experimental design 2:. good experimental designs have high internal validity: to unequivocally...

17
Experimental design 2:

Upload: roderick-stewart

Post on 17-Jan-2016

213 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Experimental design 2:

Page 2: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Good experimental designs have high internal validity:

To unequivocally establish causality, we need to ensure that groups in our study differ systematically only on our intended independent variable(s) and not on other confounding variables as well.

Page 3: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Threats to the internal validity of an experiment's results (e.g. Campbell and Stanley 1969):

Time threats:HistoryMaturationSelection-maturation interactionRepeated testingInstrument change

Group threats:Initial non-equivalence of groupsRegression to the meanDifferential mortalityControl group awareness of its status.

Participant reactivity threats:Experimenter effects, reactivity, evaluation apprehension.

Page 4: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Types of experimental design:

1. Quasi-experimental designs:No control over allocation of subjects to groups, or timing of manipulations of the independent variable.

(a) “One-group post-test" design:

treatment measurement

Prone to time effects, and no baseline against which to measure effects - pretty useless!

Page 5: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

(b) One group pre-test/post test design:

measurement treatment measurement

Now have a baseline against which to measure effects of treatment.Still prone to time effects.

Statistics marks 2006

course change Statistics marks 2007

Page 6: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

(c) Interrupted time-series design:

Still prone to time effects.

measurement

measurement

measurement

treatment

measurement

measurement

measurement

time

Page 7: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

(c) Interrupted time-series design (cont.):

Deaths for Friday nights, 10-12 pm; Saturday and Sunday nights, 10 pm - 4 am. Vertical line: implementation of British Road Safety Act, Oct. 1967 (Ross, Campbell & Glass, 1970).

Page 8: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

(c) “Static group comparison" design:

Subjects are not allocated randomly to groups; therefore observed differences may be due to pre-existing group differences.

measurement

measurement

treatment (experimental gp.)

no treatment (control gp.)

group A:

group B:

Page 9: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

2. True experimental designs:

(a) Post-test only/control group" design:

Random allocation of subjects to groups should ensure that observed differences are not due to pre-existing group differences - but can't be certain!

measurement

measurement

treatment (experimental

gp.)

no treatment (control gp.)

group A:

group B:

random allocation:

Page 10: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

(b) Pre-test / post-test control group" design:

Ensures that groups are indeed comparable before the experimental manipulation was administered.

measurement

measurement

treatment

no treatment

group A:

group B:

random allocation:

measurement

measurement

Page 11: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

(c) Solomon four group design:

Ensures that groups are indeed comparable before the experimental manipulation was administered, and that pre-testing hasn't affected performance. (Uses lots of subjects, so rarely used).

group B:

measurement

measurement

treatment

no treatment

group A:

random allocation:

measurement

measurement

measurement

measurement

group C:

group D:

treatment

no treatment

Page 12: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Between-groups versus within-subjects designs:

Between-groups (independent measures) -Each subject participates in only one condition of the study.e.g. sex differences in memory.

Within-subjects (repeated measures) - Each subject does all of the conditions in a study.e.g. effects of alcohol on memory.

Mixed designs -Mixture of both.e.g, sex differences in effects of alcohol on memory.

Page 13: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Advantages and disadvantages of between-groups and within-subjects designs:

Between groups Within subjects

Ease of design Straightforward. Can be more complicated.

Number of subjects required

More Fewer

Carry-over effects between conditions

No Possible

Sensitivity to experimental effects

Lower Higher

Reversibility of conditions

Unimportant Essential

Page 14: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Within-subjects designs and order effects:

Order effects: practice, fatigue, boredom.

A fixed order of conditions would cause order to vary systematically with condition - results are uninterpretable, because they could be due to order effects, experimental manipulations or both.

Solutions:(a) Randomise order of conditions:e.g. with 3 conditions, subjects randomly get orders ABC, BCA, ACB, CBA, CAB, BAC.(b) Counterbalance order of conditions:e.g. equal numbers of subjects get each order.

Page 15: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

A simple within-subjects design:

treatment A

treatment B

measurement B

treatment B

measurement A

measurement A

treatment A

measurement A

subject 2:

subject 1:

time

Page 16: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Disadvantages of the experimental method:

Intrusive - participants know they are being observed, and this may affect their behaviour.

Experimenter effects.

Not all phenomena are amenable to experimentation, for practical or ethical reasons (e.g. post-traumatic stress disorder, near-death experiences, effects of physical and social deprivation, etc.)

Some phenomena (e.g. personality, age or sex differences) can only be investigated by methods which are, strictly speaking, quasi-experimental.

Page 17: Experimental design 2:. Good experimental designs have high internal validity: To unequivocally establish causality, we need to ensure that groups in

Conclusion:

Experiments are a useful tool for establishing cause and effect - but other methods (e.g. observation) are also important in science.

A good experimental design ensures that the only variable that varies is the independent variable chosen by the experimenter - the effects of alternative confounding variables are eliminated (or at least rendered unsystematic by randomisation).