Case-Control Studies
EPI 200A
October 29 and November 3, 2009
2
Case-Control study; the historyA disease looking for a cause
Vincent Memorial Hospital: 8 women of 15-22 years of age with vaginal cancer between 1966-1969
A very rare disease, especially in young women No common exposure to tampons or drugs; none used
oral contraceptives (OCs) 1 case to 4 controls without the disease matched on
age, born in the same hospital Similar data on X-rays, maternal smoking, pregnancy
complications, childhood diseases, etc.
3
Case-Control study; the historyA disease looking for a cause
7 of 8 case mothers had used diethyl-stilbesterol (DES); none of the 32 mothers for controls had used DES.
Herbst et al. N Engl J Med 1971; 284: 878-81.
4
Exp Cases Non-cases
+
-
a
c
b
d
a/c > b/d if a cause
a/c and b/d are exposure odds
5
The idea of a case-control study dates back to Hippocrates …..
6
”By paying attention to what was common to every case, and particular to each case,to the patient; the prescriber and the prescription,to the epidemic constitution generally, and its local mood,to the habits of life and occupation of each patient,to his speech, conduct, silences, thought, sleep, wakefulness,and dreams – their content and incidence,to his pickings and scratchings, tears, stools, urine, spit and vomit,to earlier and later forms of illness during the same prevalence,to critical or fatal determinations,to sweat, chill, rigor, hiccup, sneezing, breathing, belching,to passage of wind, silently or with noise;to bleedings, andto piles.”
Hippocrates in first epidemics
7
The philosophy of the case-control study was taken from JSM as stated in MacMahon, Pugh and Ipsen: Epidemiologic Methods. London: Churchill, 1960.
John Stuart Mill’s logic of causation
1. Method of difference
2. Method of agreement
Only qualitative estimates
8
Broders 1920: JAMA; 74: 656-64.Cancer of the lip; 537 cases and 500 controls; similar smoking habits (80%), 78% of cases smoked the pipe; 38% among controls.
Schreck and Lenowitz 1947: Cancer Research; 7: 180-187.Cancer of the penis; circumcision as a protective factor.
1950s smoking and lung cancer
9
Doll and Hill on Smoking & Carcinoma of the Lung. BMJ September, 1950 / UK, Mortality Rates
This increase was also seen in USA, Canada, Australia, Denmark, Switzerland.
Year Rates 100,000 Males Females
1901 - 20
1936 - 9
1.1
10.6
0.7
2.5
10
Doll and Hill on Smoking & Carcinoma of the Lung. BMJ September, 1950
Better diagnostic tools? Hypotheses: Air pollution (cars, industries) or tobacco
smoking Reports from Germany 1939, 3 out of 86 lung cancer
patients were non-smokers. Similar reports from the U.S. in 1950 (Schrek, Wynder, Graham)
11
Methods 20 London Hospitals were asked to notify all patients with
cancer of the lung, stomach, colon, and rectum. Interviewers were also asked to select non-cancer patients of the same sex, age and from the same hospital.
Hospital diagnosis on discharge accepted 2370 cancer cases identified
> 75 years (150) Wrong diagnosis (80) No interview (too late (189))
(too ill (116))
(dead (67))
(too def, etc. (37))
12
Methods, cont.
No patients refused Study population
Carcinoma of lung: 709 Carcinoma of stomach: 206 Carcinoma of colon/rectum: 431 Other malignant diseases 81 Controls (other patients) 709 Other cases 335 Excluded 4 All 2475
Other cases – interviewed as cancer cases but the diagnosis was not confirmed or redundant non-cancer controls – without a match
13
Assessment of smoking
Smoking habit change as a function of e.g. price (duty raised in 1947) and disease
Were asked: 1. smoked any period of their life
2. age at which they started or stopped
3. current intensity
4. changes in smoking habits
5. type of tobacco smoking
6. inhaled or not
A smoker = at least 1 cigarette per day at least 1 year
14
Assessment of smoking, cont.
Two interviews done 6 months apart
First Interviewer
Cigarette
Second Interviewer Cigarette
0 1 5 15 25 50+ All
0
1
5
15
25
50+
8 1
4 1
1 13 3
4 9 1
1 3 01 0
9
5
17
14
4
1
All 8 6 18 13 5 0 50
15
Assessment of smoking, cont.
