Introduction
Victoria is considered to be a very desirable place to live, but residents and visitors also consider the safety of the city and its potential for crime in specific locations. In order to understand the location of crimes, the following question needs first to be answered: Are specific crime types randomly located, or if there is a pattern to their distribution, where would the highest levels of crime incidents be located?
According to Macleans magazine [#macRef] , Victoria is ranked as the 30th (out of 229) most dangerous places in Canada in 2018, with a crime severity index of 119 (Canadian average is 70.96). In 2018 there were 15219 ??? crimes, which were categorized into 18 different types of crime (explore the interactive map in figure 1 at the top of this page to view all of the 2018 theft crime locations) [#5].
Figure 2. Bright orange Police tape acts to secure a potential crime scene. [Image Source: Victoria News, 2019-07-23 #1]
The Victoria Police Department provides police service to both the City of Victoria and the Township of Esquimalt, and though crime rate statistics have been falling, police costs have been rising, and the Victoria Police Department are regularly requesting a larger budget [#pcost]. Police are kept busy investigating a variety of crimes, and while potential crime scenes being secured, assessed, and police reports initiated, bright orange Police Tape may be used as a visible barrier, as seen in figure 2.
Crime pattern theories describe crime events as complex, and that the motivation and opportunities for criminal offenders are not random, nor are their locations distributed evenly. As the use of space by people is based on available urban pathways and boundaries, as well as routine patterns of activity of both criminals and victims, many crimes can be expected to occur in areas that become a part of common activity routines of both the criminal and the victim. Identifying potential locations of non-random crimes may help researchers to identify patterns and locations which may ultimately reduce levels of crime [#cTheory].
Explain objective of project
- Clearly state objective [2]
- How will you accomplish objective? [2]
- Why is this research important? [2]
- Description of crime situation in the city [1] - DONE
- Citations included and adequate (at least 2) [#1] [2] - DONE
- Image included [1] - DONE
Study Site: City of Victoria
"Write a brief paragraph explaining the City of Victoria"
* Victoria, the provincial capital city, is located on British Columbia's southwest coast at the southern tip of Vancouver Island, on unceded Coast Salish land, and has one of the warmest winters in Canada.
* The newly published Vital Signs 2019 survey report [#vits] gives Victoria a B grade for safety and the presence of police, and a C+ for standard of living regarding available services, food and opportunities for work.
* In the most recent 2016 census, the population of the City of Victoria was 85,792, having grown 5,774 from the previous census in 2011, with a population density of 4015.7 people/km², 25% of whom are over 65 years of age. Victoria is also the largest municipality in the Capital Regional District, with 22.38% of the Greater Victoria Area 2016 population of 383,360 [#2].
* The city of Victoria covers over 21.36 km² of land area [CITE ????, with over 97 km of major roads, and 161 km of other roads (https://www.victoria.ca/EN/main/residents/road-maintenance/streets.html) # [#4]
*
*
- Background to City of Victoria and Crime [5]
Data
Crime statistics, for both Victoria and Esquimalt from January 2011 to September 2019, were downloaded from the Victoria Police Department, in a csv file organized by the incident id and case number, and include the incident date and time, type of incident grouped within 18 different crime categories, as well as the address and location coordinates, resulting in a file containing 137,530 different crime data location points [#5].
The City of Victoria's perimeter boundary was needed to trace the exact extent of the city boundaries. The boundary coordinates are available in the form of a polygon area shapefile, projected in UTM zone10, in the coordinate system NAD83 GRS80, and were downloaded from the City's open public data portal [#3].
Data Marking Matrix- Provide a description of data source and contents [5]
- Any other Data??? ... e.g. did I use neighbourhood shp file for final plot map??
Analysis
During 2018, the Victoria City Police have incidence reports filed for ???13,712 crimes in the City of Victoria [4].
The data first needed to prepared for analysis. As this study is only interested in analyzing the 2018 City of Victoria Police crime statistics, the crime points data needed to be subset to include only those crimes that occurred during the year 2018, with only the information we needed to analyze the data set including the date, location coordinates and crime type. Also, as the Victoria Police serves both Victoria and Esquimalt, the City of Victoria boundary shapefile was used to create an intersection with the crime data points, bounding an extent that will include only the crimes in Victoria. In order to find the density of crime points, the area of Victoria first needed to be calculated, which was be done in two ways, with both ending up with different values. Calculating the spatial geometry of the shapefile polygon follows the coastal outline with a bit more exactness, resulting in the larger area of 21,363,930 m², than simply relying on the shapefile-defined area of 21,347,203,m²
In order to determine if the crimes in Victoria were randomly located or had some significant spatial pattern, each separate crime incident was grouped into 18 different incident types, upon which a series of four point pattern analysis tests were done on the data, the Nearest Neighbour Distance (NND), the Quadrat Grid Cell (Quad), the K function (K-Func), and the Kernel Density Estimation (KDE).
NND: The Nearest Neighbour Distance test measures are based on the distances between points, and can explain the spatial distribution at different distance ranges. To be considered clustered there would be more than the expected average of random neighbouring points (the distance between points is less than a random average), and to be dispersed there would be fewer neighbouring points than a random distribution (the distance between points would be greater than a random average). The NND test was run to calculate the average distance between each neighbouring crime type point and comparing this distance to that of a randomly located neighbour, based on the density of the number of each particular crime type points in ratio to the total study area (21,363,930 m²). If the average distance was equal to the random distance, the crime locations would be random, however, if the resulting z score value confidence level was 95% or higher (two standard deviations around the normal distribution), those crimes would not considered to be random, but instead have a patterned distribution.
