Research Designs
Review -- research
General types of research
– Descriptive (“what”)
– Exploratory (find out enough
to ask “why”)
– Explanatory (“why”)
Unit of analysis: “object, entity
or process” under study
– Contains the variables
being measured
– Case: A single instance
of a unit of analysis
Review - variable
Any characteristic of a unit of analysis that is not fixed, meaning it can
differ or change
– How were officers accidentally killed
– During which period (pre- or post-Ceasefire) were Boston youths shot
Any concept that can be divided into subcategories or values
Only limitation is that a variable must be able to have different values,
scores or levels
– Must be conceptually free to change
– Number of officers accidentally killed each year
– How officers were killed
– Mean number of Boston youth shot dead each month
– Period when Boston youth were shot dead (pre- or post-Ceasefire)
– Assigning a measurement to a variable
Review - distributions
An arrangement of cases in a sample or population according to their values or
scores on one or more variables
Statistics – mean, median, mode, range, standard deviation – summarize distributions
Review - association and causation
Association means that the
values of two or more variables
change together
– In Boston, the number of
youth shot dead appears
to be associated with the
study period
– After invoking Ceasefire
the mean number of
youths slain by gunfire
Causation means that changes
in one variable cause corresponding changes in another variable.
The causal variable is called the “independent” variable (here it’s the time
The effect variable is called the “dependent” variable (here it’s the mean
number of monthly deaths)
So, did Ceasefire cause the reduction?
Non-experimental designs
Principles of non-experimental designs
• Begin with a hypothesis
– Changes in independent variables(s)  changes in dependent
– Lower income  more crime
• Assess the hypothesis by collecting data on variables of interest.
– Data usually reflects the values of variables at one point in time
– Data can also be collected in “waves,” at succeeding points in
– In non-experimental designs investigators only collect data they do nothing that might affect the values of the variables
• Data sources
– Field observations
– Surveys
– Official sources (public records, census, etc.)
Data source: field observations
Non-experimental designs
Research question: do police officers take harsher legal measures if youths display a
bad attitude?
Hypothesis: worse demeanor  harsher disposition
Researchers rode along with cops to observe their interactions with youths
Researchers did NOT intervene -- they
let things be
Researchers coded...
– Independent variable:
youth’s demeanor
– Dependent variable:
officer disposition
At a later time they used statistical
techniques to assess whether youth’s
demeanor was associated with
officer disposition in the hypothesized
direction (the worse the demeanor, the
harsher the disposition)
Depending on the strength of this
association they might conclude:
– There is a cause-and-effect
relationship between the variables: hypothesis confirmed
– The association does not go beyond what could be obtained by chance:
hypothesis rejected
Non-experimental designs
Data source: surveys
Non-experimental designs
Data source: official sources
Non-experimental designs
Data sources: surveys + official
Issues in non-experimental designs
Non-experimental designs
Causal order: Did the change in the independent variable precede (come
before) the change in the dependent variable?
Poverty  crime
Crime  poverty
Intervening variables: Could lack of education or living in a violent area
be the more proximate (closer) cause of crime?
Poverty  poor education  crime
Here poverty is still the cause, but it affects crime through intervening
variable education, which is the more proximate cause
Spurious relationship: What seems to be a relationship is bogus
― Often caused by a strong association between the independent
variable of interest (e.g., poverty) and another independent variable
(e.g., poor social controls) which turn out to be the real cause
Poor social controls  crime
Experimental designs
Principles of experimental designs
– Eliminate other possible “causes” (e.g., that it’s education, not poverty)
– Set the causal order (e.g., know you are testing crime  poverty)
1. Randomly assign cases to two or more groups. Random assignment
insures that the mean values of the independent variable(s) will be about
the same for each group.
2. Designate one or more groups as “experimental” and one as “control”
3. Measure the dependent variable (time 1) for each group
4. Intervene in the experimental group by adjusting the level of the
independent variable of interest
5. Post-measure dependent variable (time 2) for each group. If the
differences between experimental and control groups are “statistically
significant” they can be attributed to the intervention.
Simple experiment
( X ) DVt1…IV….DVt2
( C ) DVt1…..……DVt2 (no intervention)
Experimental designs
Hypothesis: SOCP reduces recidivism
Independent (causal) variable: SOCP (yes/no) (categorical/nominal)
Dependent (effect) variable: recidivism (rearrest rate, continuous)
Randomly assign youths being released to either X or C
Random assignment makes them about equal overall for background
factors such as age, criminal record, disciplinary history, etc.
Give X (experimental group) special intensive supervision
This is called an “intervention”
C (control group) gets regular supervision
Wait two years
Compare recidivism (rearrest) rates for both groups
Does the X group have a significantly lower rate?
1973 Kansas City Patrol Experiment
Experimental designs
Research question: Does routine patrol deter crime?
Hypothesis: Routine patrol reduces crime
1. Independent (causal) variable: Patrol
(categorical/ordinal), with three values:
– C = Same amount of patrol as before
– R = Less patrol than before
– P = More patrol than before
2. Dependent (effect) variable: crime rate
3. Randomly divide an area into 15 beats
4. Measure crime in each beat
5. Randomly assign each a different value of the independent variable
– Five C (control) beats: same patrol as usual
– Five experimental beats: less patrol than before (“R”, reactive)
– Five experimental beats: more patrol than before (“P”, proactive)
6. After one year compare crime rates
Quasi-experimental designs
Quasi-experimental designs
Experiment that lacks random assignment to groups
– Groups might differ along a key independent variable (“matching” often used
to try to make up for this)
Experiment without a control group
– An extraneous event might be the true cause of the change in the dependent
A non-experimental design that
mimics an experiment
– A known intervention did take
place (e.g., it’s known that the
level of the independent variable
did change at a certain time)
– Measures of the dependent
variable are available for the
periods before and after the
Some issues with experimental designs
Experimental designs
According to the Kansas City experimenters, there was no significant
difference in crime rates between the experimental and control groups.
– Since neither increasing nor decreasing patrol made a difference, the
hypothesis that random patrol can reduce crime was rejected.
However, the experiment was later criticized:
– Level of the independent variable (amount of patrol) was not sufficiently
increased in the proactive beats to be able to demonstrate a statistically
significant effect
– Due to contamination by other units, level of patrol was not sufficiently
reduced in the reactive beats to be able to demonstrate a statistically
significant effect
Other constraints
– Practicality
• Could we experimentally test poverty  crime?
– Ethics
• Should we experimentally test poverty  crime? We really cannot
make people poor to see what happens!
Class assignment
Hypothesis: Higher income persons drive more expensive cars - Income  Car Value
We test this hypothesis with a non-experimental design
• Independent variable: income
– Categorical, nominal: student
or faculty/staff
• Dependent variable: car value
– Categorical, ordinal: 1 (cheapest),
2, 3, 4 or 5 (most expensive)
– Will also be used, later, as a
continuous variable
• Data
– Each team systematically samples
10 cars in student lot
– Each team systematically samples
10 cars in faculty/staff lot
• Coding
– Use operationalized car values to enter values for the dependent variable
– Also draw graphs of each distribution by car value
– Each student fills in and keeps their own coding sheet (all coding sheets for each team
should be identical, and of course, correct.)

similar documents