Then they showed Lung cancer patients smoked more, had smoked for a longer time period,
smoking a pipe carried less risk
Inhaling:
Assessing 688 living cancer patients, 61.6% said they inhaled. 650 other patients, 67.2% said they inhaled.
Sex Disease Non Smokers Smokers P
Males Lung cancer
Controls
2(0.3%)
27(4.2%)
647
622 <0.001
Females Lung cancer
Controls
19(31.7%)
32(53.3%)
41
28 <0.02
16
Assessment of smoking, cont.
Interpretation Selection bias = more lung cancer patients from rural
areas restriction to greater London
– same results
= control patients – did they have a disease that prevented them from smoking
or was prevented by smoking?
- different patient control groups – same results
Information bias interviewed before they were diagnosed blinding of interviewers – did not
work
compared smoking data for patients suspected for lung cancer but who
did not have the disease
17
Assessment of smoking, cont.
It is not reasonable, in our view, to attribute the results to any special selection of cases or to bias in recording… there is a real association between carcinoma of the lung and smoking.
This is not necessarily to say that smoking causes lung cancer. The association would occur if carcinoma of the lung caused people to smoke or if both attributes were end-effects of a common cause.
Only carcinogenic substance found in tobacco smoke is arsenic. Because carcinogenic testing at this time was based upon a skin-rat-test.
18
Disease ORs and exposure ORs are similar
Exp D D N
+
-
a
c
b
d
N+
N-
ND ND
Closed Cohort
Disease odds = = ratio
Exposure odds = = ratio
a/b = axd = a/cc/d cxb b/d
a/N+ c/N-
b/N+ d/N-
a/ND b/ND
c/ND d/ND
a/bc/d
a/cb/d
19
a/bc/d
RR =CI+
CI-
~CI+ / (1- CI+ )
CI- / (1- CI -)
1-CI close to 1, if the disease is rare.
So the exposure odds ratio is equal to the disease odds ratio
and RR is closed to the disease OR when the disease is rare
OR ; = a/cb/d
20
Well suited to the study of rare diseases or diseases with
long latency periods Allows study of multiple potential causes of a disease
Relatively quick to mount and conduct
Relatively inexpensive
Requires comparatively few subjects
Existing records can occasionally be used
Often no risk to subjects
Advantages of the Case-Control Method
21
Relies often on recall or records for information on past exposures
Validation of information is difficult or sometimes impossible
Control of extraneous variables may be incomplete Selection of an appropriate control group may be
difficult Vulnerable to selection bias Rates of disease in exposed and unexposed
individuals cannot be determined (not always true)
Disadvantages of the Case-Control Method
22
In principle, provides a complete description of experience subsequent to exposure, including rates of progression, staging of disease, and natural history
Allows study of multiple potential effects of a given exposure, thereby obtaining information on potential benefits as well as risks
Allows for the calculation of rates of disease in exposed and unexposed individuals
Permits flexibility in choosing variables to be systematically recorded
Allows for thorough quality control in measurement of study variables (not time in historical cohorts)
Advantages of the cohort method
23
Large numbers of subjects are required to study rare diseases
Potentially long duration for follow-up Current practice, usage, or exposure to study
factors may change, making findings irrelevant Relatively expensive to conduct Maintaining follow-up is difficult Control of extraneous variables may be incomplete
Disadvantages of the cohort method
24
A disease “looking” for a cause Case-control study A cause “looking” for a disease Follow-up study
25
Modern case-control methods
The terminology is still confusing. You will find terms such as retrospective studies, TROHOC studies, case-referent studies, case-base studies, case-cohort studies, case-non-case studies and case-control studies.
If we forget John Stuart Mill and start with a cohort and the estimates of effect measures this study provides, we have:
26
A cohort study of CS2 exposure and AMI
E D+ D- N T
+-
400200
9,6009,800
10,00010,000
9,8009,900
RR = 400/10,000) / (200/10,000) = 2.0IRR = (400/9,800) / (200/9,900) = 2.02OR = (400/9,600) / (200/9,800) = 2.04
27
If we for some reason would reconstruct OR by using a more economic sampling approach, we would do a case-non-case
study:
E D+ Controls (D-)
+-
400200
9,600/19,400 x 600 = 296.99,800/19,400 x 600 = 303.1
N 600 600
OR = = 2.04 400/200296.9/303.1
28
A cohort study of CS2 exposure and AMI
E D+ D- N T
+-
400200
9,6009,800
10,00010,000
9,8009,900
RR = 400/10,000) / (200/10,000) = 2.0IRR = (400/9,800) / (200/9,900) = 2.02OR = (400/9,600) / (200/9,800) = 2.04
29
If we wanted to estimate RR, we would select a different sampling strategy:
The case-cohort study
E D+ Controls (D-)
+-
400200
10,000/20,000 x 600 = 30010,000/20,000 x 600 = 300
N 600 600
OR = (400/200) / 300/300) = 2.0
This is a study for a fixed cohort with no loss to follow up.
