M.Sc. (Mathematical Statistics) / In this dissertation we investigate the South-African interest rate market by analyzing the Johannesburg Interbank Agreed rate (JIBAR) and the South-African three-month treasurybill rate. In particular, we assess the goodness-of-fit of some well known parametric singlefactor short rate models. In all the data sets investigated, we firstly found the interest rate increments to exhibit severe nonnormalities, which is also found to be the case in numerous other empirical studies. Secondly, we reject the model fit for the various parametric short rate models tested. Thirdly, we found strong evidence to support the presence of jumps in all the data sets and that interest rate increments mostly exhibit fat-tailed distributions. Consequently, we tested the ability of diffusion models, driven by Brownian motions, to generate jump induced nonnormalities via a nonparametric test of diffusion model fit. The nonparametric short rate model was rejected, i.e diffusion models are misspecified. Lastly, since diffusion models are misspecified we investigated whether a jump-diffusion model can be fitted to the data with higher accuracy. In conclusion we find that a jump-diffusion model, namely the Vasiˇcek jump-diffusion model, can adequately generate the jump induced nonnormalities present in each of the data sets.

Fertility is one of the major tenets of demography. Its importance lies in the determination of fertility trends in a country, in a specific time period. These statistical inferences of fertility play an imperative role in population policy formation and planning. Thus the importance of the measurement of fertility remains undisputed. Due to the significance of fertility, its measurement and its profound impact on societies, acknowledging and addressing the quality of fertility data is of great importance. This research study was conceived in response to the above concern. This study aims at addressing and providing insight into birth history data irregularities and determining interventions of working with this issue in the context of South Africa. Through secondary analysis (i.e. descriptive exploratory and comparative analysis) the study sought to firstly establish a demographic profile of women associated with inconsistent and inaccurate reporting of their birth histories. Secondly the research attempted to ascertain a relationship between the socio-economic statuses of individuals and retrospective reporting. A third objective was to note the sex-selectiveness of reporting (i.e. were more girls or boys reported or misreported on in the retrospective birth histories). The study has established that older, married women with some educational attainment, of rural areas from either the middle and lower income categories tend to misreport more frequently than their converse counterparts. Furthermore, a plausible relationship between the socio-economic statuses of individuals was observed. In terms of the sex-selectiveness of reporting, in general, boys were reported on more consistently than girls. However in certain cases, it was found that rural and middle income women reported accurately on girl children born alive and dead girl children. Recommendations made with respect to improve the quality of fertility data for include the proper training of enumerators and data capturers, quality control during data collection, testing of questionnaires, dealing with social, cultural and language barriers and the reinforcement of publicity campaigns for censuses and surveys. / Thesis (M.A.)-University of KwaZulu-Natal, Durban, 2010.

The principal objectives of this empirical study were to test the hypothesis that eduction is a major determinant of people's earnings differentials and to calculate private and social rates of return to education of blacks in South Africa excluding Transkei, Bophuthatswana, Venda and Ciskei. Basically, the data for working men and women used in the study were extracted from the 1985 current Population survey files comprising a sample representative of the black population. Lifetime earnings profiles are constructed from these data for five educational levels, namely, no schooling up to standard 1, standards 2 to 4, standards 5 to 7, standards 8 to 9 and standard 10. Schooling is assumed to account for 60% of the income differentials between these profiles, after adjustment for the differing probabilities of finding work of persons in specific age-education groups. Imputed average household outlays on schooling are taken as the private direct cost of education supplemented by estimates of per pupil spending by the various government departments responsible for black schooling for calculation of the social costs per year of primary and secondary schooling. Indirect cost in the form of imputed foregone earnings are included from standard 5 (age 15) onwards. The resulting private internal rates of return to education of males are about 16% at primary level and 24% for secondary schooling. Corresponding social rates of return are about 6% for primary and 15% for secondary education. The estimates for females indicate that between no schooling and standards 2 to 4 level, the private and social rates of return are -1% and -4% respectively, from standards 2 to 4 to standards 5 to 7 level, private returns of 12% and social returns of 4% are reported and for the remaining secondary school phases private returns of 32% and social returns of 15% are estimated. It is implied that black education is receiving minimal government financial assistance compared to those of the other population groups. The evidence of the results of the study indicates that; besides education, marital status, locational, regional and occupational variables also influence earnings differentials, the governments responsible for black education should emphasize human capital investment in relation to physical capital investment, on average more educated persons are better off than the less educated ones and with the exception of female early primary schooling, generally, it is worthwhile for an individual to undertake a certain educational programme investment

