Correlation

Question 0

Cross-product deviations

Answer 0

Multiply deviations of one variable from mean by corresponding deviations of 2nd variable. Total relationship btwn 2 variables.

Question 1

Covariance

Answer 1

How much variables vary together…measures average relationship btwn 2 variables. Not a standardised measure

Question 2

Negative covariance =

Answer 2

One variable deviates from the mean (increases) and the other (decreases)

Question 3

Positive covariance

Answer 3

Variables deviate from mean in same direction

Question 4

Covariance standardisation

Answer 4

Convert covariance into standard set of units. divide by SD for each variable

Question 5

Pearsons correlation coefficient r

Answer 5

Covariance divided by multiplied SDs. (Standardised covariance) Sampling distribution that’s not normally distributed.

Question 6

If you find a correlation coefficient less than -1 or more than +1 you can be sure that…

Answer 6

Something has gone hideously WRONG

Question 7

Coefficient of +1 means

Answer 7

Two variables are perfectly positively correlated. Both increase or decrease together

Question 8

Coefficient of -1 means

Answer 8

Perfect negative relationship. One decreases as one increases

Question 9

Coefficient of 0 means

Answer 9

No linear relationship. If one moves the other stays the same

Question 10

Coefficient of +1 means

Answer 10

Small effect

Question 11

+3 coefficient means

Answer 11

Medium effect

Question 12

+5 coefficient means

Answer 12

Large effect

Question 13

Bivariate correlation

Answer 13

Correlation btwn 2 variables

Question 14

Confidence intervals for r

Answer 14

Convert r to z scores (make sample distribution normal). Construct normal way.

Question 15

Correlation coefficients say nothing about…

Answer 15

Direction of causality

Question 16

Coefficient of determination

Answer 16

Correlation coefficient squared x 100 = %. Measure of amount of variability in one variable that is shared by the other.

Question 17

Spearman’s correlation coefficient

Answer 17

Non parametric stat based on ranked ordinal data. Useful to minimise effects if extreme scores or effects of violations of assumptions. 1st rank data then apply pearsons equation to ranks.

Question 18

Kendalls tau (non parametric)

Answer 18

Used with small data set with large number of tied ranks. More accurate than Spearman’s at correlation within the population

Question 19

Biserial and point-biserial correlations

Answer 19

Used when one of two variables has two categories (pregnant or not preg)

Question 20

Point-biserial correlation

Answer 20

One variable is discrete (pregnancy - are or aren’t)

Question 21

Biserial correlation

Answer 21

One variable is continuos (passing or failing an exam - on a continuum)

Question 22

Partial correlation

Answer 22

Correlation btwn two variables in which effects of other variables are held constant. Measures unique relationship btwn all 3 variables. One variable must be controlled for.

Question 23

Dichotomous variable

Answer 23

One that categories are discrete

Question 24

Partial correlations used for…

Answer 24

Looking at unique relationship btwn 2 variables when other variables are ruled out.

Question 25

Correlation relationships displayed using a

Answer 25

Scatter plot

Question 26

Scatter plots work best with

Answer 26

Interval or ratio measures

Question 27

Accuracy of correlation is contingent on several assumptions:

Answer 27

Random sampling (>30)
Linear relationships
Relationship homoscedastic
Restrict the range
Outliers need to be fixed

Question 28

Homoscedastic is

Answer 28

At any point along the way of any predictor variable the spread should be fairly constant

Question 29

Heteroscedasticity is

Answer 29

Opposite of homoscedastic - not constant placed

Question 30

Chi square measures

Answer 30

The expected frequencies under the null with the actual observed frequencies (assesses goodness of fit)