organizational form, consumer preference and size. The results showed that the mutual company as well as the takaful system demonstrate better risk management performance than their stock and conventional system counterparts. In addition, size is also a significant indicator for risk management efficiency in which the larger insurer/takaful operator exhibits better risk management performance than the smaller one. However, consumer preference is found to be insignificantly correlated with the efficiency of risk management. In contrast, with risk management, organizational form, operating system and size are not indicators of the investment management efficiency, but consumer preference is significantly and positively associated with investment management efficiency.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  4. Loh, S.Y.
    JUMMEC, 2009;12(1):31-34.
    MyJurnal
    In a clinical controlled trial involving repeated measures of continuous outcomes such as quality of life, distress, pain, activity level at baseline and after treatment, the possibilities of analyzing these outcomes can be numerous with quite varied findings. This paper examined four methods of statistical analysis using data from an outcome study of a clinical controlled trial to contrast the statistical power on those with baseline adjustment. In this study, data from a CCT with women with breast cancer were utilized. The experiment (n=67) and control (n=74) were about equal ratio. Four method of analysis were utilized, two using ANOVA for repeated measures and two using ANCOVA. The multivariate between subjects of the combined dependents variables and the univariate between subjects test were examined to make a judgement of the statistical power of each method. The results showed that ANCOVA has the highest statistical power. ANOVA using raw data is the least power and is the worst method with no evidence of an intervention effect even when the treatment by time interaction is statistically significant. In conclusion, ANOVA using raw data is the worst method with the least power whilst ANCOVA using baseline as covariate has the highest statistical power to detect a treatment effect other than method. The second best method as shown in this study was in using change scores of the repeated measures.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  5. Imawana RA, Smith DR, Goodson ML
    Ann Gastroenterol, 2020 06 06;33(5):485-494.
    PMID: 32879595 DOI: 10.20524/aog.2020.0507
    Background: The current literature suggests a protective benefit of Helicobacter pylori (H. pylori) infection against inflammatory bowel disease (IBD). Here we assessed whether this effect varied by IBD subtype-Crohn's disease (CD) or ulcerative colitis (UC)-and geographic region: East Asia, Europe (non-Mediterranean) or Mediterranean region.

    Methods: A database search was performed up to July 2019 inclusive for all studies that compared H. pylori infection in IBD patients vs. non-IBD controls. The relative risk (RR) was used to quantify the association between IBD and H. pylori, and the effects were combined across studies using a mixed-effects meta-regression model, which included IBD subtype and geographic region as categorical moderator variables.

    Results: Our meta-regression model exhibited moderate heterogeneity (I2=48.74%). Pooled RR depended on both region (P=0.02) and subtype (P<0.001). Pooled RRs were <1 for all subtype and region combinations, indicative of a protective effect of H. pylori against IBD. The pooled RR was 28% (9%, 50%; P=0.001) greater for UC vs. CD and 43% (4%, 96%; P=0.02) greater for Mediterranean countries vs. East Asia. The pooled RR was 18% (-13%, 60%; P=0.48) greater for Europe vs. East Asia and 21% (-13%, 68%; P=0.42) greater for Mediterranean vs. Europe, though these differences were not statistically significant.

    Conclusions: The protective effect of H. pylori on IBD varied by both subtype (more protection against CD vs. UC) and region (East Asia more protected than Mediterranean regions). Variation due to these effects could provide insight into IBD etiology.