Quad: The Quadrat density test uses an area that is divided by a grid of cells, and the density of points is calculated for each quadrat. The Quad measures are based on number of points found within a quadrat of different sizes and locations. Choosing the number of quadrats can affect the p value test results, representing the probability of randomness, and with a p value of lower than 0.05, the point distribution would not be considered to be random. If the quadrats are too small, there will be many cells with no points, and if they are too large, any change in point density over a small area may be difficult to see.
K-Func: The K function looks at the point patterns of clustering or dispersion at a variety of distance ranges between points, and calculates the level of confidence that the point pattern distributions are random or patterned [#Dix]. As the distance between points increases, so too will the number of neighbouring points. If the number of neighbouring points is higher than a random number of points, the distribution will be clustered, and if the number is smaller, the distribution will be dispersed. On a graph of the points, if the points fall within the confidence interval, then the likelihood of the point distribution being different than random increases.
KDE: The KDE ...
* "Write section as narrative vs methods and results
* "avoid boring general public to read equations and try to understand math behind everything"
* "clearly and concisely explain the methods you used and what they produced."
* "I recommend two main sections, each focused on one of two questions posed by supervisor"
????' Do not get into the nitty-gritty details here (don’t mention R or specific methods or equations). - in intro
Are Crimes Randomly Located?
* "provide a few sentences explaining each method you use and what it does"
* "provide" a brief paragraph describing the results."
If points are considered to be randomly distributed, there would be nothing unusual about the distribution of points, but if the point distribution is not considered to be random, there would be a statistically significant distribution to the points, which would suggest some patterned distribution of either clustering or dispersion, would could then lead to further investigation of the underlying causes.
Figure 3. Statistics used to determine whether a crime was random (R) or patterned (P). ??? add info re Clustered or dispersed ???? ... add line between P & R ... sort P in highest level first
The two test results that provide the initial analysis for randomness are the NND and the Quad, which provide the z-score and the p-score. If the NND test z-score was greater than 1.96 - the 95% confidence level, and if the Quad test p value was less than 0.05, the crime type would be considered to be a non-random pattern. If the mean NND distance was greater than the random distance the pattern would be a dispersed pattern, and if less would be a clustered pattern.
(see figure 3).
The crime types that were significantly randomly located were: Alarm, Arson, Assault, Assault with Deadly Weapon, Community Policing, Drugs, Robbery, Theft of Vehicle, Vehicle Stop, Weapons Offense
Where Are The Highest Incidences of Crimes?
* "few sentences explaining each method & what it does"
* "brief paragraph describing the results."
If crime locations are not random, they will have a significant pattern, which could be either dispersed (points equally spread over area) or clustered().
What is criteria for Quad dispersed vs clustered?
Stastically speaking, the crimes that were considered to have a distributed pattern, that was non random were: Breaking & Entering, Disorder, Liquor, Other, Property Crime, Theft, Theft from Vehicle and Traffic.
"*IMPORTANT: for the nearest neighbour analysis, you NEED to include the n and the area of the study site. You can include these in the text when describing this method."
Crime Type: Theft
* ???
Figure 5. Best Kernal Density Estimate of Theft. ??? refer to figure in text ????
Figure 6. K funtion significance graph of Theft. ??? refer to figure in text ????
The Open Street Map at top of this webpage (see figure 1) is an interactive leaflet map showing all of the 2018 City of Victoria Theft Crime data points (to reset the map to the original extent after exploring the data, simply reload this webpage). The same interactive map can be accessed from the drop-down selection list in figure 4.
Crime Type: Theft from Vehicle
* ???
Figure 7.Best Kernal Density Estimate of Theft from Vehicle. ??? refer to figure in text ????
Figure 8.K funtion significance graph of Theft from Vehicle. ??? refer to figure in text ????
* ....
Crime Type: Property Crime
* ???
Figure 9. Best Kernal Density Estimate of Property Crime. ??? refer to figure in text ????
Figure 10. K funtion significance graph of Property Crime. ??? refer to figure in text ????
* ....
Crime Type: Breaking & Entering
* ???
Figure 11. Best Kernal Density Estimate of Breaking & Entering. ??? refer to figure in text ????
Figure 12. K funtion significance graph of Breaking & Entering. ??? refer to figure in text ????
* ....
Analysis Marking Matrix
Limitations
* One limitation that affected the Nearest Neighbour Distance test was in the choice of one out of two the City of Victoria area calculations, and by choosing the area that used a more refined method which resulted in a larger area, creating a lower density of crime location points per unit area, which may have underestimated the significance of spatial patterning. ?????
* Another limitation - Scale ??? when does dispersed become clustered ?? ......
* Another limitation - bias of edge effect in NND, as there would be fewer neighbours at the points nearest the edge, as some neighbours would be outside of the study area boundaries ??......
* Another limitation - This study does not test to see if any of these different crimes are related .. [CITE Jessica's Alcohol Access & Crime] ....
* Another limitation - No information is available about the person who committed these crimes, to even know if Victoria crimes are committed by Victoria residents. ......
* Another limitation - The data may not reflect all the crimes that occur in Victoria, and as the locations are generalized to the blocks in levels of one hundred, and some incident addresses relate the location the incident was reported and not necessarily where it occurred. ... [cite: https://www.vicpd.ca/crime-reports ...
* "Describe anything that reader should be aware of when making sense of your findings. Be honest, but not overly self-critical."
* "don't make it sound as if your methods are bad."
* e.g. "did number of quadrats in quadrat analysis or bandwidth in the KDE impact your results?"
Limitations Marking Matrix