Week 3: Within sjts Designs Flashcards
What are within sjts designs?
compares TWO or MORE different treatment conditions (or compares a treatment and control), by observing or measuring the same group of individuals in all treatment conditions being compared.
Another word for within sjts designs? (especially in stats)
repeated-measures experimental design
Advantages of within sjts ?
-Removes or reduces threats from individual differences e.g. cant end up with all males in one group
Because it’s the same participants, there can be no threat from assignment bias
-By controlling for the individual differences, we can remove problems of increased variance
-Fewer participants needed
-Especially useful if special population or expensive procedure
Disadvantages of within sjts?
Vulnerable to certain types of threat:
>Environmental threats
>Time-related factors including these: history, maturation, instrumentation, regression towards the mean, order effects (practice, fatigue, carry-over effects).
What are environmental threats?
characteristics of the test environment that might change from one condition to another.
Times of day
Rooms taken in
Weather
Noise
What are time related threats?
threats to internal validity related to the passage of time
Time related threats
-History effects?
any outside, environmental events that influences the participants scores in one treatment differently than it would in another treatment.
e. g. events that occur in person’s life, at school, at home, work
e. g. fire alarm goes off in college dorm and students are up all night the day before the next treatment.
Time related threats
-Maturation?
Any age-related/growing, physiological OR psychological change that occurs in participants during the study and influences person’s scores.
e. g. in elderly population, eye sight goes down hill
e. g. language intervention study given to 3 year old and then when she’s 6 (maturation effects).
Time related threats
-Regression to the mean
Idea that an extreme score in a test (either high or low), tends to be less extreme in the next test/measurement. Usually as a function of chance/guessing better or more poorly the next time.
Time related threats
-instrumentation
change in measuring instrument and problems with its calibration OR change in an observers ability to observe behaviour overtime. threat to internal validity. Can refer to either.
E.g. scales becoming slowly inaccurate
e.g. an observer thinks child smacking was discipline, while another observer codes it as aggressive.
Time related threats
- order effects
* carry over effects?
carry over effects= first treatment causes lingering aftereffects that CARRY OVER into the next treatment and affect performance.
Doesnt have to just be memory related. Could be to do with treatments. e.g. you give coffee first and then another different test on weed and its effects (BUT you’re
still feeling the effects of caffeine)
Time related threats
- order effects
- progressive error?
* practice?
* fatigue?
Progressive error: changes in participant’s behaviour or performance that are related to general experience in a research study but not related to a specific treatment.
Two examples of this are:
>Practice: improvement in performance due to practice
>Fatigue: decline in performance due to tiredness
What can we do to reduce order effects?
1) Choose a between-subjects design
2) Control time
3) Counterbalance
What is counterbalancing?
It involves varying the order of treatments to equal out order effects. It’s the process of matching treatments with respect to time.
e.g. ppl undergo the treatment conditions in different orders so that every treatment has some ppl in it who experience the treatment first, some for whom it is second or third etc… In this way, the treatments are matched or balanced with respect to time.
Limitations of counterbalancing?
If you have multiple (more than two) treatment conditions, then you need n! sequences. Going to have to deal with a high number of sequences.
