The article Crime Mapping and the Crimestat Program begins with an overview of the Crimestate program and its contribution to crime mapping. The Crimestat program provides supplemental statistical tools to aid law enforcement agencies and criminal justice researchers in crime mapping. It specifically highlights version 3.0 and emphasizes its ability for law enforcement personnel to analyze travel patterns over metropolitan areas. It is designed to increase the effectiveness of crime mapping and other GIS applications as well as work with large databases considering most police department work with large files.
Following a brief overview of Crimestat the article
provides a detailed definition of crime mapping. It states that crime
mapping is the mapping of crime incidents in order to detect general patterns
of crime to better allocate resources for enforcement
and prevention as well as to identify and apprehend offenders
committing crimes. It has multiple uses, examples include, planning
efficient deployment strategies to focus on hot spots, tracking the behavior of
serial offenders, and mapping motor vehicle crash locations.
The article provides detail into the statistics built into the
program to make crime mapping more efficient and easier to use. First,
the author describes spatial statistics. He states that a key concept in
spatial statistics is spatial autocorrelation, defining it as events that are spatially
arranged in a nonrandom manner, either more concentrated or, occasionally, more
dispersed than would be expected on the basis of chance. Next, the author
provides a description of hot spot analysis, an extreme form of spatial
autocorrelation, stating that incidents, mainly criminal activities are
concentrated in a limited number of locations. Spatial modeling is the
next area of focus. The first method in this category is interpolation,
the act of extrapolating a density estimate from individual data points.
It involves the placement of a fine-mesh grid over the area under study
and the distance from each grid cell to each data point in calculated.
This is followed by an estimate of incident density for each grid cell. Journey-to-crime
analysis is the next analytical tool discussed and is
a criminal justice method for estimating the likely residence
location of a serial offender when given the distribution of incidents and a
model for travel distance. Space-time analysis precedes journey-to crime-analysis
and includes many routines for analyzing clustering in time and space including
the Knox and Mantel indices as well as the Correlated Walk Analysis module.
The final statistical tool is crime travel demand that models criminal
travel behavior over a metropolitan area. Finally, the article is
comprised of a section discussing the miscellaneous options in Crimestat. The
concluding paragraphs reemphasize the importance of GIS and crime mapping
overall into law enforcement. Furthermore, the author reiterates the need
for statistical tools to aid in the assessment of the important trends in the
data.
Critique:
CrimeStat, a statistical tool used to increase the usefulness of
crime mapping is likely to increase the effectiveness of crime mapping overall
but considering the program developer is the writer of the article it has the
potential to be biased. It would have been useful to include reviews or
opinions by its users in the law enforcement field or other users such as
students, professors, researchers or analysts to minimize
the possibly of bias.
The article states that CrimeStat is one of the many tools
developed to summarize and assess the trends in crime mapping.
Examples of other tools used to achieve the same results for comparison
reasons would provide the reader with a better means to assess Crimestat's
effectiveness over other programs.
Given the nature of the article, to incorporate and explain
Crimestat and its use in crime mapping, a more through explanation of the
relationship between the different types of crime mapping and Crimestat’s
contribution to these methods would be highly useful. For example,
Crimestat provides seven hot spot analysis routines including the mode, the
fuzzy mode, hierarchical nearest neighbor clustering, risk adjusted nearest
neighbor hierarchical clustering, the Spatial and Temporal Analysis of Crime
routine, and K-means clustering. An example giving a basic overview of
each of these analysis routines would provide a better understanding of Crimestat's
functions in relation to crime mapping while allowing the reader to compare and
contrast the methods evaluating what method is most effective in a particular
situation. Furthermore, Crimestat uses five different mathematical
functions to estimate the density and has two different applications
including a single-variable density estimation and a dual-variable
density estimation routine. Again, the author mentions Crimestat
and the five different mathematical functions as well as the two
different applications the program is able to use. This
is another instance in which more examples would prove to be
effective in understanding the functions and their contributions to crime
mapping. This would allow for an overall better understanding of
the program and crime mapping in general.
The article discusses Version 3.0 of Crimestat stating it has a
crime travel demand module of modeling criminal travel behavior over an entire
metropolitan area. The author focuses on the concept of aiding law
enforcement in metropolitan areas throughout the article. While this is
useful, it is also important to emphasize on its effectiveness in smaller law
enforcement agencies. In the conclusion, the author stresses the strong
need for statistical and other analytical tools that can summarize the trends
in the data. Although visuals and graphs are provided for some methods,
specific examples for each method and an outright description as to how it
relates to crime mapping would be beneficial. This would allow for an
overall better understanding of the program and crime mapping in general.
Source:
Levine, Ned. (2004). Crime Mapping and the Crimestat
Program. Ned Levine & Associates,
41-56. Retrived from http://cs.iupui.edu/~tuceryan/pdf-repository/levine2006crime.pdf
Posts
No comments:
Post a Comment