Ndlovu, PetronellaPetronella, Ndlovu2021-05-032021-05-032020https://hdl.handle.net/10539/31073A research report submitted to the Faculty of Science, University of the Witwatersrand, Johannesburg, in partial fulfilment of the requirements for the degree of Master of Science in Geographical Information Systems (GIS) and Remote Sensing, 2020The study investigated the spatial distribution of five types of crimes (namely contact crimes, contact-related crimes, other serious crimes, property-related crimes and crime detected as a result of police action) in Gauteng using the traditional measure “crime count” and the five alternative measures of crimes namely: location quotient, Theil index, Herfindahl-Hirschman index, Specialisation index and Entropy index. The study found that the five types of crimes are differently distributed in the province. The five types of crimes tend to cluster in certain parts of the province. The contact crime cluster in the City of Johannesburg and the City of Tshwane municipality. The contact related crimes and property related crimes cluster in the City of Johannesburg and the West Rand District. The other serious crimes clustered in the City of Johannesburg and the City of Ekurhuleni municipality while the crimes detected as a result of police action specialisation clusters were found in West Rand District. The study found that police districts can be affected by two or more types of crimes e.g. The Johannesburg Central is affected by contact related crimes and other serious crimes. The investigation found that the five alternative measures of crime show similar spatial distribution of the five types of crimes in the Gauteng. The crime count shows a similar distribution with the Herfindahl-Hirschman index (HHI), while the location quotient (LQ), the Specialisation index (SI), the Theil index (TI), and the Entropy Index (EI) show a similar distribution of the five types of crimes. The LQ, TI, SI and EI are strongly related to each other while moderately related to the HHI. The study found that spatial autocorrelation was found present in all the five types of crimes, showing that the province has clusters of hot spots(high-high) and cold spots (low-low), and outlier hot spots and cold spots (high-low and low-high values) existing. The study also found that there are positive and negative changes in recorded crimes from the year 2014 to 2016. The contact crimes increased in recorded crimes, while the contact related crimes, property related crimes, other serious crimes and crimes detected as a result of police action decreased in recorded crimes. The five types of crimes decreased in the national effect. In contact crimes and property related crimes, decreased at the national level, and increased on the regional and industry mix. In contact related crimes, decreased at national level, increased on the industry mix and a decreased on the regional level. In other serious crimes and the crimes detected as a result of police action there is a decrease at the national level, industry mix and also on the regional shiftenThesis