PRE-EXPERIMENTS AND QUASI-EXPERIMENTAL METHODS

Question 1

True experiments

A true experiment is one that leads to an unambiguous outcome regarding what caused an event
Un verdadero experimento es aquel que lleva a un resultado sin ambigüedades y es clara la causo que provocó el evento:

1. In a true experiment some type of intervention or treatment is implementes
2. En un experimento verdadero se implementa algún tipo de intervención o tratamiento
3. True experiments are marked by the high degree of control:
   A over the arrangement of experimental conditions
   B Assignment of participants
   C Systematic manipulation of IV
   D Choice of DV
4. True experiments are characterized by an appropriate comparison

Question 2

PRE- EXPERIMENTAL DESIGNS
O1 X O2

-where O1 refers to the first observation of a group, or pretest
-X indicates a treatment
-and O2 refers to the second observation, or posttest

Answer 2

BAD EXPERIMENT

Any obtained difference between the pretest and posttest scores could be due to the treatment or to any of several threats to internal validity
The results of a bad experiment are inconclusive with respect to the effectiveness of a treatment

Question 3

Cause-and-effect statements, such as the one made by this psychologist, are essentially impossible to make when the one-group pretest/posttest design is used.

1. How might a history effect threaten the internal validity of this study?
2. Explain how maturation likely plays a role in this study.
3. Are testing and instrumentation threats likely in this study?
4. Explain how statistical regression might influence the interpretation of these findings

Question 4

EXPERIMENTS IN THE LAB VS. EXPERIMENTS IN NATURE SETTINGS

CONTROL: in a natural setting, a researcher may not always have the same degree of control over the assignment of participant or over the conditions of an experiment that she or he would have in the lab.

GOAL: applied research is directed toward discovering the reasons for a phenomenon, but it is likely to be done only when knowing the reasons for an event will lead to changes that will improve the present situation

EXTERNAL VALIDITY: experiments in natural settings may therefore need to be done in order to establish the external validity of a laboratory finding

Consequences:
Applied experiments are likely to have consequences of greater immediate impact than those of laboratory research

Question 5

APPLIED RESEARCH
Random assignment is not always “fair” or “possible”
Quasi-experimental designs

PROBLEMS:
Obtaining permission to do research from individuals in positions of authority
Access to participants

Question 6

QUASI-EXPERIMENTS

Quasi-= resembling
Quasi-experiments include some type of intervention or treatment and they provide a comparison, but they lack the degree of control found in true experiments:
-Lack of randomization
I. e, children in one classroom or school and workers at a particular plant represent intact groups that might receive a treatment or intervention without the possibility of randomly assigning individuals to conditions.

Question 7

TRUE EXPERIMENTS
Random allocation of participants of conditions

Quasi experiment
Non-equivalent pre-existing groups

Question 8

THE NONEQUIVALENT CONTROL GROUP DESIGN

A treatment group and a comparison group are compared using pretest and posttest measures:
-There exists a group “like” the treatment group that can serve as a comparison group (not randomly assigned)
-There is an opportunity to obtain pretest and posttest measures from individuals in both the treatment and the comparison groups

Because a comparison group is selected on bases other than random assignment, we cannot assume that individuals in the treatment and control groups are equivalent on all important characteristics

Question 9

INTERNAL VALIDITY IN NONEQUIVALENT CONTROL GROUP DESIGN

adding the control group, you can control:
History, maturation, testing, instrumentation, regression to the mean WHY?

You cannot control:
Selection x Maturation, selection x history, selection x instrumentation, differential statistical regression

Question 10

INVALIDITY IN NONEQUIVALENT CONTROL GROUP DESIGN

Selection x Maturation
-Additive effect of selection and maturation occurs when individuals in one group grow more experienced, more tired, or more bored at a faster rate than individuals in another group
-more likely to be a threat in self-selected samples and when the comparison group is from a different population from the treatment group

Selection x History
-this problem arises when an event other than the treatment affects one group and no the other
-local history effects

Question 11

INVALIDITY IN NONEQUIVALENT CONTROL GROUP DESIGN

Selection x instrumentation
It occurs when changes in a measuring instrument are more likely to be detected in one group in group than they are in another.

