HOTSPOTS:

1
HOTSPOTS Defining Concentrations
2
Definition

• A hot spot is an area that has a greater than
  average number of criminal or disorder events
• An area where people have a higher than average
  risk of victimization.

3

• Analysis depends on the question
• Where are drugs being sold?
• Focus on the sale and therefore large scale
  analysis
• What is the market for drugs?
• Focus on the buyer and therefore a smaller scale
  analysis

4

• Hotspots as
• Points Example?
• Smallest units of analysis
• Lines Example?
• Crimes along a specific street
• Areas Example?
• Crimes by specific area or neighborhood

5

• Cities as hotspots Probably one of the smallest
  scales
• Repeat Victimization.
• Is it address, road segment or area specific?

6
(No Transcript)
7
Repeat Place Hotspots

• Recurring crimes at a specific address
• Routine activity theory is often applied
• Management sub theory.
• Bar management and assaults???
• Absence of good control and management
• Therefore routine activity theory says what????

8
Repeat Place Hotspots

• Maps that work?
• Single points per assault ?????
• Accumulated values for a specific point
• Carefully define the time period of tabulate
• Graduate symbols
• Obscured points at small scale.. Why?
• Best to use large scale maps
• Color gradient dots yellow to red grades
• Repeat address maps 10 highest addresses
  graduated symbols or gradients

9
Repeat Victimization Hotspots

• A repeat victim could be a
• Repeat crime at a specific place or
• Repeat crime at different places
• Domestic assault .. Repeated
• What symbols would be best
• A specific person who is assaulted in multiple
  locations
• Points might not work ..
• A specific type of person .. Taxi driver
• Defining a vulnerable population not a specific
  person

10
Repeat Streets Hotspots

• Repeat crimes along thoroughfares
• Targets are defined during day to day activity
  space routines
• Targets ..
• Offender movement patterns and target placement
  patterns create hot lines.
• Mapping can be tricky .. Accumulation problems

11
Area Hotspots

• Typically this is how the analysis was done
• Classifying areas by social factors

12
Area Hotspots

• Common explanations
• Social Disorganization Theory
• Lack of social controls
• Constant residential turnover
• Poverty and unemployment
• Social efficacy theory what is it?
• the willingness of local residents to intervene
  for the common good.
• Broken windows theory
• A spiral process

13
Area Hotspots

• Common explanations
• Crime Opportunity Theory
• Number of available targets of opportunity
• Risk/ reward
• Example??
• Cars parked on the street
• Dual income households in the suburbs

14
What Map Type to Use?

• Point maps for ????
• Line maps for ????
• Ellipse, Choropleth and Isoline maps ???

15

• Mean Center ?????
• Standard Deviation
• Standard Deviation Ellipse

16

• Nearest Neighbor Analysis
• How is it computed?
• Uniform, random, clustered
• What statistic is generated?
• Will it vary by scale?
• Large scale ????
• Small scale ????

17

• Toblers Law
• The first law of geography everything is
  related to everything else, but near things are
  more related than distant things (Tobler 1970).

18
(No Transcript)
19

• Spatial autocorrelation techniques test whether
  the distributions of point events are related to
  each other.
• Positive spatial autocorrelation is said to exist
  where events are clustered or where events that
  are close together have similar values than those
  that are farther apart
• One location affects another

20
Morans I

• It evaluates whether the pattern expressed is
  clustered, dispersed, or random.
• Derives a Z statistic Normal Probability
• Less than .05 ???

21
(No Transcript)
22
What is our conclusion?
23
Spatial Autocorrelation
24
Raster Techniques for Hotspots

• First we start with points representing crimes
• Then we select the crime to analyze
• Then we select the time period
• Then we MAY calculate crimes per unique location
• Then we May calculate crimes per general location
  Crimestat Fuzzy values

25
Raster Techniques for Hotspots

• Simple density points per raster cell
• Density using Kerneling
• Density using Kerneling with intensity values

26
(No Transcript)
27
The Problem of the K Value/Bandwidth

• Bandwidth the searching radius
• Bandwidth relates to the mean nearest neighbor or
  distance for different orders of K
• K is computed in the nearest neighbor statistic
  the average distance between points
• The smaller the bandwidth the more local detail
  but . What if it is larger

28
Check Display Output
29
(No Transcript)
30
Case 2.1
31
Raster Generation
32
The Problem of Grid Cell Size
33
(No Transcript)
34
(No Transcript)
35
(No Transcript)
36
(No Transcript)
37
Natural Breaks
38
Quantiles
39
Equal Intervals
40
Standard Deviation
41
Raster display
42
Mean Center and Standard Deviational Ellipse
Burlaries
43
Mean Center and Standard Deviational Ellipse
Homicides
44
Hierarchical Clustering Burglary
45
Spatial Autocorrelation
46
(No Transcript)
47
(No Transcript)