Week 6: Experimental Research Designs Flashcards
Experimental research is often referred to as:
And what’s its purpose
-randomised trial
-clinical trial
-randomised clinical trial
-randomised controlled trial
Purpose: support a cause and effect relationship between the independent variable (treatment) and dependant variable (outcome)
Experimental research allows us to do what?
Allows the researcher to control for the effects of extraneous variables (ie nuisance variables)
-any factor that isn’t directly related to the purpose of the study, but may affect the dependant variable
-when extraneous variables are not controlled, this is called CONFOUNDING
eg testing a new weight loss pill on a group who just started Jenny Craig
What are the characteristic of experimental research?
1) the independent variable must be manipulated by the researcher
2) a control or comparison group must be Incorporated in the design
3) subjects must be randomly assigned to groups
What is the purpose of the control group?
Control groups is used to compare to experimental group
-helps to rule out extraneous factors
Subjects in the control group may receive:
-placebo
-usual care
-sham procedure
-no treatment
What is random assignment involve and why do we do it?
Random assignment refers to way patients are assigned to groups
-used to make groups equivalent regarding prognostic factors eg pain levels
-random assignment doesn’t always work, the groups may still be different after randomisation
-each subject has an equal chance of being assigned to any group
-random assignment helps to control for extraneous variables which are known and unknown
-if we can assume that 2 groups are the same at baseline, we can be confident that aft treatment is applied the difference is due to he independent variable.
RANDOM ASSIGNMENT IS NOT THE SAME AS RANDOM SAMPLING
Random assignment
Blinding
Targets for blinding
Blinding:
-assignments is often hidden from researcher or subject, to avoid the temptation of allocating patients with certain traits to groups that will receive special treatment
Targets for blinding:
-research staff recording outcome measure
-research staff providing treatment
-research subjects
Designs may be
-single blinded, double blinded, triple binded. Eg double blinded randomised trial
Types of experiments
Pretest-posttest control group design
-both groups are measured before and after the treatment
So differences between the groups can be attributed to the treatment (cause and effect)
-you can have a multigroup pretest-posttest group design (more than 2 groups)
Types of experiments
Posttest only control design
Advantages and disadvantages
-the pretest is not administered to either group
Advantages:
-less labour and less costly to perform
-may be most appropriate when a pretest is impractical or has the potential to skew the studies results
Disadvantages:
-you don’t know if the groups were equivalent at baseline!
Types of experiments
One-way repeated measures design
What is the problem with this approach?
-subjects are exposed to all levels of the independent variable (they get all treatments)
-there is no control group (subjects act as their own controls)
Problem: order effects: the outcome may be dependant on he order for the measurements eg what if they are fatigued by try 3
Solution?
Randomised the order of the independent variable
Types of experiments:
Crossover design
What is the problem with this approach?
It is used when there are 2 levels of the independent variable and the patients condition is stable over time.
Subjects are randomised to 2 groups:
1) those who receive treatment A followed by treatment B
2) those who receive treatment B followed by treatment A
Problem?
-the first treatment may be exerting an effect when the second treatment is started
Washout period: a sufficient period of time to eliminate the prolonged effects of the treatment
Efficacy vs. effectiveness
The effects of treatment can be refers to as treatment effectiveness or efficacy
Efficacy: the benefit of a treatment delivered in a under highly controlled and ideal environment
Effectiveness: the benefit of a treatment delivered in a pragmatic manner under “real world” conditions