    Matched MeSH terms: Effect Modifier, Epidemiologic
  6. Ahadzadeh AS, Rafik-Galea S, Alavi M, Amini M
    Health Psychol Open, 2018 06 10;5(1):2055102918774251.
    PMID: 29977587 DOI: 10.1177/2055102918774251
    This study examined the correlation between body mass index as independent variable, and body image and fear of negative evaluation as dependent variables, as well as the moderating role of self-esteem in these correlations. A total of 318 Malaysian young adults were conveniently recruited to do the self-administered survey on the demographic characteristics body image, fear of negative evaluation, and self-esteem. Partial least squares structural equation modeling was used to test the research hypotheses. The results revealed that body mass index was negatively associated with body image, while no such correlation was found with fear of negative evaluation. Meanwhile, the negative correlation of body mass index with body image was stronger among those with lower self-esteem, while a positive association of body mass index with fear of negative evaluation was significant only among individuals with low self-esteem.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  7. Wah, Yap Bee, Nurain Ibrahim, Hamzah Abdul Hamid, Shuzlina Abdul-Rahman, Fong, Simon
    MyJurnal
    Feature selection has been widely applied in many areas such as classification of spam emails, cancer cells, fraudulent claims, credit risk, text categorisation and DNA microarray analysis. Classification involves building predictive models to predict the target variable based on several input variables (features). This study compares filter and wrapper feature selection methods to maximise the classifier accuracy. The logistic regression was used as a classifier while the performance of the feature selection methods was based on the classification accuracy, Akaike information criteria (AIC), Bayesian information criteria (BIC), Area Under Receiver operator curve (AUC), as well as sensitivity and specificity of the classifier. The simulation study involves generating data for continuous features and one binary dependent variable for different sample sizes. The filter methods used are correlation based feature selection and information gain, while the wrapper methods are sequential forward and sequential backward elimination. The simulation was carried out using R, an open-source programming language. Simulation results showed that the wrapper method (sequential forward selection and sequential backward elimination) methods were better than the filter method in selecting the correct features.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  8. Awang H, Mansor N
    Saf Health Work, 2018 Sep;9(3):347-351.
    PMID: 30370168 DOI: 10.1016/j.shaw.2017.11.001
    Background: The success of an injury intervention program can be measured by the proportion of successful return to work (RTW). This study examined factors of successful return to employment among workers suffering from work-related injuries.

    Methods: Data were obtained from the Social Security Organization, Malaysia database consisting of 10,049 RTW program participants in 2010-2014. The dependent variable was the RTW outcome which consisted of RTW with same employer, RTW with new employer or unsuccessful return. Multinomial logistic regression was performed to test the likelihood of successful return with same employer and new employer against unsuccessful return.

    Results: Overall, 65.3% of injured workers were successfully returned to employment, 52.8% to the same employer and 12.5% to new employer. Employer interest; motivation; age 30-49 years; intervention less than 9 months; occupational disease; injuries in the lower limbs, upper limbs, and general injuries; and working in the manufacturing, services, and electrical/electronics were associated with returning to work with the same employer against unsuccessful return. Male, employer interest, motivation, age 49 years or younger, intervention less than 6 months, occupational disease, injuries in the upper limbs and services sector of employment were associated with returning to new employer against unsuccessful return.

    Conclusion: There is a need to strengthen employer commitment for early and intensified intervention that will lead to improvement in the RTW outcome.

    Matched MeSH terms: Effect Modifier, Epidemiologic
  9. Foong HF, Hamid TA, Ibrahim R, Haron SA
    Aging Ment Health, 2018 04;22(4):483-488.
    PMID: 28060527 DOI: 10.1080/13607863.2016.1274376
    OBJECTIVES: Research has found that depression in later life is associated with cognitive impairment. Thus, the mechanism to reduce the effect of depression on cognitive function is warranted. In this paper, we intend to examine whether intrinsic religiosity mediates the association between depression and cognitive function.

    METHOD: The study included 2322 nationally representative community-dwelling elderly in Malaysia, randomly selected through a multi-stage proportional cluster random sampling from Peninsular Malaysia. The elderly were surveyed on socio-demographic information, cognitive function, depression and intrinsic religiosity. A four-step moderated hierarchical regression analysis was employed to test the moderating effect. Statistical analyses were performed using SPSS (version 15.0).

    RESULTS: Bivariate analyses showed that both depression and intrinsic religiosity had significant relationships with cognitive function. In addition, four-step moderated hierarchical regression analysis revealed that the intrinsic religiosity moderated the association between depression and cognitive function, after controlling for selected socio-demographic characteristics.

    CONCLUSION: Intrinsic religiosity might reduce the negative effect of depression on cognitive function. Professionals who are working with depressed older adults should seek ways to improve their intrinsic religiosity as one of the strategies to prevent cognitive impairment.

