For unlimited access to Textbook Notes, a Class+ subscription is required.
Chapter 9: Experimental Research
- Experimental research builds on the principles of a positivist approach more directly than
do the other research techniques.
- Begin with a hypothesis, modify something in a situation, and compare the outcomes
with and without the modification
Research questions appropriate for an experiment
- The issue of an appropriate technique
- Research questions for experimental research
oCan’t be survey questions, need to have a scenario where something can be
oBetter suited for micro-level
-Random Assignment: dividing subjects into groups at the beginning of experimental
research using a random process, so the experimenter can treat the groups as
equivalent. It is a way to divide or sort a collection of cases into two or more groups to
increase ones confidence that the groups do not differ in a systematic way. The
assignment is automatic.
- In probability theory, random describes a process in which each case has a known
chance of being selected. Random means a case has an exactly equal chance of ending
up in one or the other group.
- Difference between random sampling and random assignment: Figure 9.1 (196)
How to randomly assign
- A researcher begins with a collection of cases and then divides it into two or more
groups by a random process, such as asking people to count off or tossing a coin.
Matching versus random assignment
- Matching has one problem: what are the relevant characteristics to match on, and can
one locate exact matches? People are just way to different.
Experimental design logic
- 7 parts of the experiment:
oTreatment: (independendent variable). This is what the research modifies
oDependent variable: outcomes, they are the physical conditions, social
behaviours, attitudes, feelings or beliefs of subjects that change in response to a
treatment. They are measured
oPretest: the measurement of the DV prior to treatment
oPost-test: the measurement of the DV after the treatment
oExperimental group: receives the treatment
oControl group: does not receive the treatment
oFigure 9.2 for the order
Steps in conducting an experiment
- Decide on topic, narrow it into a testable research problem or question, and then
develop a hypothesis with variables.
- Crucial early step is to plan a specific experimental design
- Confederates: people who pretend to be other subjects but who actually work for the
researcher and deliberately mislead subjects.
Types of design
-Classical experimental design: Have random assignment, a control group, an
experimental group, and pretests and post tests for each group. Example on page 201
-Pre-experimental design: designs that lack random assignment, or use shortcuts, or
are weaker than the classic. They may be substituted in situations where an
experimenter cannot use all the features of a classical experimental design, but they
have weaker internal validity.
oOne-shot case study design: only an experimental group and a post test (no
pretest). Example in book. Lacks random assignment
oOne group post-test design: one group, a pretest and a post test. Lacks a
control group and random assignment. Example in book
oStatic group comparison: two groups, no random assignment, only a post-test.
Example in book
-Quasi-experimental designs: stronger than pre-experimental designs. They are
variations on the classical one that an experimenter uses in special situations or when
an experimenter has limited control over the IV. Called quasi because they are variations
of the classical experimental designs.