| Peer-Reviewed

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

Received: 8 January 2019     Accepted: 28 January 2019     Published: 21 February 2019
Views:       Downloads:
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.

Published in American Journal of Theoretical and Applied Statistics (Volume 8, Issue 1)
DOI 10.11648/j.ajtas.20190801.12
Page(s) 7-17
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2019. Published by Science Publishing Group

Keywords

Crime, Principal Component Analysis, Total Variation, Scree Plot

References
[1] Fajemirokun F., Adewale O., Idowu T., Oyewusi A. and Maiyegun B. (2006). A GIS Approach to Crime Mapping and Management in Nigeria: A case study of Victoria Island Lagos, CBN. Journal of Applied Statistics, Vol.3 No.2 49, .www.oicf.org.
[2] Aki Stravra, (September 2002). Crime on Nairobi: Results of a City wide victim survey. UN Habitat (safer cities: series 4), Nairobi.
[3] Masese Grace (2007). Crime and Violence Trends in Nairobi, Kenya. Case study prepared for Enhancing Urban Safety and Security: Global Report on Human Settlements 2007. UN Habitat 2007.
[4] GOK and UNDP (2010-2013). Report on overview of crime incidents in Nairobi Region Security Research Information Centre (SRIC).
[5] Rev. Fr. Dr. Ndikaru Wa Teresia (2011). Crime causes and victimization in Nairobi city slums. International journal of current research, 3 (12) 275-285.
[6] Darkey D. and Kariuki A. (2013). A study on Quality of Life in Mathare, Nairobi Kenya. Journal of Human Economic Development. 41 (3) 207-219.
[7] Andvig J. C and Barasa T. (2014). A political Economy of slum spaces: Mathare valley. Norwegian Institute of International Affairs. Norway.
[8] Chris Muchwanju, Joel C. Chelule and Joseph Mung’atu (2015). Modelling crime rate using a mixed effect regression model. American journal of Theoretical and Applied statistics. 4 (6), 496-503.
[9] Wanjiru M. W and Matsubara K. (2017). Slum toponymy in Nairobi, Kenya. A case study analysis of Kibera, Mathare and Mukuru. Urban and Regional Planning review, 4.
[10] Mburu L. W (2014). Modeling and mapping crime in Eastern Nairobi, Kenya. GIScience Research Group. University of Heidelberg.
[11] Jolliffe, I. T (2002).Principal Component Analysis, 2nd Edition, Springer-Verlag, New York.
[12] Rencher, AC. (2002). Methods of Multivariate Analysis, 2nd edition, John Wiley & Son, New York. Richard, A.J. and Dean, W. W. (2001). Applied Multivariate Statistical Analysis, 3rd edition, Prentice-hall, New Dehli.
[13] Kendall Williams and Ralph Gedeon (2004), A Multivariate Statistical Analysis of Crime Rate in US Cities.
[14] Yusuf Bello, Yusuf U. Batsari and Abdullahi S. Charanchi (2014). Principal Component Analysis of Crime Victimizations in Kastina Senatorial zone. International journal of science and Technology,3 (4).
[15] Olufolabo O. O.,Akintande O. J., Ekum M. I. (2015). Analysing the Distribution of crimes in Oyo State using Principal Component Analysis. IOSR Journal of Mathematics (IOSR-JM) Vol.11 Issue 3.
[16] Soren, H. (2006). Example of multivariate analysis in R-Principal Component Analysis (PCA).
[17] Perry. R. H., Charlotte, B., Isabell M. and Bob, C. (2004).SPSS Explained, ISBN: 0-203-67627-0, Routledge, Taylor &Francis Group, London &New York.
Cite This Article
  • APA Style

    Wafula Mike Erick, Samson Wangila Wanyonyi, Chris Muchwanju. (2019). Application of Principal Component Analysis to Crime Data, Case Study: Mathare Slums, Nairobi County in Kenya. American Journal of Theoretical and Applied Statistics, 8(1), 7-17. https://doi.org/10.11648/j.ajtas.20190801.12

    Copy | Download

    ACS Style

    Wafula Mike Erick; Samson Wangila Wanyonyi; Chris Muchwanju. Application of Principal Component Analysis to Crime Data, Case Study: Mathare Slums, Nairobi County in Kenya. Am. J. Theor. Appl. Stat. 2019, 8(1), 7-17. doi: 10.11648/j.ajtas.20190801.12

    Copy | Download

    AMA Style

    Wafula Mike Erick, Samson Wangila Wanyonyi, Chris Muchwanju. Application of Principal Component Analysis to Crime Data, Case Study: Mathare Slums, Nairobi County in Kenya. Am J Theor Appl Stat. 2019;8(1):7-17. doi: 10.11648/j.ajtas.20190801.12

    Copy | Download

  • @article{10.11648/j.ajtas.20190801.12,
      author = {Wafula Mike Erick and Samson Wangila Wanyonyi and Chris Muchwanju},
      title = {Application of Principal Component Analysis to Crime Data, Case Study: Mathare Slums, Nairobi County in Kenya},
      journal = {American Journal of Theoretical and Applied Statistics},
      volume = {8},
      number = {1},
      pages = {7-17},
      doi = {10.11648/j.ajtas.20190801.12},
      url = {https://doi.org/10.11648/j.ajtas.20190801.12},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajtas.20190801.12},
      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.},
     year = {2019}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Application of Principal Component Analysis to Crime Data, Case Study: Mathare Slums, Nairobi County in Kenya
    AU  - Wafula Mike Erick
    AU  - Samson Wangila Wanyonyi
    AU  - Chris Muchwanju
    Y1  - 2019/02/21
    PY  - 2019
    N1  - https://doi.org/10.11648/j.ajtas.20190801.12
    DO  - 10.11648/j.ajtas.20190801.12
    T2  - American Journal of Theoretical and Applied Statistics
    JF  - American Journal of Theoretical and Applied Statistics
    JO  - American Journal of Theoretical and Applied Statistics
    SP  - 7
    EP  - 17
    PB  - Science Publishing Group
    SN  - 2326-9006
    UR  - https://doi.org/10.11648/j.ajtas.20190801.12
    AB  - 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.
    VL  - 8
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • Department of Mathematics and Actuarial Science, Kenyatta University (KU), Nairobi, Kenya

  • Department of Mathematics, University of Eldoret, Eldoret, Kenya

  • Department of Statistics and Actuarial Science, Jomo Kenyatta University of Agriculture and Technology (JKUAT), Nairobi, Kenya

  • Sections