    Matched MeSH terms: Effect Modifier, Epidemiologic
  10. Lew B, Chistopolskaya K, Liu Y, Talib MA, Mitina O, Zhang J
    Crisis, 2020 Mar;41(2):82-88.
    PMID: 30935245 DOI: 10.1027/0227-5910/a000604
    Background: According to the strain theory of suicide, strains, resulting from conflicting and competing pressures in an individual's life, are hypothesized to precede suicide. But social support is an important factor that can mitigate strains and lessen their input in suicidal behavior. Aims: This study was designed to assess the moderating role of social support in the relation between strain and suicidality. Methods: A sample of 1,051 employees were recruited in Beijing, the capital of China, through an online survey. Moderation analysis was performed using SPSS PROCESS Macro. Social support was measured with the Multidimensional Scale of Perceived Social Support, and strains were assessed with the Psychological Strains Scale. Results: Psychological strains are a good predictor of suicidality, and social support, a basic need for each human being, moderates and decreases the effects of psychological strains on suicidality. Limitations: The cross-sectional survey limited the extent to which conclusions about causal relationships can be drawn. Furthermore, the results may not be generalized to the whole of China because of its diversity. Conclusion: Social support has a tendency to mitigate the effects of psychological strains on suicidality.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  11. Ismail, I., Yap, B.W., Abidin, A.S.Z.
    MyJurnal
    Prolonged mechanical ventilation (PMV) is associated with increase in mortality and resource utilisation as well as hospitalisation costs. This study evaluates the risk factors of PMV. A retrospective study was conducted involving 890 paediatric patients comprising 237 neonates, 306 infants, 223 of pre-school age and 124 who are of school going age. The data mining decision trees algorithms and logistic regression was employed to develop predictive models for each age category. The independent variables were classified into four categories, that is, demographic data, admission factors, medical factors and score factors. The dependent variable is the duration of ventilation where it is categorized 0 denoting non-PMV and 1 denoting PMV. The performances of three decision tree models (CHAID, CART and C5.0) and logistic regression were compared to determine the best model. The results indicated that the decision tree outperformed the logistic regression model for all age categories, given its good accuracy rate for testing dataset. Decision trees results identified length of stay and inotropes as significant risk factors in all age categories. PRISM 12 hours and principal diagnosis were identified as significant risk factors for infants.
    Matched MeSH terms: Effect Modifier, Epidemiologic
  12. Wessells KR, Arnold CD, Stewart CP, Prado EL, Abbeddou S, Adu-Afarwuah S, et al.
    Am J Clin Nutr, 2021 11 02;114(Suppl 1):68S-94S.
    PMID: 34590114 DOI: 10.1093/ajcn/nqab276
    BACKGROUND: Small-quantity lipid-based nutrient supplements (SQ-LNSs) have been shown to reduce the prevalence of child anemia and iron deficiency, but effects on other micronutrients are less well known. Identifying subgroups who benefit most from SQ-LNSs could support improved program design.

    OBJECTIVES: We aimed to identify study-level and individual-level modifiers of the effect of SQ-LNSs on child hemoglobin (Hb), anemia, and inflammation-adjusted micronutrient status outcomes.

    METHODS: We conducted a 2-stage meta-analysis of individual participant data from 13 randomized controlled trials of SQ-LNSs provided to children 6-24 mo of age (n = 15,946). We generated study-specific and subgroup estimates of SQ-LNSs compared with control, and pooled the estimates using fixed-effects models. We used random-effects meta-regression to examine potential study-level effect modifiers.

    RESULTS: SQ-LNS provision decreased the prevalence of anemia (Hb < 110 g/L) by 16% (relative reduction), iron deficiency (plasma ferritin < 12 µg/L) by 56%, and iron deficiency anemia (IDA; Hb < 110 g/L and plasma ferritin <12 µg/L) by 64%. We observed positive effects of SQ-LNSs on hematological and iron status outcomes within all subgroups of the study- and individual-level effect modifiers, but effects were larger in certain subgroups. For example, effects of SQ-LNSs on anemia and iron status were greater in trials that provided SQ-LNSs for >12 mo and provided 9 (as opposed to <9) mg Fe/d, and among later-born (than among first-born) children. There was no effect of SQ-LNSs on plasma zinc or retinol, but there was a 7% increase in plasma retinol-binding protein (RBP) and a 56% reduction in vitamin A deficiency (RBP effect modification by individual-level characteristics.

    CONCLUSIONS: SQ-LNSs can substantially reduce the prevalence of anemia, iron deficiency, and IDA among children across a range of individual, population, and study design characteristics. Policy-makers and program planners should consider SQ-LNSs within intervention packages to prevent anemia and iron deficiency.This trial was registered at www.crd.york.ac.uk/PROSPERO as CRD42020156663.

    Matched MeSH terms: Effect Modifier, Epidemiologic
Filters
Contact Us

Please provide feedback to Administrator ([email protected])

External Links