KIN 232 Module 4 Flashcards
Experimental designs
Specifically testing hypotheses in a systemic manner
Deliberate consideration of variables
A major aim is to examine a cause and effect relationship
- Manipulation of variables (independent variables)
- Control group
- Random assignment
Experimental research
Participants are assigned to an interventional group
Researcher manipulates the level of the independent variable by group
Types of independent variables
Active variable: an independent variable that can be manipulated (ex drug dosage)
(Experimental research must have at least one active variable)
Attribute variable: an independent variable that cannot be manipulated (genetics, geography)
Control groups
The group you compare your intervention group to
Shares many characteristics as experimental/intervention as possible except the actual intervention
Group equivalents
Random assignment
every participant has the same chance of being assigned to any group in the study
Guarantee traits balance out in an infinite population but not in a finite sample
Assumption that there is balance
Blocking and Random
Step 1: Randomization– randomizing within blocks of a trait (sex, age)
Step 2: Blocking – separating people based on attribute variable (not random)
Step 3: Randomly assigned people from each block into control or intervention group (randomization)
Matching
Not randomization
match on key variables and then assign them to opposite groups
Not for experimental
Bias associated with it
Limitations to experimental
- MUST manipulate variables
- Controlling many variables causes a poor external validity
- expensive/difficult to manipulate intervention
Masking
Individuals involved in the experiment are prevented from knowing certain information about the study
Ex. Intervention or group they belonged into
Typically masking the participant
Masking participants
Expectation that experimental group will influence behavior
Masking researchers administering intervention
Could change how researcher administers intervention
Masking of Researchers Evaluating Outcome
Experimental group will have better (or worse) may influence measurement, especially where not entirely objective
Placebo
A dummy treatment administered to the control group to distinguish specific and nonspecific effects of the experimental treatment
Participants are generally masked to group assignment by administration of a “placebo condition”
The placebo effect
observable, tangible, measurable effects, nothing to do with the intervention
effects in cases of pain, depression, insomnia, anxiety
Number of assessments: Randomized control trial
(most common way to determine cause and effect in experimental design)
Pre test and post test
Number of assessments: Post only disadvantages
Disadvantage: doesn’t ensure the group are all the same at the beginning (group equivalents) , only relying on random assignment since we are missing pre test
Number of assessments: Repeated measures
A midpoint observation during intervention
To determine when the intervention will have its effect (temporal aspect)
A washout period after post-test where they stop administering the intervention
How long does it take for the intervention to linger after administering
Number of Experimental groups: Different levels of groups/independent variables
An additive effect that will improve dependent variable (0 mg to 100 mg to 200 mg – dose effect)
Dose response relationship (dose value linearly or non-linearly related to independent variable)
To determine what dose is the most effective
Number of Experimental groups: Repeated measures between subject (between subjects design)
Participants are assigned to and only receive 1 level of the independent variable
Examines the variability and differences BETWEEN groups
“What is the effect of each intervention”
Number of Experimental groups: Repeated measures within subject design (within subject design)
Participants receive every level of the independent variable
Examines the variability and differences within a person, and of course examines the effect of the independent variable
The different levels of the independent variable can be given to the participants in a randomized or fixed order
You act as your own control and compare outcomes to your results
Number of Experimental groups: Crossover design
Allows for washout period in between interventions
Reduces the likelihood of carryover effects
Preferred when only two interventions are used
Having more than 1 independent variable allows for
creation of a factorial design (multifactoral)
Number of independent variables..
2 independent variables referred to as 2 way design
3 variables refers to 3 way design
2 independent variables with 2 levels of each
2x2 factorial design
2 independent variables, one independent variable with 2 levels and the other independent variable with 3 levels
2x3 factorial design
3 independent variables with 2 levels of each
2x2x2 factorial design