30
A cohort study of CS2 exposure and AMI
E D+ D- N T
+-
400200
9,6009,800
10,00010,000
9,8009,900
RR = 400/10,000) / (200/10,000) = 2.0IRR = (400/9,800) / (200/9,900) = 2.02OR = (400/9,600) / (200/9,800) = 2.04
31
In a cohort with loss to follow-up or in a dynamic population, one would aim at estimating the IRR. As it is seen in the cohort example, we need to sample controls to estimate thedistribution of exposed and unexposed observation time.
E D+ Controls (D-)
+-
400200
9,800/19,700 x 600 = 298.59,900/19,700 x 600 = 301.5
N 600 600
OR = 2.02
32
To obtain this estimate, we sample from the population at risk at the time of the onset of the disease (incidence density sampling). In a small population like this:
12345678
D
D
ttime
3 is our case at time t, and the population at risk is number 1, 4, 5, 6 and 7.
All selected controls that get the disease during recruitment should also become cases and controls may be selected more than once.
D
33
Summary:
Assume an underlying follow-up study like
Exp D+ D- N T
+-
ac
bd
N+N-
t+t-
RR = (a/N+) / (c/N-) or (a/c) / (N+/N-)IRR = (a/t+) / (c/t-) or (a/c) / (t+/t-)OR = (a/b) / (c/d) or (a/c) / (b/d)
The right-hand figures are what we want controls to estimate.
34
Food poisoning: diarrhea and fever within 48 hours following a picnic
Food/drinks N Disease
All 480 24
Shrimp salad 122 8
Olives 326 20
Fried chicken 430 10
Barbecued chicken 183 18
Beans 256 12
Potato salad 375 17
Bread 178 7
Beer 466 23
How would you get data?
How would you analyze data?
How would you do a case-control study?
35
Cohort
RRB-chicken = = 4.869
Case cohort approach
Sampling fraction, r, 48/480 = 0.10
4.869 =
4.869 =
4.869 =
1402.27 – 2.921N- = 1.8N-
N- = 297
Exp Cases Controls
+
-
18
6
9.15
14.85
24 24
18/183 6/297
18/(480x0.10-0.10N-) 6/0/10N-
18x0.10N-
6x(48-0.10N-)
1.8N-
288-0.6N-
36
Summary:
Assume an underlying follow-up study like
Exp D+ D- N T
+-
ac
bd
N+N-
t+t-
RR = (a/N+) / (c/N-) or (a/c) / (N+/N-)IRR = (a/t+) / (c/t-) or (a/c) / (t+/t-)OR = (a/b) / (c/d) or (a/c) / (b/d)
The right-hand figures are what we want controls to estimate.
37
In a case control study we get estimates of relative effect measure. We usually cannot estimate absolute measures of association, why not?
In some situations we can
38
We sample a fraction r then
r+N+/r-N- = N+/N- if r+ = r-
r+t+/r-t- = t+/t- if r+ = r-
r+b/r-d = b/d if r+ = r-
Since we in a study with a known source population, N, get data on RR and have data on a and c, we get:
RR = a/(rN-rN-)
c/rN-
That equation can be solved for N- given r is known and absolute risks can be estimated
39
Or in the book (ME3) terminology:
Follow-up
I+ = I- =
We sample a rate r of controls per unit time
B+/T+ = B-/T- = r or B+/r = T+ and B-/r = T-
Exp D D T
+
-
A+
A-
B+
B-
T+
T-
A+
T+
A-
T-
40
In the case-control study, we have the following pseudo rate:
A+/B+ and A-/B-
To get incidence rates I+ = A+/T+
We:
I+ = A+/B+ x r orI+ = A+/B+ x B+/T+ = A+/T+
If r is not known we still get:
= =
= = =
requires incidence density sampling
IRR
Pseudo rate+
Pseudo rate-
A+ /B+
A-/B-
A+ /((B+ /T+)T+)A-/((B-/T-)T-)
A+ /(r xT+)A-/(r xT-)
A+/T+
A-/T-
41
Case-control studies are not conceptually retrospective. They do not compare cases with non-cases, but exposed with not exposed. They apply a specific sampling strategy to provide the relative effect measures in the underlying cohort.
