Application of Principal Component Analysis to Crime Data, Case Study: Mathare Slums, Nairobi County in Kenya

Abstract

The study focuses on statistical analysis of causes of crimes in Mathare slums, Nairobi county using data collected via questionnaires in April 2018.The Correlation analysis was carried out to explain the association between the causes of crimes while the principal component analysis (PCA) was used to reduce the dimensionality of the data sets. The Correlation analysis indicates a fairly strong positive relationship between unemployment and drugs and substance abuse which means that their variables can be used to predict one another. PCA analysis reveals that three PCs (drugs and substance abuse, unemployment and neglect from parents) that explains about 52.6% of the total variability of the causes of crimes against person are suggested to be retained. Similarly, two PCs (drugs and substance abuse and unemployment) that explain about 42.2% of the total variability of the causes of crimes against property are suggested to be retained. Generally, the causes of crimes against person and property in Mathare slums are not unique.