Philosophiae Doctor - PhD (Statistics and Population Studies)

Permanent URI for this collection

https://hdl.handle.net/10566/14933

Browse

Now showing 1 - 20 of 28

Estimating household vulnerability to poverty at the municipality level in South Africa using the cluster analysis approach
(University of the Western Cape, 2023) Ahmed Abdelkarim Eldud Omer, Eldud; Tati, Gabriel; Stiegler , Nancy
Influence of data accuracy and non-use of quality information on reproductive health: a comparative study of Nigeria and South Africa
(University of the Western Cape, 2023) Oyekola, Adetooke Bukola; Sathiyasusuman, Appunni; Appunni, Sathiyasusuman
In healthcare settings, information systems play a critical role in providing safe, timely, and effective healthcare services. Decision-making on medical supplies, healthcare providers, service delivery, finance, and governance all depend on access to health information. To improve overall health services and processes, these information systems manage data collection, processing, storage, retrieval, and utilisation. The effectiveness of health systems depends on effective administration and data quality. Irrespective of the significance of health information systems, many low- and middle-income nations, such as South Africa and Nigeria, continue to encounter challenges with data accuracy and the use of high-quality information. Inaccurate data can lead to misinformed policy decisions and resource allocation, hindering efforts to improve reproductive health outcomes. Problems such as incomplete, outdated, unreported data, poor integration, and underutilisation of technology affect data quality and completeness. Data quality impacts decision-making, performance, and the ability to achieve national and international health goals. Government involvement and suitable policies are crucial for addressing these challenges and improving the effectiveness of health information systems.
Handling heteroskedasticity in the linear regression model
(University of the Western Cape, 2022) Farrar, Thomas; Blignaut, Rénette
This research project delves into the problem of heteroskedasticity in the linear regression model. Having defined the problem and its consequences for estimation and inference, a comprehensive literature review of existing methods for diagnosing and correcting for heteroskedasticity is undertaken, with special emphasis on heteroskedasticity tests. New theory on the statistical properties of the Ordinary Least Squares residuals is developed, leading to new models for estimating linear regression error variances. The most important of these models is the Auxiliary Linear Variance Model, which is further classified into sub-types (e.g., clustering, linear, penalised polynomial, spline). Model fitting techniques are discussed, which reduce to quadratic programming problems. An Auxiliary Nonlinear Variance Model is also developed, which can be fitted using a maximum quasi-likelihood method. Techniques for tuning of model hyperparameters and feature selection are discussed. Bootstrap methods of obtaining interval estimates for error variances are also proposed. A new heteroskedasticity test is constructed based on the auxiliary linear variance model. To make existing and new methods of handling heteroskedasticity more accessible to the practitioner, a new package called skedastic has been developed for R statistical software. Its functionality is described in detail.
Violence against women in Burkina Faso: A quantitative and qualitative study
(University of the Western Cape, 2022) Zakaliyat, Bonkoungou; Appunni, Sathiya
Many socio-anthropological and/or quantitative studies have attempted to address the issue of violence against women indirectly by focusing on the perceptions of the actors rather than on the fact of having suffered it directly. This is the case, for example, in Burkina Faso, with certain nationwide studies such as the Demographic and Health Surveys (DHS) and the Multiple Indicator Cluster Surveys (MICS) of 2003, 2006 and 2010. Thus, the direct measurement of the phenomenon, i.e. whether or not the phenomenon has been experienced, is rarely addressed through household surveys.
Determinants of health care use and mothers' preventative and curative health care practices in Burkina Faso
(University of the Western Cape, 2022) Badolo, Hermann; Susuman, A Sathiya
In about two-thirds of all countries in sub-Saharan Africa, low coverage of effective interventions to prevent maternal and child deaths has been attributed to both weaknesses in the supply and demand for health services. These interventions require access to and use of health services. Conceptually, the availability, quality of health care, financial and geographical accessibility, socio-economic and demographics factors and cultural barriers are the main factors associated with health care use. These associated factors and the causes of low utilization of health services have been studied by several authors in Burkina Faso and other countries, often from the point of view of health care demand or supply.
