15 terms

# Chp 11

T Test For Two Related Samples
###### PLAY
In the repeated-measures t statistic, the value of the estimated standard error in the denominator is computed entirely from the sample data
False
In a repeated-measures study comparing two treatments with a sample of n=15 participants, the researcher measures two scores for each individual to obtain a total of 30 scores. The repeated measures t statistic for this study has df=29
False; The 30 scores are used to compute 15 different scores: df=14
If a set of n=16 difference scores has a mean of MD=4 and a variance of s(sqd)=36. Cohen's d for this sample is d=4/6
True
A repeated measures study with a sample of n=16 participants produces a repeated measures t=2.00. If effect size is measuring using r(sqd), then r(sqd)=4/20.
False; r(sqd)=4/19
High variance for a sample of difference scores indicates that the treatment does not have a consistent effect.
True
If other factors are held constant, the higher the variance is for a sample of difference scores, the lower the likelihood of rejecting the null hypothesis
True
A repeated measures study would not be appropriate for which situation?
A researcher would like to compare individuals from two different populations. (Two difference populations will require two different samples).
A repeated measures study and a matched subjects study are both used to compare two treatments. If each study uses a total of 30 participants, then what are the df values for the two studies?
repeated measures df=29
matched subjects df=14 (study uses 15 matched pairs)
A repeated measures exp. & an independent measures exp. both produce t statistics with df=20. How many individuals participated in each experiment?
n=22 for independent measures (2 groups, each n-11
n=21 for repeated measures (1 group n=21
In general, what characteristic of the difference scores are most likely to produce a significant t statistic for the repeated-measures hypothesis test?
a large number of scores & a small variance
What's indicated by a large variance for a sample of difference scores?
a consistent treatment effect & a high likelihood of a significant difference

A large variance indicates that the difference scores are widely scattered.
A researcher is using a repeated-measures study to evaluate the difference btw two treatments. If there's a consistent difference btw the treatments then the data should produce
a small variance for the difference scores & a small standard error

Consistent difference scores produce a small variance & less error
For which of the following situations would a repeated-measures design have a substantial advantage over an independent measures design
few subject available & individual differences are large

RMD: requires few participants & removes the ind dif
Which of the following would have little or no influence on effect size as measured by Cohen's d or by r(sqd)?
Increasing the sample size

sample size has little or no influence on measures of effect size
Which of the following is not true of a repeated-measures design compared to an independent measures design?
The repeated measures design is less likely to reject the the null hypothesis.

RMD typically has a smaller standard error & is more likely to detect a real treatment effect.