Trade unions in South Africa are a growing force. The discussion that follows and the accompanying tables describe this in some detail. Finding accurate and consistent statistics is not always easy, but everyone in industrial relations relies on good information when making decisions. This analysis attempts to provide the best available information on trade unions today. There have been considerable legislative changes in industrial relations since 1979, but the growth of unions preceded that, and, indeed, caused it. Africans were "entering" unions several years before the Wiehahn Commission reported - often by forming new ones. Since Wiehahn, and the adaptations made by existing unions, the stream has become a torrent. Most new members are African workers; but 'Coloured' and Asian and White membership has also increased significantly.Yet at least 3 out of every 4 "organizeable" workers remain to be unionised. Plainly, the South African trade union movement has only begun its greatest period of growth.

Estimates of the value of manufacturing sector output enter into many economic indices, especially those measuring productivity. The South African Central Statistical Services has twice made substantial errors in the output series. Revisions to correct the first of these raised the growth rate in manufacturing over the period 1970-80 from 2,6 per cent per annum (compound) to 5 per cent. This episode is not common knowledge. After examining the conceptual difficulties involved in producing output stimates, a practical technique for detecting errors in the series , the Euler Consistency Test, is presented. Developed, refined, and then applied to the South African data, it predicted, retrospectively, the first set of errors (using only the information available at the time those errors were made), then detected another set of errors , not previously known to exist. The study records the process by which the CSS was made to concede this second error. Acknowledgement only came after protracted correspondence and an examination conducted by a special committee formed to investigate my complaints. With 1979 set equal to 100, the output level in 1988 was originally given as 113,8. After investigation, the CSS raised this to 126,1. The magnitude of this second error is equivalent to the omission of the total output of the two SASOL plants commissioned during the early 1980s. Estimates of productivity growth by the National Productivity Institute using these incorrect figures are shown to have created a misleading picture of the sector's performance, especially in the sensitive debate over the relationship between wage and productivity growth. An attempt is made to lay the groundwork of an analytical framework for comprehending (from a Marxist point of view) the activities of ideological state apparatusses like the NPI. A review of the literature on theory choice is conducted, and the necessarily political nature of this activity is explored. The relative impotence of I science' in the face of ideology in a conflict-ridden society is considered. The question of the significance of disagreements between economists is examined, and prospects for convergence and consensus on certain issues are weighed. / Thesis (Ph.D.)-Unversity of Natal, 1994.