The dynamics of modern method contraception among sexually active unmarried adolescents in Nigeria
(University of the Western Cape, 2022) Ojoniyi, Olaide; Stiegler, Nancy
It is just stating the obvious to aver that young people in all regions are reaching puberty earlier and are habitually engaging in sexual activity at a younger age, and thereafter, marrying later. As a result, they are sexually exposed for a longer time before marriage than has historically been the case, and as such, are at higher risk of unintended pregnancy and sexually transmitted infections. Needless to say, nonmarital sexual activity is increasing among adolescents. However, less than half of those who want to avoid pregnancy are using a modern method of contraception.
Assessment of the potential of hospital birth records to estimate the number of births: A case study of Germiston and Nkomazi Local Municipalities
(University of the Western Cape, 2020) Nhlapo, Mosidi Sarah; Stiegler, Nancy
The advantage of a well-developed health information system is the significant role played by records produced by such a system beyond recording medical history of individuals. They are the foundation for birth registrations which when fully complete is an important tool for acquiring data necessary for planning and monitoring child and maternal health in a country. This study aimed to investigate the potential of hospital birth records to estimate the number of births in the country and supplement birth registrations data. Data was abstracted from public facilities where births occur in two municipalities; Germiston in Gauteng and Nkomazi in Mpumalanga for the period 2014 to 2016. Modified version of the BORN Data Quality Framework (BORN-DQF) of the Ontario Agency for Health Protection and Promotion (2016) was used to assess the contents and quality of hospital birth records.
Challenges of postgraduate students at the University of the Western Cape 2009 - 2013
(University of the Western Cape, 2019) Lewis, Priscilla-Anne; Holtman, Lorna
In South Africa, postgraduate education is a catalyst in national development and poverty alleviation that is widely acknowledged by the state and higher education institutions, such as the University of the Western Cape (UWC). Previously disadvantaged universities in South Africa were systematically moulded by apartheid planning and the prevailing social-economic-political order of the time. The structural legalised differences between historically white and historically black institutions created the key inequities between them. Unjust laws and institutionalised racism caused historical black universities (HBUs), such as the University of the Western Cape, also known as the University for the left, to lag behind with the intake of postgraduate students. Prior to 1994, students, who were fortunate enough to attend university, were mostly limited to studying towards an undergraduate degree, diploma or a certificate course, in the fields of teaching, nursing or law enforcement. The dawn of democracy opened up new possibilities; however, a major sphere of concern, was the need to speedily transform the education system, to make it inclusive for all. Systematically, institutions of higher learning focussed more on postgraduate education, as it was a stepping stone to improve enrolment growth research output, and collaborative partnerships, at national and international level. However, socio-economic factors, such as the lack of funding, were major constraints, as most postgraduate students were challenged to pay registration fees, or accommodation deposits, upon registration.
Differentials in unemployment duration across households in South Africa: A two-level modelling approach
(University of the Western Cape, 2018) Lartey, Nathaniel; Tati, Gabriel
This study aimed to examine the structural changes affecting the duration of unemployment across households in South Africa. It made use of existing datasets from the Labour Force Survey produced by Statistics South Africa, covering a period of six years (2011-2016). Relations among demographic and household variables were explored to determine how they related to unemployment duration. On the basis of the relations identified, a predictive analysis of unemployment duration was attempted using two-level modelling. The results suggest a significant difference in the duration of unemployment, according to the individual socio-demographic characteristics and the household moderating variables. More specifically, the greatest share percentage of both men and women experiencing long-term unemployment were found within the age group 25-34 years. The study also found that the percentage share of Non-White population groups experiencing longer duration of unemployment was more than for the White population group. Another variable found to have great influence on the duration of unemployment was the individual’s previous work experience. Going beyond the individual’s socio-demographic characteristics to consider household variables. It was found that unemployed workers living in households headed by a female are more vulnerable to longer unemployment duration. The study found individuals living in smaller households displaying longer unemployment duration. Also, it was found that individuals living in less endowed households (households where no one or few people were in gainful employment) were more vulnerable to experiencing longer unemployment spells. The study concluded with some recommendations for employment policy and follow-up research.
