Solvability Analysis: Increasing the Likelihood of detection in Completed, Attempted and In-Progress...
description
Transcript of Solvability Analysis: Increasing the Likelihood of detection in Completed, Attempted and In-Progress...
Solvability Analysis:Increasing the Likelihood of detection in Completed,
Attempted and In-Progress Burglaries
Colin Paine & Barak Ariel
• All residential burglaries in Thames Valley from 1st March 2010 to 31st October 2011
•11,769 full offence residential burglaries
•Excludes distraction burglary, aggravated burglary and non-residential burglaries.
Data Set I
• All residential burglaries in Thames Valley from 1st March 2010 to 31st October 2011
•2,537 attempted residential burglaries
•Excludes distraction burglary, aggravated burglary and non-residential burglaries.
Data Set II
• All in-progress residential burglaries in Thames Valley from1st November 2009 and 31st October 2012 (i.e. Burglary emergencies).
•N = 6,119
•Includes aggravated, distraction and non residential burglaries.
Data Set III
Collapsed four databases:• “Socrates” – the forensic information database• CEDAR – the crime recording database• IMM – the crime investigation management application• Command and control – the incident resourcing
system (only this system used for data on in-progress offences).
• (Datasets aligned using crime numbers & cleansed to remove duplicates)
Data Sources
LimitationsUnable to study ‘Suspect Named’ variable (Greenberg 1970).
Unable to study intelligence as a variable
Insufficient capacity to study ANPR as a variable
Full and Attempted Burglaries
129 variables in the data set 57 useful variables, such as:
1. Time range of offence, 2. time to first officer attendance, 3. offence witnessed, 4. suspect seen, 5. suspect disturbed, 6. fingerprints recovered, 7. DNA recovered, 8. items left at scene by offender, 9. rural/town location, 10. media appeal completed, 11. called in as burglary in progress.
Variables
Non-Dwelling Burglary
Dwelling Burglary
Distraction Burglary
Aggravated Burglary
0
2000
4000
6000
8000
10000
12000
14000
16000
18000
2000018029
14306
362 61
Burglary Offences by Catagory
43.7% of all burglaries are residential (dwellings)
0
4000
8000
1200011769
2537
Number of Burglary Dwelling Of-fences (Completed Offences and
Attempts)
17.7% of Residential Burglaries are Attempts.
00:00 - 1...
01:00 - 0...
02:00 - 0...
03:00 - 0...
04:00 - 0...
05:00 - 0...
06:00 - 0...
07:00 - 0...
08:00 - 0...
09:00 - 0...
10:00 - 1...
11:00 - 1...
12:00 - 1...
13:00 - 1...
14:00 - 1...
15:00 - 1...
16:00 - 1...
17:00 - 1...
18:00 - 1...
19:00 - 1...
20:00 - 2...
21:00 - 2...
22:00 - 2...
23:00 - 2...
0100200300400500600700800900
Frequency of Burglary Offences by Time of Day
Most burglaries do not occur at night
Monday
Tuesday
Wednesday
Thursday
Friday
Saturday
Sunday
0500
10001500200025003000
Frequency of Burglary Of-fences by Day of week
Description of Dataset(Solved Residential Burglary)
0
200
400
600
800
1000
1200
1400
1600
1344
522
32 20 5 2 1
Burglary Detection by Type
69.8% of detections are charges.
Solved Crimes• Detected crime selected as
the definition of solved crime. 1926 detected crimes (12.99%)
• Removed secondary detections – 525 removed
• 1401 detected crimes (9.79%)
• 4 methods of disposal included; charges, reprimands, final warnings, cautions.
• Majority are chargesBurgl
aries C
harg
ed
Juve
nille R
eprim
and
Juve
nille fin
al warn
ing
Adult C
autio
n0
200400600800
1000120014001600
1344
5 20 34
Number of Disposals For Residential Burglary 01/03/10 to 31/10/11
Attempted burglary
Full burglary Total0.00%
5.00%
10.00%
15.00%
5.68%
10.68% 9.79%
Detection rates of Residential Burglaries 01/03/10 to 31/10/11
Attempted burglary is harder to solve than the full offence.
