Correlation Flashcards Preview

Biostatistics > Correlation > Flashcards

Flashcards in Correlation Deck (9)
Loading flashcards...
1
Q
  1. Measures the strength of association (linear relationship) between 2 variables
  2. Used in conjunction with scatterplots
A

Correlation

2
Q

value of the correlation coefficient

A

a. –1 indicates a very strong negative correlation
b. +1 indicates a very strong positive correlation
c. As the r goes towards 0, the relationship becomes weaker.
c. 0 indicates no correlation

3
Q

the variables move in the same direction. As 1 variable ↑, the other also ↑

A

Positive Correlation

4
Q

the variables move in inverse direction. As 1 variable ↑ the other ↓

A

Negative Correlation

5
Q

The most widely used correlation statistic

A

Pearson r correlation

6
Q

Assumptions for Pearson r

A

a. Normally distributed (assumes a normal curve or bell shape for both variables)
b. Linear (assumes a straight-line relationship between each of the two continuous variables)
c. Homoscedastic (assumes that data is equally distributed about the regression line)

7
Q
  1. A non-parametric test that measures the strength of dependence between 2 variables
  2. Used to measure the ordinal association between 2 measured quantities.
A

Kendall rank correlation:

8
Q

A non-parametric test that is used to measure the degree of association between two variables.

A

Spearman rank correlation

9
Q

Assumption for Spearman rank

A

a. Does not carry any assumptions about the distribution of the data
b. The variables are at least ordinal and the scores must be related