Quasi experiemtal designs and field research

Download Report

Transcript Quasi experiemtal designs and field research

Quasi experiemtal designs
and field research
Variations in classical experiments
Post test only designs
 Used when pretesting might affect the
results
 To assess this could use a 4 group design,
experimental pre-post
 Experimental post
 Control pre-post
 Control post

Non-equivalent groups
Comparison group rather than control
group (difference is random assignment)
 Use of matching
 Widom’s study of child abuse and
criminality
 Abused matched with a non-abused group
on gender, race, age, and SES
 Problem with matching

Non-equivalent
Predicting parole risk
 Use of LSI
 3 jails, one (comparison) not informed of
LSI scores
 In all groups, LSI predictive of further
recidivism
 Jails who knew LSI scores released more
low risk offenders

Non-equivalent
Telephone service areas with caller ID
compared to those without services to
observe effects on obscene phone calls
 Would be deceptive if there are
differences in obscene phone calls from
area to area—probably not the case
 Less complaints in caller ID areas

Cohorts
Using a particular group that all begin at
the same time, compare to a group that
began at another time. Make assumption
of equivalence
 i.e., compare graduate students who
started in 2003 with those who started in
2004
 Police class, those sentenced to probation
in a particular month, etc.

Time series designs
Interrupted time series design
 Take baseline data, make an intervention,
collect data
 See p. 196
 First example, general trend, not clear
that the intervention made a difference
 Current downward trend in crime

Time series
Second pattern: random fluctuation
 3rd pattern: immediate effect (in this
example, incapacitation)
 4th pattern: more gradual effect
(deterrence?)
 Interrupted time series with nonequivalent
comparison group

Time series
Time series design with switching
replications
 If similar changes occur in DV in different
places at different times, corresponding to
when the intervention was introduced, it
makes it likely that the IV did affect the
DV

Field research
Best for topics that can best be
understood in their natural setting
 Example: nonverbal behaviors
 Relationship between environmental
design and crime requires observation of
the environment
 Pedestrians before and after street lighting
was enhanced

Types of participation
Full participant (deception, may affect
what is going on, safety issues,
incompatibility)
 Observing around the periphery of
criminal activity
 Observer-as-participant: identifies self as
research, interacts with subjects
 Police patrol studies (ride along)

Types of participation
Going native problem
 Complete observer, not part of the action
in any way. May be unobtrusive, or might
identify oneself as a research, but no
interaction
 Less able to ask questions

Observation
Observe, sometimes ask questions
 Questions are often more spontaneous,
unstructured “informal conversational
interview”
 Listening and probes

Gaining access
Formal organizations
 Sponsor, letter, phone call, meeting
 Gaining access to subcultures
 Sponsor/informant
 May be people working with criminals,
such as caseworkers, police, probation,
lawyers, private investigators, treatment
centers, ex-offenders, hangouts

Selecting subjects
Snowball sampling
 Potential biases, i.e., only people who
have been caught or treated
 Purposive sampling, sampling dimensions
 Group, location, time, weather

Recording observations
Cameras to take photos
 Video recordings
 Tape recorders
 Field notes—what we know, what we think
happened
 Sketchy notes, expand later, write out
everything
 Unstructured observation

Recording observations
Structured observations
 Instruments to guide observations
 Environmental surveys (BJA), may be used
to plan strategies
 Other observations
 Possibilities listed, recorded with details as
they happen

Combining with other data
Linking research methods
 i.e., combining observational studies of
neighborhoods with surveys of resident
perceptions and crime statistics

Examples of studies
Shoplifters
 How much? How much is identified?
 Participant observation—participants
pretended to be shoppers
 # shoppers who stole divided total # of
shoppers
 Sampled days and times

Shoplifters
Everyone who entered the store was
counted
 Systematic random sampling used to
select subjects
 Subjects followed and observed
 # thefts divided by the total observed

shoplifters
To determine detection rates, research
staff were used as confederate shoplifters
and some of them were observed by
research staff assigned to make
observations (double blind)
 Reliability of observers could thus be
assessed
 Reliability could then be used to adjust
shoplifting rates

Other studies
Seat belts—how many people where seat
belts?
 Sampled time of day, type of road and
observation site, density of auto
ownership
 Explicit instructions p. 307

Racial profiling
Problem with comparing race of drivers
stopped with race of distribution for a
resident population (i.e., more nonresidents may be stopped)
 Estimate of drivers by observing race from
toll booths
 Estimate of # of cars eligible to be
stopped

Profiling
Having observers drive 5 miles over speed
limit, count the number speeding and their
race
 Lambeth’s study—blacks 13.5% of drivers,
15% of those speeding. 35% stopped
were black and 73% of those arrested
after the stop were black.
 However, speeding not the only violation

Profiling

Lange study—examined only cases going
15 or more miles over the speed limit

Bars and violence: illustrates flexibility of
the method, changed study from one
examining why bars were violent (even at
violent bars, a low frequency behavior) to
what situations led to violence
Bars
Young working class, two groups in an
encounter where they are strangers
 Crowded, no entertainment
 High level of drunkenness (cheap drinks)
 Over aggressive bouncers
