Exam 3: Chapters 8, 9, 10, 11 Flashcards
internal validity
the independent variable is the cause of the experiment.
Confounding variables
A variable that varies with the independent variable. The variables are intertwined so you cannot determine which variable is the cause of the observed effect.
Posttest-only design
1: two equivalent groups
2: introduce independent variable
3: measure the effect of the independent variable on the dependent variable.
Pretest-posttest design
given before the experimental manipulation is introduced.
EX: participants, pretest: dependent variable then variable. page 160
Morality (attrition)
The drop out factor in experiments.
Repeated Measures Design ( within-subjects design)
A measure in which the same subjects (participants) are assigned to each group.
Independent groups design (between-subjects design)
One procedure where participants are randomly assigned to the various condition so that each participates in one group.
Random Assignment
Independent groups design, are assigned randomly to the conditions.
order effect
order of presenting the treatments effects the dependent variable.
Practice Effect (Learning Effect)
Improvement in participant performance with repeated testing.
Fatigue Effect
deterioration in performance
carryover effect
effect of the first treatment carries over to influence the response to the second treatment.
Counterbalancing
All possible orders of presentation are included in the experiment. EX: half of a study assigned to high and half assigned to low study.
Latin Square
A technique to control for order effects without having all possible orders
a limited set of orders constructed to insure that :
1) each condition appears at each ordinal position
2) each condition precedes and follows each one time.
Straightforward
Manipulate variables with instructions and stimulus presentations.
Straightforward Manipulation
manipulate variables with instruction and verbal or written form, videotape, or a computer.
Staged Manipulation
simulation manipulate the independent variable.
Confederate Manipulation
an accomplice to the observer. Acts as a participant.
Strength of the manipulation
two levels of the independent variable.
Manipulation Check
attempt to directly measure whether the independent variable manipulation has the intended effect on the participant.
Self- Report
measure attitudes, liking for someone, judgements about personality characteristics, etc.
Behavioral Measure
measure of direct observations of behavior.
Physiological Measure
recording of the bodies response.
Ceiling effect
the task is so easy anyone can do it.
Floor effect
The task is so difficult no one can complete it.
Demand characteristic
informs participant of the purpose of the study.
placebo effect
participants receive a harmless pill or injection that will have no effect on participant.
experimenter bias or expectancy effects.
experimenter develops expectations about how participants should respond.
single blind
the participant is unaware if they recieved the placebo or active medicine.
Double blind
the participant and person distributing the pill or injection do not know if it is a placebo or real medicine.
demand characteristics, what can be done to minimize these.
use deception, filler items, or conducted in field setting.
expectancy effects what can be done to minimize these.
practice behaving consistently with all participants, run all conditions simultaneously, use automated system, use a double blind experiment.
why use a pilot study
try out see how long to conduct future research.
describe how to do a manipulation check
useful in a pilot study to see if the independent variable is having the right effect. EX: using an attractive person to conduct interview and rate if the participant rates the person as attractive.
Factorial Design
designs with more than one independent variable.
main effect
the first information about the effect of each independent variable taken by itself. EX: A design with two independent variables has 2 main effects.
Interaction
an interactions is between the two independent variables.
it is the times that both variables cross paths. or connect.
IV x PV design
an experimental and non experimental design.
why two or more levels for IV in an experiment
The outcomes are more clear on a graph
threats to internal validity
history effects, instrument decay, maturation defects, regression towards the mean, testing effects, and mortality.
Single subject design ( single case experimental design)
used to see if an experimental manipulation had an effect on a single research participant.
baseline
subjects behavior is measured over time in a baseline control period.
Reversal design
ABA design: (A) baseline period (B) treatment period (A) baseline period. it can continue for stronger correlation to an ABAB or ABABAB this makes the outcome of treatment stronger and not due to chance.
Multiple Baseline Design
the effectiveness of the treatment is demonstrated when a behavior changes only after the manipulation is introduced. must be observed under multiple circumstances.
Program Evaluation
research on programs that are implemented to achieve some positive effect on a group of individuals. EX: programs for schools, work, or communities.
- Needs Assessment
- Program Theory Assessment
- Process Evaluation
- Outcome Evaluation
- Efficiency Assessment
Quasi-Experimental Design
address the need to study the effects of an independent variable in setting in which the control features of true experimental designs cannot be achieved.
One-Group Posttest- Only Design
Participant—> independent variable—> dependent variable
sit next to stranger measure time until person leaves
cannot get viable answer because maybe of different possibilities.
One-Group Pretest- Posttest Design
measure participant before the manipulation and again afterward.
problems: history, maturation, instrument decay, testing
History Effects
event or person that occurs before the manipulation.
EX: Angelina mastectomy
Maturation
changes that occur systematically overtime.
EX: bored, fatigue
Testing Effects
sensitizing
EX: keeping a journal of how much you smoke a day, might make you smoke less before experiment.
Instrument Decay
the measuring instrument changes over time.
EX: scale, forgetting to record data
regression toward the mean
participant being selected due to high or low testing.
Non-equivalent control group design
employs a separate control group, but the participants in the two conditions. this makes a confounding variable. This results in selection differences or selection bias.
selection difference (bias)
participants who for the two groups in the experiment are chosen from existing natural groups.
Nonequivalent control group pretest-posttest design
one of the most useful quasi experimental designs. not a true experimental design group assignment is not random and may not be equivalent.