Thesis (MBA) -- Stellenbosch University, 2002. / ENGLISH ABSTRACT: The role of the Global Environment Monitoring System / Food Contamination Monitoring and Assessment Programme (GEMS/Food) is to assess and inform governments, the Codex Alimentarius Commission and other relevant institutions, as well as the public, on levels and trends of contaminants in food, their contribution to total human exposure, and their significance with regard to public health and trade. The primary objective of this study is to generate a reference list of “most commonly” consumed food items and average intakes of these items in the diet of South Africans, using GEMS/Food specifications. The list is required to be representative of foods eaten by children and adults from all age and ethnic groups in South Africa. The list will serve as a reference for the Department of Health who will undertake analyses of (a) toxic chemicals, such as pesticides, heavy metals and environmental contaminants; (b) naturally occurring toxins; and (c) food additives in the commonly consumed food items, as required by the Codex Alimentarius Commission. A secondary objective of the study is to derive average (mean) weights of South Africans in different age groups in order for the calculation of dietary exposure of selected contaminants. Secondary data-analysis was conducted on existing dietary databases (raw data) obtained from surveys undertaken in South Africa between 1983 and 2000. The National Food Consumption Survey (NFCS) served as a framework for compiling data on children since this was a national representative survey of 1 to 9 year-old children in South Africa. However there has never been a national dietary survey on adults in South Africa. Consequently the data had to be extrapolated from existing isolated surveys on adults. The dietary intake for the groups 1 to 5 years and 6 to 9 years was calculated only from the NFCS, and was not supplemented by other databases. The substantiation for treating age 10+ as a unit (and calling it an adult group), was the finding that average consumption of adolescents (10 – 15 years) did not differ significantly from that of adults when comparing mean energy intakes and mean quantities consumed, of age groups in the studies analysed. Data were analysed in terms of the percentage of the group consuming specific food main groups / subgroups / food items and on average per capita portion size. Factor analyses were done to analyse the inter-relationships among the food consumption patterns of NFCS 6-9 year-olds in 9 provinces, urban and rural separately, and the inter-relationships among food consumption patterns of these children and other children and adults in other independent food consumption studies. Two methods of estimating adult consumption were derived. The results from Method 1 corresponded with results from the NFCS, which was over-sampled for lower socio-economic areas, whereas the results from Method 2 ignored relationships with NFCS data and were based on the ethnic proportions of the population in South Africa. A final list, validated against international data, is included, which provides the per capita consumption per food item, average amount consumed (consumers only), the 97,5th percentile of the consumption figures (consumers only), as well as the corresponding gram per kilogram body weight consumed. These figures represent food items consumed by 3% or more of the South African population, for the following age groups: 1-5 years, 6-9 years and age 10+ (adults). Also, average weights of South Africans for the corresponding age groups are provided, which is calculated similarly to the methods used to calculate dietary intake. / AFRIKAANSE OPSOMMING: Die rol van die “Global Environment Monitoring System / Food Contamination Monitoring and Assessment Programme”, of (GEMS/Food), is om regerings, die “Codex Alimentarius”, ander relevante instellings en die publiek, op hoogte te hou (en selfs te monitor), ten opsigte van vlakke en neigings van kontaminasie in voedsel, die omvang van blootstelling aan die mens, en die beduidendheid hiervan vir openbare gesondheid en handel. Die doel van hierdie studie is om ‘n lys van voedselitems wat meestal deur die Suid- Afrikaanse bevolking geëet word, op te stel. Die lys moet hoeveelhede wat ingeneem word reflekteer, en moet aan die GEMS/Food spesifikasies voldoen. Dit moet verteenwoordigend wees van kos wat kinders en grootmense, van alle ouderdomsgroepe en rassegroepe in Suid- Afrika eet. Hierdie lys sal as verwysing vir die Departement van Gesondheid dien, om sodoende dan die berekenings van (a) toksiese chemikalië, soos plaagbeheermiddels, swaar metale en omgewingsbesoedelingsagente; (b) toksine wat natuurlik voorkom; en (c) voedselaanvullings in kossoorte, soos voorgeskryf deur die “Codex Alimentarius Commission”, te bereken. ‘n Sekondêre doel van hierdie studie is om die gemiddelde gewig van Suid-Afrikaners vir verskillende ouderdomsgroepe te bereken, om gebruik te word vir die berekenings van blootstelling aan geselekteerde toksine en besoedelingsagente. Sekondêre data-analise is op bestaande diëetkundige databasisse (oorspronklike data), wat opnames in Suid-Afrika vir die tydperk 1983 tot 2000 verteenwoordig, uitgevoer. Die Nasionale Voedselverbruikersopname, “National Food Consumption Survey” (NFCS), dien as raamwerk om die verbruik van kinders saam te stel, want hierdie opname was ‘n nasionaalverteenwoordigende opname van kinders van die ouderdom 1-9 jaar in Suid-Afrika. Daar was egter tot nou toe nog nie ‘n nasionaal-verteenwoordigende opname van voedselverbruik vir volwassenes in Suid-Afrika nie. Gevolglik moet hierdie data vanuit geïsoleerde opnames op volwassenes onttrek word. Voedselinname van kinders van ouderdomsgroepe 1-5 jaar en 6-9 jaar is dus bereken deur van die NFCS data gebruik te maak sonder aanvulling van enige ander databasisse. Die motivering om kinders van die ouderdomsgroep 10+ te hanteer in dieselfde groep as volwassenes, was die bevinding dat gemiddelde verbruik van adolessente (10 – 15 jaar) nie beduidend verskil het van die van volwassenes nie, veral as daar na die kilojoule inname en die hoeveelheid (gemeet in gram) inname, gekyk word. Die data van die verskeie opnames is ge-analiseer in terme van die persentasie verbruikers en die per kapita inname per voedselsoort, gegroepeerd en ongegroepeerd. Verbande tussen NFCS 6-9 jaar data in die 9 provinsies, landelike en stedelike gebiede afsonderlik beskou, asook verbande tussen hierdie kinders en kinders en volwassenes in onafhanklike ander opnames is met behulp van faktorontledings vasgestel. Twee metodes waarmee die voedselinnames van volwassenes voorspel kan word, is afgelei. Die resultate van Metode 1 stem met die resultate van die NFCS ooreen, waar die aanname is dat daar in die steekproefneming meer op kinders van laer sosio-ekonomiese areas gekonsentreer is. Metode 2 se resultate is gebaseer op die etniese verspreiding van die rassegroepe in Suid-Afrika, en voedselinnames van die blankes, byvoorbeeld, word meer in ag geneem. Die finale lys van voedselsoorte, wat gevalideer is teenoor ander internasionale studies, sluit die volgende veranderlikes in: die per kapita verbruik van die items, die gemiddelde verbruik per item (deur net die verbruikers van die spesifieke item in ag te neem), die 97,5de persentiel van voedselitems wat bereken is vir die groep wat die voedselitem verbruik, en ook die gram (gebaseer op die 97,5de persentiel verbruikers) per kilogram ligaamsgewig verbruik vir hierdie items. Hierdie syfers is vir voedselitems wat deur 3% of meer van die verbruikers in Suid-Afrika geneem word, en vir die volgende ouderdomsgroepe: 1-5 jaar, 6-9 jaar vir die ouderdom 10+ . Die gemiddelde gewig van Suid-Afrikaners vir die ooreenstemmende ouderdomsgroepe is ook bereken deur van dieselfde tegnieke gebruik te maak as die waarmee die voedselinnames bereken is.