Fostering collaboration amongst business intelligence, business decision makers and statisticians for the optimal use of big data in marketing strategies
(University of the Western Cape, 2019) De Koker, Louise; Tati, Gabriel
The aim of this study was to propose a model of collaboration adaptable for the optimal use of big data in an organisational environment. There is a paucity of knowledge on such collaboration and the research addressed this gap. More specifically, the research attempted to establish whether leadership, trust and knowledge sharing influence collaboration among the stakeholders identified at large organisations. The conceptual framework underlying this research was informed by collaboration theory and organisational theory. It was assumed that effective collaboration in the optimal use of big data possibly is associated with leadership, knowledge sharing and trust. These concepts were scientifically hypothesised to determine whether such associations exist within the context of big data. The study used a mixed methods approach, combining a qualitative with a quantitative study. The qualitative study was in the form of in-depth interviews with senior managers from different business units at a retail organisation in Cape Town. The quantitative study was an online survey conducted with senior marketing personnel at JSE-listed companies from various industries in Cape Town. A triangulation methodology was adopted, with additional in-depth interviews of big data and analytics experts from both South Africa and abroad, to strengthen the research. The findings of the research indicate the changing role of the statistician in the era of big data and the new discipline of data science. They also confirm the importance of leadership, trust and knowledge sharing in ensuring effective collaboration. Of the three hypotheses tested, two were confirmed. Collaboration has been applied in many areas. Unexpected findings of the research were the role the chief data officer plays in fostering collaboration among stakeholders in the optimal use of big data in marketing strategies, as well as the importance of organisational structure and culture in effective collaboration in the context of big data and data science in large organisations. The research has contributed to knowledge by extending the theory of collaboration to the domain of big data in the organisational context, with the proposal of an integrated model of collaboration in the context of big data. This model was grounded in the data collected from various sources, establishing the crucial new role of the chief data officer as part of the executive leadership and main facilitator of collaboration in the organisation. Collaboration among the specified stakeholders, led by the chief data officer, occurs both horizontally with peers and vertically with specialists at different levels within the organisation in the proposed model. The application of such a model of collaboration should facilitate the successful outcome of the collaborative efforts in data science in the form of financial benefits to the organisation through the optimal use of big data.
Developing a model of school climate unique to secondary schools in South Africa: A multilevel analysis approach
(University of the Western Cape, 2018) Winnaar, Lolita Desiree; Blignaut, Rénette; Zuze, Linda
The educational landscape in South Africa is unique and has also seen many changes since the dawn of democracy more than 20 years ago. The apartheid education system was marred by severe inequalities between schools and, for this reason, the democratic government post 1994 established a number of policies and interventions in an attempt to improve access, equity and quality between schools. The country has made significant advances in improving access to education. This is reflected in the Millennium Development Goals progress indicators showing that, as of 2013, almost all learners between the ages of 7 and 15 were enrolled in schools. While great strides have also been made with regard to equity, evidence shows that many schools in South Africa are still largely inequitable. Education quality, however, is an area that is still of grave concern and the matter requires much attention from educational stakeholders. International studies, such as the Trends in International Mathematics and Science Study (TIMSS) and the Progress in International Reading Literacy Study (PIRLS), use learner performance to measure the quality of the system. Such studies consistently report that South Africa is performing poorly and that large inequalities still exist between schools in the country. Improved quality is associated with effective schools and, in South Africa, only 20% of schools have been found to be functional or effective. Much of research focussed on school effectiveness, both nationally and internationally, however has been explained by factors in the school, including the appropriateness of curriculum content, infrastructure, resources in the school and teacher content knowledge. These factors have been found to be strongly correlated with effective schools.
Inequalities in the use of maternal and reproductive health services in Sierra Leone
(University of the Western Cape, 2019) Tsawe, Mluleki; Susuman, Sathiya
This thesis extends the literature on the trends and magnitude of health inequalities in the area of maternal and reproductive health services in Sierra Leone, and particular across sub-Saharan Africa. It attempted to provide a good understanding of, not only the determinants of maternal and reproductive healthcare use, but also factors that enable health inequalities to exist in Sierra Leone. This is an appropriate topic in population health studies as it aims to address important questions on the research agenda in the context of sub-Saharan Africa, particularly in a country with poor health outcomes such as Sierra Leone. A proper understanding of not only the coverage rates of population health outcomes but also the extent of health inequalities as well as the factors that contribute to these inequalities is crucial for any government. The thesis applied various techniques in the analysis of DHS data (from 2008 and 2013 rounds) in an attempt to answer the research questions.