Differential statistical regression
Differential regression can occur when regression is more likely in one group than in another
For example, consider a nonequivalent control group design in which the participants with the most serious problems are placed in the treatment group.

Question 12

EXTERNAL VALIDITY IN NONEQUIVALENT CONTROL GROUP DESIGN

What evidence is there that the particular pattern of results is restricted to a particular group of participants, setting, or time ?
The investigator must be ready to replicate an experimental finding with different populations, settings, and times in order time?

The investigator must be ready to replicate an experimental finding with different populations, settings, and times in order to establish external validity
The deductive process applied to questions of internal validity must also be used to examine a study’s external validity

We must be ready to live with the fact that one study is not likely to answer all questions about a research hypothesis

Question 13

TIME - SERIES DESIGNS
Researchers examine a series of observations both before and after a treatment

INTERRUPTED TIME-SEIRES DESIGN
TIME SERIES WITH NONEQUIVALENT CONTROL GROUP
TIME SERIES WITH SWITCHING REPLICATIONS

Question 14

INTERRUPTED-TIME SERIES DESIGN

Researchers can observe changes in a dependent variable for some time before and after a treatment is introduced
There is only one group
It can be used to assess the effect of a treatment in situations such as when a new product has been introduced, a new social reform instituted, or a special advertising campaign begun

Question 15

INTERRUPTED-TIME SERIES DESIGN

A discontinuity in the time series is the major evidence of an effect of treatment
Only abrupt changes in the time-series can be interpreted because gradual changes are indistinguishable from normal fluctuations over time

Answer 15

Incidence of smoking behavior just before and just after a hypothetical antismoking campaign

Question 16

INTERNAL VALIDITY IN INTERRUPTED-TIME SERIES DESIGN

Threats to internal validity due to maturation, testing, and regression are controlled in the simple interrupted time-series design
An effect of history is the main threat to internal validity in this type of design
Change of measurement (instrumentation) is also a threat

Question 17

INTERRUPTED TIME SERIES WITH NONEQUIVALENT CONTROL GROUP
Researchers make a series of observation before and after treatment for both a treatment group and a comparable comparison group.
The researcher must find a group that is comparable to the treatment group and that allows a similar opportunity for multiple observation before and after the time that the treatment is administered to the experimental group.

VALIDITY: it permits researchers to rule out many threats due to history

Question 18

INTERRUPTED TIME SERIES WITH SWITCHING REPLICATIONS

The same treatment or program is put into place in two different locations, but at two different points in time
There is no control group
If the outcome pattern in location 2 matches that of location 1, the researcher can be more confident about the generality of the phenomenon being studied

Question 19

KEY IDEAS (1)
Quasi-experiments provide an important alternative when true experiments are not possible
Quasi-experiments lack the degree of control found in true experiments; most notably, quasi-experiments typically lack random assigment.
Researchers must seek additional evidence to eliminate threats to internal validity when they do quasi-experiments rather than true experiments
The one-group pretest-posttest design is called a pre-experimental design or a bad experiment because it has so little internal validity

Question 20

KEY IDEAS (2)
In the nonequivalent control group design, a treatment group and a comparison group are compared using pretest and posttest measures
If the two groups are similar in their pretest scores prior to treatment but different in their posttest scores following treatment, researchers can more confidently male a claim about the effect of treatment
Threats to internal validity due to history, maturation, testing, instrumentation, and regression can be controlled in a nonequivalent control group design

Question 21

KEY IDEAS (3)
In a simple interrupted time-series design, researchers examine a series of observations both before and after a treatment
Evidence for treatment effects occurs when there are abrupt changes (discontinuities) in the time-series data at the time treatment was implemented
In a time series with nonequivalent control group design, researcher make a series of observation before and after treatment for both a treatment group and a comparable comparison group