They provide estimates with far less observations than in the cohort study. Given the necessary exposure data and sampling data are available, they are equivalent in quality to the cohort approach. In fact they represent just a different approach to obtain the cohort result.
Case-control studies are the studies of choice if you can reconstruct exposure data back in time (for the exposure of interest as well as for confounders). They represent often the design of choice in genetic studies
42
If you want to study if bacterial vaginoses causes preterm birth, how would you sample cases and controls?
43
If you want to study if antibiotics prevent preterm births, what is the source population (study base)?
If you want to study if use of bicycle helmets prevents head injuries, what is the source population (study base)?
44
The described type of case-control study is a study with a primarily defined study base. Cases come from a well-defined cohort and we
may sample controls from this cohort. Or
Cases come from a well-defined population. We have complete ascertainment and we may sample controls from this population at given points in time.
Be careful if these conditions are not met. Sometimes cases are prevalent cases.
45
Since prevalence is a function of incidence and duration (D) P/I-P= I x D
Determinants of prevalence reflect aetiologic as well as prognostic factors.
46
Exp D+ S+ S- N
+-
3030
2010
1020
1,0001,000
RR = (30/1,000) / (30/1,000) = 1.0
Example: Exercise and AMI
Exp DS+ Cohort
+-
2010
1515
N 30 30
OR = (20/10) / (15/15) = 2.0
47
The same rules as for risks will apply for estimating effect measures based on prevalence data.
A case-non-case study will estimate
)1/(
)1/(
PP
PPOR
Control sampling from the entire population (including prevalent cases) will estimate:
P
POR
48
Controls are ideally randomly sampled from the same population that gave rise to the cases.
Controls will then estimate the exposure distribution in the source population but this estimate will be subject to random sampling variation.
49
It will often be difficult to make random sampling and:
If the selected sampling strategy produces exposure estimates that are interchangeable with the exposure distribution in the study base, results will be unbiased. If not, effect estimates will be biased.
50
If all cases cannot be ascertained (no registry, not all come to the health care system), a case-control study should be designed to take this lack of ascertainment into consideration. This type of case-control study is usually ”weak”. Our source population definition will be:
All potential cases define the source population.
The conditions that actually led to case identification should lead to identification of all member of the source population. (those who would enter the case group if they have the conditions that were seen for cases – may depend upon disease characteristics, insurance conditions, financial means etc)
51
How to design a case-control study on male risk factors of infertility. Only half of those with an infertility problem seek medical help?
52
The method of choice is to use a register that includes the entire population that gave rise to the cases, without such register it is
more difficult to make sure all have same chance of being selectedRDD - random digit dialling
who has a telephonewho is homehow many are homewho has more numbershow many do not respond to unsolicited calls
Neighbourhood controlsmake sure they were residents at case diagnosis risk of
overmatchingFriend controls
++
++
Selection of population controls
53
Complicated if time must be taken into consideration. Best would be “density sampling” or could be sampled at one point in time.
One option:1. Select a date at random from the case ascertainment
period
2. Select a person at random from the list
3. If resident at the selected date (1) - then OK as a control4. Repeat 1-3 until the desired number of controls is
reached5. Exp. Data is collected according to date at onset of the
disease or the random date (1)
Population controls - sampling from a list of list of residents
54
Sampling within an existing cohort e.g. diet and cancer
a. make list of time units (e.g. 1 month) for all participants
b. sample from these units
Sampling of time - not persons
55
Use of patient controls rather than population controls.
This idea stems from Mill’s “method of scientific inference”, not from sampling from the underlying cohort.
