testing for differences

Question 1

what is cohen’s d?

Answer 1

• measures the effective size by measuring the differences between two sample means
• takes the standard deviation into account as well

Question 2

how do you calculate cohen’s d for a population or a sample?

Answer 2

1. calculate the mean SD
   pop = s.d(1) +s.d(2)/2
   sample = s(1) + s(2)/2
2. calculate cohen’s d
   pop = mean(1)-mean(2)/mean SD
   sample = m(1)-m(2)/mean SD

Question 3

the bigger the cohen’s d….

Answer 3

the larger the difference, the less overlap of scores there are between two samples, meaning there was a larger effect

Question 4

what would be considered a small cohen’s d value?

Answer 4

0.2

Question 5

what would be considered a medium cohen’s d value?

Answer 5

0.5

Question 6

what would be considered a large cohen’s d value?

Answer 6

0.8

Question 7

degrees of freedom: one sample t-test

Answer 7

N-1

Question 8

degrees of freedom: paired t-test

Answer 8

N-1

Question 9

degrees of freedom: independent groups t-test

Answer 9

(Na-1) + (Nb-1)

Question 10

degrees of freedom: pearson’s r

Answer 10

N-2

Question 11

degrees of freedom: chi square 1 variable

Answer 11

no of categories-1

Question 12

degrees of freedom: chi square 2 variable

Answer 12

(no of rows -1) x (no of columns -1)

Question 13

parametric tests (2)

Answer 13

• find smaller details about effects in data
• assumes - normal distribution, no extreme scores and variances of samples/populations roughly equal

Question 14

non-parametric tests

Answer 14

• focus on ranks not scores
• sample sizes may not be small, variances may not be equal, data may not be normally distributed

Question 15

what is the non-parametric alternative to the independent t test?

Answer 15

mann-whitney U

Question 16

what is the non-parametric alternative to the paired/related t test?

Answer 16

wilcoxon signed rank

Question 17

what is the non parametric alternative to pearson’s r?

Answer 17

spearman’s rho

Question 18

how to conduct a pearson’s r test

Answer 18

1. calculate mean and s.d for group X and group Y
2. calculate how far each score deviates from its group mean
3. multiply x and y deviations together and add up all the values in this column
4. calculate the sample covariance by doing: total covariance/n-1
5. r = sample covariance/s.dX times s.dY
6. df = N-2

Question 19

how to conduct a spearman’s rho test

Answer 19

1. convert data into ranks - separate for each group
2. calculate the difference in ranks for each group - i.e RANKx-RANKy
3. square the differences. add this column together
4. spearman’s rho: (1-value from S3)/n(n2-1)
   - where N is the size of the X or Y sample in a related condition

Question 20

how to conduct a 1 variable chi-squared test

Answer 20

1. calculate expected fr: total number of values/total number of categories
2. calculate difference score: expected-actual
3. square the differences
4. squared frequency/expected frequency
5. chi = sum of squared frequencies/expected frequencies
6. df = no of categories-1

Question 21

how to conduct a 2 variable chi squared test

Answer 21

1. calculate the expected frequency -
   a. add up the values in column A (C1), and column B (C2)
   b. add up the values in row A (R1) and row b (R2)
   c. for each box, multiply the the column total*row total/total number of people in A and B
2. calculate (expected-observed)2 for each value
3. (expected-observed)2/expected for each value - sum all together
4. df = (no of rows -1)*(no of columns-1)

Question 22

how to conduct a mann-whitney U test

Answer 22

1. replace all scores with ranks - take ties into account
2. sum ranks for each group
3. calculate the smallest possible rank sum for each group by doing: n0.5(N+1)
4. rank sum - rank minimum for each group
5. U = the smaller value

Question 23

how to conduct a wilcoxon signed rank test

Answer 23

1. calculate difference in condition scores
2. if difference is a negative value, assign it a ‘-1’, is difference is positive, assign it ‘+1’, if there is no change, assign it ‘0’
3. diff score*sign value for each value
4. rank all these values, not including 0 and taking ties into account
5. create a positive and negative difference columns - for ranks that came from a positive difference value, put them in the positive difference column, for ranks that can from a negative difference value, put them in the negative difference column.
6. calculate the sum of each of these columns.
7. t = sum of the least occurring sign