<p>Research shows that more than 60 percent of South African born professionals, who graduated from South African universities, are leaving the country to work abroad in search of better working environments and financial rewards. This research assessed the intention to migrate and a number of factors that are likely to influence intentions to migrate such as age, professinal group, education, gender, and population group. The research also examined the countries to which people intend to migrate.</p>

MSc., Faculty of Science, University of the Witwatersrand, 2011 / The purpose of the study is to investigate possible reasons as to why different surveys conducted by Statistics South Africa (Stats SA) give different estimates of the percentages in the different employment categories. In order to investigate the different sources of variability, that is, surveys done in different years, surveys using different questionnaires, different sample designs and different employment profiles, the following comparisons were done for Gauteng and the Eastern Cape: • To compare estimates of employment status over time for the March Labour Force Survey (LFS) 2006 and 2007; September LFS 2006 and 2007; and General Household Survey (GHS) September 2006 and July 2007. • To compare estimates of employment status across surveys for LFS September 2006; GHS September 2006; and LFS September 2007, July GHS 2007 and Community Survey (CS) October 2007. In order to generate a set of comparable estimates across surveys and within surveys over time, this study identifies and addresses the various sources of potential non-comparability. The methodologies utilised are Chi-squared Automatic Detection (CHAID) and multinomial logistic regression. These statistical techniques were used to identify variables which are associated with employment status. The predictor variables included in the analysis are age group, highest level of education, marital status, population group, sex and source data. The results from CHAID for all data sets show that age group is the most significant predictor on which data on employment status can be segmented. At the root node (the first level of the CHAID tree), data was partitioned by the categories of age group. Highest level of education, sex, population group and province were significant within the categories of age group. Either province or population group was significant within the age group 20–29 years old depending on the data that is being analysed. Sex was most significant within the age group 50–65 years old. The results of multinomial regression show several significant interactions involving from five to seven factors for different data sets. The logistic regression results were not as good as those of the CHAID analyses, but both techniques give us an indication of the relationships between the predictor variables and employment. The analysis of the CS, LFS and GHS in 2007, when explaining employment status, split on age group. Highest level of education was the most significant predictor when comparing the three data sets. There are differences among the three data sets when explaining employment status. This is due to the use of different mid-year population estimates, differences in the instructions given in the questionnaire for CS 2007 and other surveys, as well as the sample size of the surveys. There are indeed significant differences between Gauteng and Eastern Cape in relation to employment status.