Missing imputation methods explored in big data analytics
(University of the Western Cape, 2018) Brydon, Humphrey Charles; Blignaut, Renette
The aim of this study is to look at the methods and processes involved in imputing missing data and more specifically, complete missing blocks of data. A further aim of this study is to look at the effect that the imputed data has on the accuracy of various predictive models constructed on the imputed data and hence determine if the imputation method involved is suitable. The identification of the missingness mechanism present in the data should be the first process to follow in order to identify a possible imputation method. The identification of a suitable imputation method is easier if the mechanism can be identified as one of the following; missing completely at random (MCAR), missing at random (MAR) or not missing at random (NMAR). Predictive models constructed on the complete imputed data sets are shown to be less accurate for those models constructed on data sets which employed a hot-deck imputation method. The data sets which employed either a single or multiple Monte Carlo Markov Chain (MCMC) or the Fully Conditional Specification (FCS) imputation methods are shown to result in predictive models that are more accurate. The addition of an iterative bagging technique in the modelling procedure is shown to produce highly accurate prediction estimates. The bagging technique is applied to variants of the neural network, a decision tree and a multiple linear regression (MLR) modelling procedure. A stochastic gradient boosted decision tree (SGBT) is also constructed as a comparison to the bagged decision tree. Final models are constructed from 200 iterations of the various modelling procedures using a 60% sampling ratio in the bagging procedure. It is further shown that the addition of the bagging technique in the MLR modelling procedure can produce a MLR model that is more accurate than that of the other more advanced modelling procedures under certain conditions. The evaluation of the predictive models constructed on imputed data is shown to vary based on the type of fit statistic used. It is shown that the average squared error reports little difference in the accuracy levels when compared to the results of the Mean Absolute Prediction Error (MAPE). The MAPE fit statistic is able to magnify the difference in the prediction errors reported. The Normalized Mean Bias Error (NMBE) results show that all predictive models constructed produced estimates that were an over-prediction, although these did vary depending on the data set and modelling procedure used. The Nash Sutcliffe efficiency (NSE) was used as a comparison statistic to compare the accuracy of the predictive models in the context of imputed data. The NSE statistic showed that the estimates of the models constructed on the imputed data sets employing a multiple imputation method were highly accurate. The NSE statistic results reported that the estimates from the predictive models constructed on the hot-deck imputed data were inaccurate and that a mean substitution of the fully observed data would have been a better method of imputation. The conclusion reached in this study shows that the choice of imputation method as well as that of the predictive model is dependent on the data used. Four unique combinations of imputation methods and modelling procedures were concluded for the data considered in this study.
Proximate determinants of fertility and contraceptive use among currently married women in Ethiopia
(University of the Western Cape, 2017) Lailulo, Yishak Abraham; Susuman, A. Sathiya
Fertility is one of the elements in population dynamics that has significant contribution towards changing population size and structure over time. In Ethiopia, fertility dropped only slightly between 2000 and 2005, from 5.5 children per woman to 5.4, and then decreased further to 4.8 children in 2011(CSA, 2012). Although a slight decreasing trend has shown from year to year, it is still high as compared to developed nations (Tewodros,2011). The age at which childbearing begins is an important factor in the overall level of fertility as well as of the health and well-being of the mother and the child (CSA, 2012).In 2008, of the 1.4 billion women in the developing world of reproductive age (15-49 years), more than 570 women die per 100,000 live births, and 70 percent of them die due to totally avoidable reasons (World Bank,2010). These women live in countries where their status is poor to extremely poor, and these conditions threaten their health in many ways. Sedgh, Hussain, Bankole, and Singh (2007) found that wherever fertility is high, maternal and infant and child mortality rates are high. In addition to these, high fertility and shorter birth intervals affect the survival chance of children and the health status of mothers. Demographic and Health Surveys (DHS) data from 18 developing countries in Asia, Latin America, Africa, and the Middle East showed that a birth interval of threeyears increases the survival status of under-five children (Rutstein, 2003). Moreover, a similar survey of 52 developing countries found that markedly short birth intervals have a negative effect on pregnancy outcomes, increased morbidity in pregnancy, and increased infant and child mortality (Rutstein,2005). Setty-Venugopal and Upadhyay (2002) have documented that, in Sub-Saharan Africa, about 60% of women deliver the next child before the index child celebrates his/her third birthday, and almost a quarter before the second birth day.
