Correlation
A correlation between two variables in a sample is represented with the statistic ____.
r
How is simple linear regression different from multiple linear regression?
Simple Linear Regression: Can use one variable to predict the value of another variable
Multiple Linear Regression: Can also use two or more variables to predict the value of another variable
How many independent variables are needed for a factorial ANOVA?
2+
What is the related t-test to a one-way repeated measures ANOVA?
Paired samples t-test
Research has shown that losing even one night’s sleep can have a significant effect on performance of complex tasks such as problem solving. To demonstrate this a sample of n = 20 college students was given a problem-solving task at noon on one day and again at noon the following day. The students were not permitted to sleep between the two tests. For each student, the difference between the first and the second score was recorded.
Paired samples t-test
What scale of measurement is each variable in a correlational analysis (nominal, ordinal, or continuous)?
continuous and continuous
(X predictor can also be categorical or ordinal)
What is the simple linear regression equation?
Y^i = bXi + ⍺
How many levels are needed for each IV?
2+
What is the total variance (SST) the sum of?
Between-groups variance (SSB) + Within-groups variance (SSw)
When we create our hypotheses do we put them in the context of the sample or the population?
Population
The number that indicates no correlation between variables is _____.
Zero
What is extrapolation?
Predicting the outcome variable using the predictor variable that is beyond the range of our dataset.
If the ANOVA is significant, what do we do next and why?
We run posthoc tests to identify where the significant difference(s) are between groups.
Write the null and alternative hypotheses.
H0: mu1 = mu2 = mu3
H1: at least one mu is different from another
Occurs when we fail to reject the null when the null is false.
Type II error
One of the assumptions we operate under when calculating correlation coefficients is that the relationship between variables is linear. True or false
True
How do we find the residual or ei?
ei = Yi - Y^i
actual score - predicted score
Write the f-statement for this main effect (A):
dfA = 2
dfw = 18
F-statistic = 6.2327
p = .03246
F(2,18) = 6.23, p =.032
How do we find the f-statistic by hand?
MSB/MSerr
What does effect size tell us?
How large the difference is between our sample mean and the population mean according to the null hypothesis.
All outliers weaken the correlation coefficient between 2 variables. True or False
False (In-line outliers strengthen correlation coefficient. Off-line outliers weaken correlation coefficient.)
What is the statistic for the coefficient of determination and what does it tell us?
r2 or R2
It tells us what percentage of variance in y can be explained by x.
If you run a factorial ANOVA and there is a significant interaction and two significant main effects what do you examine first?
The interaction
What correction do we use to not worry about the sphericity assumption affecting our calculations?
Greenhouse-Geisser correction
How does the following affect statistical power?
-increased sample size
-decreased effect size
-decreased variability
-increase statistical power
-decrease statistical power
-increase statistical power