56
If case ascertainment depends on a factor (e.g. access to medical care) sampling of controls must have similar dependency (e.g. hosp. Controls)
Advantages of hospital controlseasy to samplebetter response ratesymmetry in data collection
57
The “control disease” must neither be caused nor prevented by the exposure
If cases are referred to the case ascertainment hospital - hospital controls must have the same referral pattern
Use a single disease if an ideal ‘control’ disease exist, but it may also be acceptable to:
Exclude all diseases with a known or suspected association with exposure
- and make use of the remaining diseases as controls
One control group, or more than one
58
Two stage sampling
First stage case-control sampling could be based upon inexpensive (perhaps already existing) data.
A second stage sample could take analytical costs into consideration. Could be:
1. All cases and a random sample of controls
2. Oversampling of more informative cases and/or cohorts. For example, those with the highest exposure levels. Such a sampling strategy must be taken
into consideration when doing the analysis.
Exposure
Levels
Cases Controls
0
1
2
c
a1
a2
d
b1
b2
59
Matching
Definition:
Cases and controls are selected to be similar withrespect to certain variables - usually controls are selected to be similar to cases. Maching could be 1:1,1:2, …, 1:5.
60
12345678
D
D
tTime
At time t, 1, 3, 4 and 6 are candidates. Which ones fit the matching criteria?
61
If matching is done for four age groups, two sex groups and four socioeconomic groups, there are 4 x 2 x 4 = 32 classifications - it may be difficult to find a match.
62
Matching is usually done on confounders, but matching in a case-control study does not in itself eliminate confounding why?
2
E
C
D
Confounding requires:
1. The confounder is a cause (1)
2. The confounder (c) is associated with E (2).
1
63
Matching on (1) does not eliminate a causal association - causation is a fact of life independently of our manipulations.
We compare exposed and not exposed. We should not try to compare cases with non-cases. We try to identify not-exposed according to our counterfactual ideal. We have no similar guidelines for cases and controls. We may use restrictions –but then they should be used for cases as well as controls. It is a mistake to think controls should be as healthy as possible.
Matching may produce a well-balanced data set for analyses.
Matching usually requires matched analysis. The matched sets are kept in the analyses and should be
identifiable.
64
Matching may even lead to confounding (create an association between E and C) in situations where this was not present in the study base. All of this is very different from using matching in follow-up studies.
The effect of the matching variables on the outcome cannot be studied.
Matching is not always done on confounders; could be done on time (incidence density sampling) or on a sampling criteria (like data or birth).
Is birth weight correlated with cancer of the testis? Select controls among boys born in the same hospital before and after the birth of the cases. What is wrong with that?
65
Evaluation of a screening programme for cervical cancer matching on the ”GP factor”.
Setting: A doctors screen 80% B doctors 20%
Example:
E
C
D
66
A 10,000 8,000 sc+ 40 D(0.5%)2,000 sc- 20 D(1.0%)
B 10,000 2,000 sc+ 10 D(0.5%)8,000 sc- 80 D(1.0%)
RR = 0.5
67
Case-cohort study
E D Cohort
+-
50100
6684
OR = RR = 0.64
68
Stratified analysis or analysis of matched sets will solve the problems
GP E D Cohort OR
A+-
4020
4812 0.50
B+-
1080
1872 0.50
69
In order to have true confounding, GPs must be a risk factor of cervical cancer
E
C
D
70
Setting:
A 10,000 8,000 sc+ 40 D(0.5%)2,000 sc- 20 D(1.0%)
B 10,000 2,000 sc+ 20 D(1.0%)8,000 sc- 160 D(2.0%)
RR = 0.5, but now confounding in the study base
71
The cohort:E D All RR
+-
60180
10,00010,000 0.33
Matchedcase-cohort study:
E D Cohort OR
+-
60180
84156 0.62
72
Again, stratification will solve the problems
GP E D Cohort OR
A+-
4020
4812 0.50
B+-
20160
36144 0.50
73
Cross-sectional study – a survey
An observational study in which all variables are measured at a single point in time
74
Are used to estimate prevalences of diseases and frequencies of exposures.
Diseases of short duration will not be well presented since prevalence is a function of incidence and duration
75
A study of peripheral vascular disease (PVD) in Scotland and smoking
Measures of association? Interpretation?
Smoking
Ever Never All
PVD
No PVD
23 8
1704 1291
31
2995
All 1727 1299 3026
76
Because exposure and disease are assessed at the same time, cross-sectional studies may not be able to establish that exposure preceded onset of the disease process.
77
78
79
80
81
82
Case-crossover design
Cases and controls should come from the same study-base. Fulfilled if cases are also the controls.
