T-tests

Question 1

what is a t-test used for?

Answer 1

used to compare two means or medians

Question 2

for one sample compared to a population, what test do you use?

Answer 2

one sample t-test

Question 3

for two sample groups, what t- test do you use?

Answer 3

unpaired or paired t-test

Question 4

what are the 4 t-test assumptions?

Answer 4

normal/gaussian distribution, randomly sampled, equal variances, data measured on interval or ratio scale

Question 5

t-tests assume ________ variances.

Answer 5

equal

Question 6

if the larger sample has a _________ variance, the test is less powerful

Answer 6

larger

Question 7

if the smaller sample has large variance, the _________________ increases

Answer 7

type I error

Question 8

what are the three types of t-tests?

Answer 8

one sample t-test, student’s/unpaired t-test, paired t-test

Question 9

What stats test do you use on this example? A professor wants to know if her intro stats class has a good grasp of basic math. Six students are chosen at random from the class and give a math proficiency test. The professor wants the class to be able to score at least 70 on the test. The six students get scores of 67, 89, 77, 68, 83, 98. Can the professor be at least 95% certain that the mean score for the class on the test would be at least 70?

Answer 9

one-sample t-test (compares sample to population mean)

Question 10

Which stats test would you use? An experiment is conducted to determine whether a new gasoline additive can increase the gas mileage of SUVs. SUVs were chosen randomly and put into either “additive” or “no additive” group. Gas mileage was determined in each group.

Answer 10

Student t-test (compares two samples)

Question 11

Which stats test would you use for this example? Does a week of tutoring help a group of students improve their scores on a calculus test?

Answer 11

paired t-test (before and after)

Question 12

what would be an inappropriate use of a t-test?

Answer 12

use it to compare more than two means