0 10 20 30 40 50 60 70 80 90 100 110 120 130 140 150 160 170 180 1900
10
20
30
40
50
60
70
Number of days to detect Burglary (exclud-ing 10% and 90% Percentile)
No. of days to detect
No.
of b
urgl
arie
s
Mean 41 daysMedian 25 daysMode 3 days
Over 96% of all detections are obtained in 180 days. 1 Burglary took 5 and half years to solve.
Solvability Analysis
Data Quality Assurance and Cleansing
•Random selection and review of quality of data capture in 100 burglaries from the sample
•Review of missing data to determine whether it will undermine internal validity.
•Data was pretty good!
0.00%2.00%4.00%6.00% 4.93%
1.39%0.27% 0.12%
Percent of cases where a footwear mark is recovered
Detected cases %Undetected Cases %
Compared percentage of marks recovered in solved sample and unsolved sample.
0.00%4.00%8.00%
12.00%13.29%
9.72%
0.90% 1.00%
Percent of cases where DNA is recovered
Detected cases %Undetected Cases %
Compared percentage of marks recovered in solved sample and unsolved sample.
0.00%
10.00%
20.00%21.24%
13.89%
3.61%1.00%
Percent of cases where a fingerprint is recovered
Detected cases %Undetected Cases %
Compared percentage of marks recovered in solved sample and unsolved sample.
0
10
2030
22.19
30.55
9.16 9.9
Percent of cases with one or more witnesses recorded
Detected cases %Undetected Cases %
Burglary in progress (full burglaries)
Burglary in progress (attempt burglaries)
0.00%
5.00%
10.00%
15.00%
20.00%
25.00%
8.43%
19.44%
3.86%
5.97%
Percent of cases initially reported as a burglary in progress
Detected cases %Undetected Cases %
Compared percentage of burglaries in progress in solved sample and unsolved sample.
0
100
200
300
144.94116.22
178.17
260.51
Average (mean) time to attend-ance of first officer (minutes) excluding burglaries in pro-
gress
Detected CasesUndetected Cases
New solvability factors identified: media appeal, vehicle stolen in the crime, anything left at scene by the offender, stolen property recovered, reported as a burglary in progress, DNA and footwear marks recovered.
The most powerful solvability factors occur the least often.
Premise
s were
occu
pied
Any st
olen p
ropert
y rec
overe
d
Offend
er dis
turbe
d
Witnes
s
Offend
er See
n
Anythi
ng le
ft at s
cene
by of
fende
r
Fingerp
rint Id
ent
Vehicl
e stol
en in
the c
rime
Burglar
y in P
rogres
s
DNA Iden
t
Offend
ers ve
hicle
sighte
d
Suspe
ct de
scrip
tion r
ecord
ed
Footw
ear Id
ent
0.00%
5.00%
10.00%
15.00%
20.00%
25.00%
30.00%
35.00%
40.00%
Percentage Frequency for Completed and Attempted Burg-laries
Completed BurglariesAttempted Burglaries
0 1 2 3 4 5 6 70.00
10.00
20.00
30.00
40.00
50.00
60.00
70.0057.69
24.88
9.414.53
2.35 0.88 0.20 0.04
Percentage of full burglaries by number of solvability factors
Most burglaries have no solvability factors present.
372 solved residential burglaries had no solvability factors present. Sample of 62 reviewed.
Consp
iracy
Cha
rges
Suspe
ct na
med by
victi
m
CCTV Pres
ent
Unkno
wn
Witnes
s pres
ent
Forens
ic Mate
rial P
resen
t
Stolen
Prop
erty r
ecov
ered
Intell
igenc
e0
5
10
15
20
2521
12
8 7 6 52 1
Frequency of Factors Associated with Case Solution Where No Solvability Factors are Present
It is possible to predict the outcome of case dependent on presence of solvability factors. Predictive accuracy would be enhanced if suspect named variable were added, conspiracy charges removed from sample and each variable were statistically weighted.