Background: In 2007, occupational specific dispensation (OSD) was introduced for public sector employees in South Africa which is unique to each identified occupation in the public service. The OSD for doctors was later introduced in 2009. The purpose of the OSD was to improve government's ability to attract and retain skilled employees, through increased remuneration. Previously, employees in the public service were remunerated by a single salary structure which did not adequately address the diverse needs of occupational categories in the public service (DPSA, 2009). Although the South African government has been investing a significant amount of resources to attract and retain medical doctors in public service, no formal study has been done to evaluate its impact in reducing the vacancy rate and retention of medical doctors in public hospitals in South Africa. This study aimed to assess the vacancy rate and the profile of doctors working at the Dr George Mukhari Hospital (DGMH) a public sector tertiary academic hospital for last three years (2007-2010) to determine the impact of OSD. Aim: To determine the impact of OSD on the vacancy rate and the profile of doctors working at the DGMH during a three year period (2007 to 2010) Methodology: A cross sectional study design was used to extract retrospective data routinely collected from the Personnel Salaries (PERSAL) system. Variables for the study included: Number of posts per category (Medical officer/ Registrar/ Specialist) funded/ filled and vacant, Profile (age, gender, ethnicity, nationality). The data was exported to MS EXCEL for storage and analysis. No primary data collection was done. The study commenced after obtaining approval from the University of the Witwatersrand ’Human research Ethics Committee (Medical) and Gauteng Department of Health and Social development. Results: The vacancy rate for doctors at the DGMH did not show any significant change after the introduction of ODS. The Hospital employed around 40% female doctors. The majority of doctors were Black and Coloured doctors, although certain department were still staffed by White doctors. There were no significant changes in the mean age of the doctors working in the Hospital. As expected the specialists were generally older than the registrars and medical officers. More South African doctors were appointed in 2010 in comparison to 2008. Conclusion: OSD did not have the intended effect of decreasing the vacancy rate of doctors at the DGMH. This might be because unfunded posts did not get additional funding to free them and therefore the status quo would have remained the same with or without OSD. It suggests that the additional funding should be considered for vacant unfunded posts. Hopefully, the funding model for NHI will dramatically increase the funding in the public sector allowing for OSD and an increase in funded vacant posts simultaneously.

M.Sc., Faculty of Science, University of the Witwatersrand, 2011 / The need for Official Statistics to assist in the planning and monitoring of development projects is becoming more intense, as the country shifts toward better service delivery by local government. It is evident that the demand for statistics at small area level (municipal rather than provincial) is high. However, the statistics with respect to employment status at municipal level is limited by the poor estimation of unemployment in 2001 Census and by changes in boundaries in local government areas. Estimates are judged to be reliable only at provincial level (Stats SA, 2003) The aim of this study is to investigate possible methods to resolve the problem of the misclassification of employment status in Census 2001 by readjusting the data with respect to the classification of people as employed, unemployed or economically inactive, to that of Labour Force Survey of September 2001. This report gives an overview of the different methods of small area estimation proposed in the literature, and investigates the use of these methods to provide better estimates of employment status at a small area (municipal) level. The application of the small area estimation methods to employment status shows that the choice of the method used is dependent on the available data as well as the specification of the required domain of estimation. This study uses a two-stage small area model to give estimates of unemployment at different small areas of estimation across the geographical hierarchy (i.e. District Council and Municipality). Even though plausible estimates of the unemployment rate were calculated for each local municipality, the study points out some limitations, one of which is the poor statistical representation (very few people) living in some specific municipalities (e.g. District Management Areas used for national parks). Another issue is the poor classification of employment status in rural areas due to poor data with respect to economic activities, mostly with respect to family businesses, and the non-availability of additional auxiliary data at municipal level, for the validation of the results. The inability to incorporate the time difference factors in the small area estimation model is also a problem. In spite those limitations, the small area estimation of unemployment in South Africa gives the reference estimates of unemployment at municipality level for targeted policy intervention when looking at reducing the gap between those who have jobs and those who do not. Hence, the outcome of the small area estimation investigation should assist policy makers in their decision-making. In addition, the methodological approach used in this report constitutes a technical contribution to the knowledge of using Small Area Estimation techniques for South African Employment statistics.