ch 11
assumptions of related samples t statistic
-dependent observation -normal distribution
matched subjects test
-each individual in one sample is matched to an individual in the other sample -the matching is done so that the 2 individuals are equivalent with respect to a variable that the researchers would like to control
pro of repeated-measures study
-is uses exactly the same individuals in all treatment conditions -there's no risk that the participants in one treatment are diff from the participants in another
variance and effect size (d and r^2)
-larger variance produces smaller effect size -N has no effect on the value of cohen's d and only a small effect on r^2
counterbalancing
-participants are randomly divided into 2 groups, with one groups receiving treatment 1 first and then 2, and the other group receiving treatment 2 first and then 1 -goal is to distribute any outside effects evenly over the two treatments
repeated measures
-requires fewer participants than the independent measures -is well suited for studies that take place over time -reduces or eliminates problems caused by individual differences
factors that can influence the outcome of a hypothesis test with a t statistic
-size of MD --larger Md increases the likelihood of rejecting the null and increases the effect size -variability of scores and N influence the magnitude of the SMD --larger N = smaller error --larger variance = larger error, which produces a smaller t statistic and reduces change of finding significant result
repeated measures design (or within-subject design)
-the dependent variable is measure 2 or more times for each individual in a single sample -the same group of subjects is used in all treatment conditions
cons of repeated measures design
-the structure of the design allows for factors other than the treatment effect to cause a participant's score to change from one treatment to the next (b/c individuals are measured in 2 different conditions, usually at 2 diff times, outside factors over time can be responsible for participants' changes in scores -order effects // testing effects
unlike the other CIs in ch 9 and 20, the CI for a repeated measures t is influenced by many factors OTHER THAN THE SIZE OF THE TREATMENT EFFECT
-the width depends on the % of confidence used --a larger % produces a wider interval -the width depends on N --larger N produces a narrower interval
in independent measures, every score represents ....
a different person -but for dependent measures, the same participants are measured in both treatment conditions (therefore, each person counts as one score)
CI
can be used as an alternative method for measuring and describing the size of the treatment effect (for T TESTS)
order effects
changes in scores that are caused by participants in an earlier treatment and can distort the MD found
one way to deal with order effects is through _____________
counterbalancing
repeated samples t is based on ....
difference scores (D) rather than raw scores (X values)
t/f: a repeated measures t-test is based on raw scores
false, it's based on difference scores
if there is reason to expect strong-time related effects or strong order effects, your best strategy is to...
not use repeated-measures design and to use independent measures, so that each individual participates in only one treatment and is measured only once
in t tests, the _______ is known but the __________ is unknown
population mean (just by the null; still kind of not known though) standard deviation (and with that, variance, o^2)
which design has the most advantages? repeated measures or independent measures design?
repeated measures
which type of t-test has more power?
repeated measures (AKA within subjects) b/c it eliminates individual differences
the sign of each D (in the table) shows you...
the direction of the change
in repeated measures design, n refers to...
the number of D scores, not the number of X scores in the original data`
t/f: there's only one D score for each subject and so the n refers to the number of D scores not the number of X scores
true
what affects cohen's d
variance
what affects the hypothesis test
variance and sample size
one big advantage of the repeated measures design is that it reduces ....
variance by removing individual differences, which increases the chance of finding a significant result --variance and SE are reduced