Wind
sor a
nd M
aiden
head
Brackn
ell Fore
st
Wes
t Oxfo
rdshir
e
Wok
ingha
m
Chilter
n and
Sou
th Buc
ks
Cherw
ell
Wes
t Berk
shire
Readin
g
Aylesb
ury V
ale
Milton K
eyne
s
Oxford
South
and V
ale
Slough
Wyc
ombe
455055606570
Percentage of Burglaries with one or more solvability factors by police area
The presence of solvability factors in burglaries is not uniform
Burglaries In Progress
• 5.59 Reported Burglaries in Progress in TVP per day
• 6.11% result in an arrest at or near scene.
• 4% daytime and 7% nighttime.
01000200030004000500060007000 6119 5745
374
Burglaries in Progress - Arrests Made
Just 6.11% result in an arrest in immediate response to the initial call
South
and V
ale
Brackn
ell Fore
st
Readin
g
Cherw
ell
West B
erksh
ire
Slough
Windso
r And
Maid
enhe
ad
Wycom
be
Milton K
eyne
s
Aylesb
ury V
ale
West O
xfords
hire
Chilter
n and
Sou
th Buc
ks
Oxford
Woking
ham
Out of
Force
0
1
2
3
4
5
6
7
8
9 8.3
7.2 7.26.8
6.4 6.3 6.1 6.15.6 5.6 5.6 5.4
4.8 4.8
0.0
Percentage of Burglaries in Progress with an arrrest by LPA
The arrest rate following burglaries in progress is not uniform across police areas.
<1 Minu
te
1 minu
te
2 minu
te
3 minu
te
4 minu
te
5 minu
te
6 minu
te
7 minu
te
8 minu
te
9 minu
te
10 m
inute
11 m
inute
12 m
inute
13 m
inute
14 m
inute
15 m
inute
16 m
inute
17 m
inute
18 m
inute
19 m
inute
20 m
inute
21 m
inute
22 m
inute
23 m
inute
24 m
inute
25 m
inute
26 m
inute
27 m
inute
28 m
inute
29 m
inute
> 29 m
inutes
0
5
10
15
20
25
Percentage of Arrests Made at Burg-laries in Progress by the Minutes to
the Arrival of First Unit on Scene
The percentage likelihood of capture does not decrease with the passage of time.
1 to 3 Units
4 to 6 units
7 to 9 units
10 to 13 units
13 to 15 units
16 to 18 units
19 to 21 units
More than 21
units
0
5
10
15
20
25
30
35
40
45 Percentage of arrests made by number of units attending
The optimum number of units to send to a burglary in progress is 19 to 21.
Predictor Odds of Making an Arrest (OR)
Helicopter Attending 66%*Dog Unit Attending 41%**Number of Units Attending 13%***Number of Officers Attending 5%**Sergeant Attending 4%Time to arrive 0%
Conclusions
• Once interaction effects have been taken into account those factors that most strongly predict arrest remain deployment of the helicopter and the number of units deployed.
• For every additional officer the likelihood of making an arrest increases by 6%.
• Deploying more units is more effective than just deploying officers – better to send 2 single crewed units than 1 double crewed. For every additional unit the odds of making an arrest increases by 13%.
• The attendance of dog units is correlated with arrest, but is masked by the effect of number of officers.
• The impact of Sergeant attendance is not statistically significant.
• Burglary is hard to solve. Most burglaries have no solvability factors. The most powerful solvability factors occur infrequently.
• The recovery of forensic material is more powerfully correlated than expected, especially for completed burglaries.
• Solved attempted burglaries are more strongly correlated with burglaries in progress, witnesses and the offender being disturbed.
• Solved full burglaries are more strongly correlated with forensic recovery.
• It is possible to adopt a case screening model based on the presence of solvability factors.
• This is now ready for an RCT to test a case screening approach.