Survival modelling and analysis of HIV/AIDS patients on HIV care and antiretroviral treatment to determine longevity prognostic factors
(University of the Western Cape, 2016) Maposa, Innocent; Blignaut, Renette
The HIV/AIDS pandemic has been a torment to the African developmental agenda, especially the Southern African Development Countries (SADC), for the past two decades. The disease and condition tends to affect the productive age groups. Children have also not been spared from the severe effects associated with the disease. The advent of antiretroviral treatment (ART) has brought a great relief to governments and patients in these regions. More people living with HIV/AIDS have experienced a boost in their survival prospects and hence their contribution to national developmental projects. Survival analysis methods are usually used in biostatistics, epidemiological modelling and clinical research to model time to event data. The most interesting aspect of this analysis comes when survival models are used to determine risk factors for the survival of patients undergoing some treatment or living with a certain disease condition. The purpose of this thesis was to determine prognostic risk factors for patients' survival whilst on ART. The study sought to highlight the risk factors that impact the survival time negatively at different survival time points. The study utilized a sample of paediatric and adult datasets from Namibia and Zimbabwe respectively. The paediatric dataset from Katutura hospital (Namibia) comprised of the adolescents and children on ART, whilst the adult dataset from Bulawayo hospital (Zimbabwe) comprised of those patients on ART in the 15 years and above age categories. All datasets used in this thesis were based on retrospective cohorts followed for some period of time. Different methods to reduce errors in parameter estimation were employed to the datasets. The proportional hazards, Bayesian proportional hazards and the censored quantile regression models were utilized in this study. The results from the proportional hazards model show that most of the variables considered were not signifcant overall. The Bayesian proportional hazards model shows us that all the considered factors had different risk profiles at the different quartiles of the survival times. This highlights that by using the proportional hazards models, we only get a fixed constant effect of the risk factors, yet in reality, the effect of risk factors differs at different survival time points. This picture was strongly highlighted by the censored quantile regression model which indicated that some variables were significant in the early periods of initiation whilst they did not significantly affect survival time at any other points in the survival time distribution. The censored quantile regression models clearly demonstrate that there are significant insights gained on the dynamics of how different prognostic risk factors affect patient survival time across the survival time distribution compared to when we use proportional hazards and Bayesian propotional hazards models. However, the advantages of using the proportional hazards framework, due to the estimation of hazard rates as well as it's application in the competing risk framework are still unassailable. The hazard rate estimation under the censored quantile regression framework is an area that is still under development and the computational aspects are yet to be incorporated into the mainstream statistical softwares. This study concludes that, with the current literature and computational support, using both model frameworks to ascertain the dynamic effects of different prognostic risk factors for survival in people living with HIV/AIDS and on ART would give the researchers more insights. These insights will then help public health policy makers to draft relevant targeted policies aimed at improving these patients' survival time on treatment.
Health inequalities of children in sub-Saharan Africa from 1990 to 2010 : comparative analysis using data from Health and Demographic Surveys
(University of the Western Cape, 2016) Bado, Aristide Romaric; Susuman, Sathiya A.
This study is based on the assumption that the under-five mortality rate, in recent decades, has declined, particularly in developing countries. However, all the social strata across many countries do not seem to benefit from this reduction of mortality - and mortality remains abnormally high among children especially those from underprivileged social strata. This research is, therefore, a holistic approach to analyse and quantify the inequalities of health among children under five in sub-Saharan Africa over the last two decades (1990-2010). The research sought to investigate the trend and determinants of health inequalities of under-five years (mortality and morbidity) in sub-Saharan Africa (SSA) from 1990 to 2010. An essential point has been devoted to the decomposition of effects and analysis of the contribution of the factors explaining these inequalities. The data used in the study come from Demographic and Heath Surveys (DHS) done between 1990 and 2015 in sub-Saharan Africa countries. In order to analyse the inequalities in trends of mortality and morbidity of children, different selected countries that have conducted at least three DHS during the 1990-2010 period. Several statistical methods were used for data analysis. There were four chapters which is prepared with an article style. For the first paper titled "Decomposing Inequalities in Under- Five Mortality in Selected African Countries", concentration index (CI) and Generalised Linear Model (GLM) with a logit link were used to analyse and measure under 5 mortality inequalities and the associated factors. This paper has been published in the Iranian Journal of Public Health. For the second paper titled "Determinants of Under-Five Mortality in Burkina Faso: A Concentration Dimension". The study used logistics regression and Oaxaca-Blinder decomposition method for the binary outcome to analyse data was involved. For data analysis of the third paper titled "Women Education, Health Inequalities in Under-Five Mortality in sub-Saharan Africa, 1990 – 2013", logistic regression and Bius's decomposition method were used to examine the effect of mother's education level on childhood mortality. In the fourth paper titled "Trends and Risk Factors for Childhood Diarrheal in sub-Saharan Countries (1990-2010): Assessing the Neighbourhood Inequalities", a multilevel logistic regression modelling was used to determine the fixed and random effects of the risk factors associated with the diarrheal morbidity. The work carried out during this on-going thesis helps to understand the magnitude of inequalities in under-five mortality in sub-Saharan countries. The findings showed that the contributing factors of inequalities of child mortality were birth order, maternal age, parity and household size. With regards to the relationship between mother's education level and inequalities in mortality of children under-five in sub-Saharan Africa, findings showed that children of mothers who did not attend school have a higher rate of death compared to those who had been to school. However, we have observed that the inequalities have narrowed over time. The results showed the risk factors of diarrheal morbidity varied from one country to another, but the main factors included: child's age, the size of the child at birth, the quality of the main floor material, mother's education and her occupation, type of toilet, and place of residence. In conclusion, the results of this study show that inequalities in under-five mortality are still important among different social strata in sub-Saharan Africa countries. It is then urgent to take actions to save the lives of children in disadvantaged social strata.
