Lectures 7-9

Question 1

what determines the probability that a sample of ratio-interval scale data was taken from a population with a pre-determined mean

Answer 1

One-sample t-test

Question 2

what is an a priori constant

Answer 2

pre-determined mean (c)

Question 3

(one-sample t-test, 2-tailed) H0

Answer 3

μ = c (calculated mean = pre-determined mean)

Question 4

(one-sample t-test, 2-tailed) HA

Answer 4

μ ≠ c (calculated mean ≠ pre-determined mean)

Question 5

(one-sample t-test) test statistic

Answer 5

t

Question 6

(one-sample t-test) degrees of freedom

Answer 6

n - 1 (n = sample size)

Question 7

what are 2-tailed tests

Answer 7

no direction of the difference (not less than or greater than) || can also denote if there is change or no change

Question 8

what are 1-tailed tests

Answer 8

testing in a particular direction (more/less, better/worse, higher/lower)

Question 9

What is HA in ratio-interval scale data

Answer 9

whatever the question asks, H0 will be opposite to the question asked

Question 10

What happens when we have a -t in 2-tailed?

Answer 10

ignore (-) due to symmetrical t-distribution

Question 11

What happens when we have a -t in 1-tailed?

Answer 11

check to see if HA is satisfied by inputting mean of the sample in order to ignore (-) || if HA is not satisfied, immediately accept H0

Question 12

confidence intervals (CI) and limits

Answer 12

it can determined with 95% confidence that the mean of a population lies between two values (the lower and upper limit)

Question 13

(confidence intervals) what does a smaller interval indicate?

Answer 13

a smaller standard error

Question 14

what would happen if a 99% confidence interval was employed

Answer 14

the critical value = 0.01 = more confident the larger/wider the interval gets

Question 15

what does the t-statistic calculate?

Answer 15

calculates the probability where the sample came from the population where H0 is true || t(0.05)(1 or 2 tailed)(DF=n-1)

Question 16

What to consider when dealing with 2 samples of ratio-interval scale data

Answer 16

see if 2 samples have equal variances (variance-ratio test), compare the means of the samples, and the relationship between those samples (does S1 values increase while S2 values decrease or increases?)

Question 17

What to consider when dealing with central tendency tests

Answer 17

are samples paired or independent? are the assumptions met?

Question 18

(central tendency tests) independent samples

Answer 18

values in one sample are not in any way related to values in the other sample

Question 19

(central tendency tests) paired samples

Answer 19

each value in one sample is associated with a particular value in the other sample (i.e.: via biological link)

Question 20

why use paired samples?

Answer 20

more direct comparison, reduces the extra extraneous variation (controlled) || cancels out other variables that may affect data

Question 21

(central tendency tests) two assumptions

Answer 21

RSNDP and homoscedasticity

Question 22

RSNDP

Answer 22

Randomly Sampled from a Normally Distributed Population || tests if data is normally distributed

Question 23

what test can test for normality

Answer 23

D’Agostino Pearson k^2

Question 24

what terms describe for equal or unequal variances

Answer 24

Homoscedastic/Heteroscedastic

Question 25

what tests for homoscedasticity

Answer 25

variance-ratio test

Question 26

(variance-ratio test) H0

Answer 26

σ1(^2) = σ2 (^2)

Question 27

(variance-ratio test) HA

Answer 27

σ1(^2) ≠ σ2 (^2)

Question 28

(variance-ratio test) test statistic

Answer 28

F(0.05)(2-tailed)(DF of larger s^2)(DF of smaller s^2)

Question 29

What if the assumptions are not met?

Answer 29

must do data transformations

Question 30

types of data transformations

Answer 30

logarithmic, square root, arcsine sq.rt.

Question 31

which data transformation is the "go to" transformation when not dealing with specific scenarios

Answer 31

logarithmic: x' = log(x)

Question 32

which data transformation is used when the original raw data are now counted as whole numbers

Answer 32

square root

Question 33

which data transformation is used when you have proportions or percentages

Answer 33

arcsine square root transformations: x' = arcsin(sqrt(x))

Question 34

what tests for differences in central tendency, BUT DO NOT test for differences in the PARAMETER

Answer 34

non-parametric tests

Question 35

when are non-parametric tests appropriate to use for?

Answer 35

can use when assumptions are not met or for ranked data (ordinal-scale data), but run the risk of making a type II error

Question 36

two examples of nonparametric tests

Answer 36

Mann-Whitney U test and Wilcox-Paired Sample test

Question 37

Can one-sample t-tests, contingency tables, and goodness-of-fit tests be considered nonparametric tests?

Answer 37

one-sample t-test is a robust statistical test so it is NOT affected if assumptions are not met, and although contingency tables and goodness-of-fit tests are nonparametric, no assumptions are made

Question 38

What does a two-sample t-test tests for

Answer 38

difference in the means of two independent samples of ratio-interval scale data

Question 39

(two-sample t-test) 2-tailed H0/HA

Answer 39

H0: μ1 = μ2 || HA: μ1 ≠ μ2

Question 40

(two-sample t-test) 1-tailed H0/HA

Answer 40

H0: μ1 (>,≥,,≥,

Question 41

(two-sample t-test) test statistic

Answer 41

tests if the population means are equal

Question 42

(two-sample t-test) degrees of freedom

Answer 42

DF= DF1 +DF2