Vehicle ownership for South Africa : developing a forecasting model and assessing household vehicle ownership
| dc.contributor.advisor | Krygsman, Stephan C. | en_ZA |
| dc.contributor.author | Mtembu, Trishia Thokozile | en_ZA |
| dc.contributor.other | Stellenbosch University. Faculty of Economic and Management Sciences. Dept. of Logistics. Logistics. | en_ZA |
| dc.date.accessioned | 2020-02-25T12:05:18Z | |
| dc.date.accessioned | 2020-04-28T12:22:40Z | |
| dc.date.available | 2020-02-25T12:05:18Z | |
| dc.date.available | 2020-04-28T12:22:40Z | |
| dc.date.issued | 2020-03 | |
| dc.description | Thesis (MCom)--Stellenbosch University, 2020. | en_ZA |
| dc.description.abstract | ENGLISH SUMMARY : This study provides details on the findings of an analysis of data on the South African vehicle population and data from the National Household Travel Survey conducted in 2013; an analysis to forecast vehicle population and household vehicle ownership. The study analysed historical data from two data bases, namely eNaTiS and the 2013 National Household Travel Survey. The aim for both data sets was to forecast vehicle numbers and household vehicle ownership respectively. Vehicle population is important for economic development, policy and planning concerning road infrastructure, therefore the study analysed the real GDP as an indicator of economic growth and development, and the South African population as an influence driving vehicle demand. The historical data used shows an annual average compound growth rate of 3.07% for vehicle population and a predicted annual average compound growth rate of 2.22%. Though a decrease in growth rate, the vehicle population is predicted to grow to 17 637 672 vehicles in 2038 compared to a population of 71 452 500 people, thus an estimated ratio of 247 vehicles per 1 000 people in 2038. The study applies Multinomial Logistics Regression, an essential method for categorical data, to the National Household Travel Survey 2013 data. All the variables within the model are categorical, and thus this model is evidently a significant fit to the data. The dependent variable in the model is the number of vehicles owned by a household in 3 categories (0, 1 and 2 or more vehicles) and the independent variables consist of: main dwelling, income quintiles, geographical location and total household expenditure. The analysis shows that the probability of households in the lowest income quintile owning 1 vehicle compared to owning no vehicles was 0.161 times lower than the odds of households in the highest income quintile. Households with total household expenditure of R0-R300 were respectively 0.056 and 0.011 times less likely to influence household ownership of 1 and 2 or more vehicles. However, households residing within metropolitan areas are 1.182 times more likely to influence household ownership of 1 vehicle. | en_ZA |
| dc.description.abstract | AFRIKAANSE OPSOMMING : Geen opsomming beskikbaar. | af_ZA |
| dc.description.version | Masters | en_ZA |
| dc.format.extent | ix, 113 pages ; illustrations, includes annexure | |
| dc.identifier.uri | http://hdl.handle.net/10019.1/108158 | |
| dc.language.iso | en_ZA | en_ZA |
| dc.publisher | Stellenbosch : Stellenbosch University | en_ZA |
| dc.rights.holder | Stellenbosch University | en_ZA |
| dc.subject | Motor vehicles -- Ownership -- South Africa | en_ZA |
| dc.subject | Motor vehicles – Purchasing -- South Africa -- Forecasting | en_ZA |
| dc.subject | Motor vehicle industry -- South Africa | en_ZA |
| dc.subject | National Household Travel Survey (South Africa) | en_ZA |
| dc.subject | UCTD | |
| dc.title | Vehicle ownership for South Africa : developing a forecasting model and assessing household vehicle ownership | en_ZA |
| dc.type | Thesis | en_ZA |