Imputation techniques for non-ordered categorical missing data
(University of the Western Cape, 2016) Karangwa, Innocent; Kotze, Danelle; Blignaut, Renette
Missing data are common in survey data sets. Enrolled subjects do not often have data recorded for all variables of interest. The inappropriate handling of missing data may lead to bias in the estimates and incorrect inferences. Therefore, special attention is needed when analysing incomplete data. The multivariate normal imputation (MVNI) and the multiple imputation by chained equations (MICE) have emerged as the best techniques to impute or fills in missing data. The former assumes a normal distribution of the variables in the imputation model, but can also handle missing data whose distributions are not normal. The latter fills in missing values taking into account the distributional form of the variables to be imputed. The aim of this study was to determine the performance of these methods when data are missing at random (MAR) or completely at random (MCAR) on unordered or nominal categorical variables treated as predictors or response variables in the regression models. Both dichotomous and polytomous variables were considered in the analysis. The baseline data used was the 2007 Demographic and Health Survey (DHS) from the Democratic Republic of Congo. The analysis model of interest was the logistic regression model of the woman’s contraceptive method use status on her marital status, controlling or not for other covariates (continuous, nominal and ordinal). Based on the data set with missing values, data sets with missing at random and missing completely at random observations on either the covariates or response variables measured on nominal scale were first simulated, and then used for imputation purposes. Under MVNI method, unordered categorical variables were first dichotomised, and then K − 1 (where K is the number of levels of the categorical variable of interest) dichotomised variables were included in the imputation model, leaving the other category as a reference. These variables were imputed as continuous variables using a linear regression model. Imputation with MICE considered the distributional form of each variable to be imputed. That is, imputations were drawn using binary and multinomial logistic regressions for dichotomous and polytomous variables respectively. The performance of these methods was evaluated in terms of bias and standard errors in regression coefficients that were estimated to determine the association between the woman’s contraceptive methods use status and her marital status, controlling or not for other types of variables. The analysis was done assuming that the sample was not weighted fi then the sample weight was taken into account to assess whether the sample design would affect the performance of the multiple imputation methods of interest, namely MVNI and MICE. As expected, the results showed that for all the models, MVNI and MICE produced less biased smaller standard errors than the case deletion (CD) method, which discards items with missing values from the analysis. Moreover, it was found that when data were missing (MCAR or MAR) on the nominal variables that were treated as predictors in the regression model, MVNI reduced bias in the regression coefficients and standard errors compared to MICE, for both unweighted and weighted data sets. On the other hand, the results indicated that MICE outperforms MVNI when data were missing on the response variables, either the binary or polytomous. Furthermore, it was noted that the sample design (sample weights), the rates of missingness and the missing data mechanisms (MCAR or MAR) did not affect the behaviour of the multiple imputation methods that were considered in this study. Thus, based on these results, it can be concluded that when missing values are present on the outcome variables measured on a nominal scale in regression models, the distributional form of the variable with missing values should be taken into account. When these variables are used as predictors (with missing observations), the parametric imputation approach (MVNI) would be a better option than MICE.