For most exposures, we move from being exposed to unexposed. If we have no carry-over effect and the cause-effect relationship is short, we may compare IR in the two time segments.
IRexp / IRnon-exp
83
As always a case-control study samples the underlying population experience. Each case represents the follow-up of one person.
If cases are their own controls, we adjust for subject characteristics, sometimes for confounding by indication.
84
If the time period before onset of the case status equals the reference time period, 4 outcomes are possible
TypeCase-period
Reference period
1234
expexpnot-expnot-exp
expnot-expexpnot-exp
Type 1 and 4 provide no indication of causal relevance.
Type 2 indicates causal association. Type 3 indicates the opposite.
3
2
type
typeOR
85
The design rules out time-stable personal habits as confounders but not time-dependent factors.
Selection bias if type 2 and type 3 cases decide on participation based upon their case status.
Information bias is a potential problem if exposure status is based upon recall.
86
The case-crossover design is biased if the exposure varies over the time period under study.
The case-time study tries to incorporate adjustment for this change over time by including data on exposure used over time for controls.
This will not automatically adjust for confounding by indication. Data on disease severity are needed.
87
Case-crossover studyN Engl J Med 1997;336:453-58
Aim:Use of cellular telephones - a risk factor for motor vehicle accidents?
Methods:Case-crossover = case ascertainment North YorkCollision Reporting Centre, Toronto. July 1, 1994- August 31, 1995, 10-18 hours, Monday-Friday.
Note! Centre does not include accidents with injuries, only substantial property damage.
Criteria:Excl. drivers who had no cellular phone or no billing records.
88
Case-crossover studyN Engl J Med 1997;336:453-58
Timing of the accidentSubject statementPolice recordsCall to emergencyTwo out of 3 = exact
Timing of exposure:10 minutes prior to accident
Reference exposure time:Workday before the accidentSame weekdayThe week before the accidentAdjustment for driving
89
Case-crossover studyN Engl J Med 1997;336:453-58
5890 drivers - 1064 had a phone - 742 participated - 699 had a billing record
Time of accident: exact 231 inexact 468
170 had used the phone 10 minutes prior to the accident
37 the weekday before
crude OR 6.5 (4.5, 9.9)
adj OR 4.3 (3.0, 6.5)
90
Table 2. Relative risk of a motor vehicle collision in 10-minute periods, according to selected characteristics
CharacteristicsNo. with telephone
use in 10 min before collision
Relative Risk (95% CI)
All subjects 170 4.3 (3.0-6.5)
Age (yr)< 2525-3940-54≥ 55
21954410
6.5 (2.2 - )4.4 (2.8 - 8.8)3.6 (2.1 - 8.7)3.3 (1.5 - )
SexMale Female
12347
4.1 (2.8 - 6.4)4.8 (2.6 - 14.0)
High-school graduation
YesNo
15317
4.0 (2.9 - 6.2)9.8 (3.0 - )
Type of job ProfOther
34136
3.6 (2.0 - 10.0)4.5 (3.1 - 7.4)
91
Characteristics
No. with telephone use in
10 min before collision
Relative Risk (95% CI)
Driving experience (yr)
0-910-1920-29≥ 30
40673627
6.2 (2.8 - 25.0)4.3 (2.6 - 10.0)3.0 (1.7 - 7.0)4.4 (2.1 - 17.0)
Cellular telephone experience (yr)
0 or 12 or 34 or 5≥ 6
51393644
7.8 (3.8 - 32.0)4.0 (2.2 - 12.0)2.8 (1.7 - 6.7)4.1 (2.3 - 12.0)
Type of cell phone
Hand-heldHands free
12941
3.9 (2.7 - 6.1)5.9 (2.9 - 24.0)
92
Fig. 1. Relative Risk of a collision for different control periods
Day before Workday Weekday Max-use Matching day day
10
8
6
4
2
0
Relative risk
of a collision
Comparison Day
93
Fig. 2 Time of cellular-telephone call in relation to the relative risk of a collision
10
8
6
4
2
0•
• •
•
94
Fig. 3 Consistency of relative risks obtained from different collision times
100.0
10.0
1.0
0.1
Morning
Aftern
oon
Evening
Other
Monda
y
Tuesday
Wed
nesd
ay
Thurs
day
Frid
ayW
eeke
nd
•• • • • •
••
•
•
Time of Day Day of Week