14

Question 1

Planned comparisons?

Answer 1

similar to two sample t test, but using all samples to estimate SE

Question 2

Unplanned comparisons?

Answer 2

go in with a lot of groups and interested in knowing whether any of them are different from pairs.

Question 3

Tukey-Kramer test?

Answer 3

Done after finding variation among groups with sample-factor ANOVA. It compares every single group mean with all other group means.

Question 4

!!!Why not use a series of two-sample t tests?

Question 5

Steps of tukey-Kramer test?

Answer 5

*order the means
*H_0 = u1 = u2
H_0 = u1 = u3
H_0 = u2 = u3
*Compute SE with MS_error.

Question 6

With the tukey-Kramer method, the probability of making at least one type 1 error throughout the course of testing all pairs of means is no greater than the significance level of alpha.

Question 7

2 factor ANOVA?

Answer 7

Compare effects of two factors (two categorial variables) on a single continuous variable.

Question 8

Correlation coefficient: r?

Answer 8

describes the strength and direction of the linear relationship between two numerical variables with a parameter of rho and an estimate of r.

Question 9

Ranges of rho and r?

Answer 9

between -1 and 1. Zero means no correlation. Positive means positive correlation, and negative means negative correlation.

Question 10

Correlation assumes?

Answer 10

*Random sample
*X is normally distributed with equal variance for all values of Y
*Y is normally distributed with equal variance or all values of X.

Question 11

r is essentially an estimate of?

Answer 11

rho, so r has a sampling distribution.