Some non-standard statistical dependence problems
(University of the Western Cape, 2016) Bere, Alphonce; Koen, Chris
The major result of this thesis is the development of a framework for the application of pair-mixtures of copulas to model asymmetric dependencies in bivariate data. The main motivation is the inadequacy of mixtures of bivariate Gaussian models which are commonly fitted to data. Mixtures of rotated single parameter Archimedean and Gaussian copulas are fitted to real data sets. The method of maximum likelihood is used for parameter estimation. Goodness-of-fit tests performed on the models giving the highest log-likelihood values show that the models fit the data well. We use mixtures of univariate Gaussian models and mixtures of regression models to investigate the existence of bimodality in the distribution of the widths of autocorrelation functions in a sample of 119 gamma-ray bursts. Contrary to previous findings, our results do not reveal any evidence of bimodality. We extend a study by Genest et al. (2012) of the power and significance levels of tests of copula symmetry, to two copula models which have not been considered previously. Our results confirm that for small sample sizes, these tests fail to maintain their 5% significance level and that the Cramer-von Mises-type statistics are the most powerful.
Determinants of youth sexual behaviours and knowledge of reproductive tract infections (RTIs) and sexually transmitted infections (STIs) in Malawi : evidenced from the Demographic Health Survey 2010
(University of the Western Cape, 2015) Ningpuanyeh, Wilson Chialepeh; Susuman, Sathiya A.
The sexual behaviour of youths is believed to play a role in the spread of SexuallyTransmitted Infections (STIs) and Reproductive Tract Infections (RTIs). This study examinesthe determinants of youth sexual behaviours and knowledge of reproductive tract infections (RTIs) and sexually transmitted infections (STIs) in Malawi. It explores rural/urbandifferentials in sexual behaviours using indicators such as early sexual initiation, multiplesexual partnerships, and non-use of condoms, in order to establish policy recommendationstoward improving sexual behaviour among youths. The Malawi Demographic Health Survey2010 data was used. Out of a sample of 2987 males and 9559 females aged 15-24 years,5652 females and 1405 males (condom use), 675 females and 511 males (inconsistentcondom use), 6470 females and 2026 males (multiple sexual partnerships (MSP)), and 15217females and 1405 males (early sexual debut) were filtered in the study.Chi-square and logistic regression techniques were performed to test for association betweensexual behaviour indicators and socio-demographic variables. The prevalence of non-use ofcondom was higher among catholic females (OR=1.11), lower among Muslim males (OR=0.81) and higher among CCAP females (OR=1.19). Muslim females were (OR=1.42) more likely to initiate sexual activities early, while Muslim males were (OR= 0.57) less likelyto initiate sexually activities early. Females in the central region (OR=1.51) and catholicmales (OR=1.63) were more likely to have more sexual partners.Encouraging these young people to be faithful to one uninfected partner, abstinence fromsexual activities, use condoms consistently and delay sexual initiation will help curb the spread of STIs in Malawi.
A forgotten diaspora : forced Indian Migration to the Cape Colony, 1658 to 1834
(University of the Western Cape, 2015) Rama, Parbavati; Shell, Robert C. H.; Stiegler, Nancy
This thesis aims to explore Indian forced migration to the Cape Colony from 1658 to 1834. The forgotten diaspora‘ of its title refers to the first Indians who had come to the shores of South Africa, long before the arrival—between 1860 and 1911—of the indentured Indians. This diaspora has been forgotten, partially because these migrants came as slaves. The author uses data extracted from the newly transcribed Master of the Orphan Chamber (MOOC) series and slave transfers which are housed in the Western Cape Provincial Archives and Records Service (WCARS). The Cape colonial data is considered among the best in the world. Earlier historians such as Victor de Kock, Anna Böeseken, Frank Bradlow and Margaret Cairns, have made us aware of their existence primarily through Transportenkennis and Schepenkennis (transport and shipping information) documents in the Deeds Registry. Not nearly enough, however, is known about these Indian slaves, especially about those who arrived between 1731 and 1834. These lacunae include the number of arrivals; their sex ratios; ages and origins; and the circumstances under which they came. This thesis aims to construct a census of Indian slaves brought to the Cape from 1658 to 1834—along the lines of Philip Curtin's aggregated census of the Trans- Atlantic slave trade, but based on individual case level data coded directly from primary sources. This is the first time the size of the creole population born at the Cape will be established.

Browse

collection.page.browse.recent.head