-
What is correlation?
correlation
measures the relationship between two variables
there are more than one type of correlation (depending on level of measurement)
-
Pearson product moment correlation
correlation
between interval/ratio variables
most widely used measure of correlation
has the most assumptions
-
Speraman rank correlation
correlation
between ordinal variables
-
Phi coefficient
correlation
between dichotomous variables
-
point-biserial correlation
correlation
between a dichotomous & interval/ration variables
ex: right or wrong of an exam item and total score
-
biserial correlation
correlation
between a dichotomous (w/ underlying continuum) & interval/ratio variables
ex:anxiety (low, high) & depression
-
polyserial correlation
correlation
between a polytomous (3 or more levels) (w/ underlying continuum) & interval/ratio variables
ex: anxiety (low, medium, high) & depression
-
tetrachoric correlation
correlation
betwee dichotomous variables (w/ underlying continuum) and depression
ex: anxiety (low, high) & depression (low, high)
-
polychoric correlation
correlation
between polytomous variable (w/ underlying continuum)
-
Pearson Product Moment Correlation Assumptions
correlation
No Outliers
Linearity
Normal Distribution
-
Pearson Assumptions: No Outliers
correlation
no extreme scores
- two types:
- -univariate
- -multivariate
-
Pearson Assumption: No Outliers - Univariate
correlation
an extreme score that is far away from the distribution of a variable
-only one variable
-
Pearson Assumption: No Outliers - Multivariate
correlation
an extreme score that is far away from the joint distribution of variables
it is possible for a case to be a multivariate outlier without bieng a univaritate outlier
-
Pearson Assumption: Linearity
correlation
variables should NOT show any non-linear pattern
-
Pearson Assumption: Normal Distribution
correlation
distribution of a variable should be univariate normal
distribution of variables should be multivariate normal
-
Range of Correlation
correlation
- all correlation range from -1 to +1
- a measure of correlation is unitless (or standardized).
- r = -1 perfect negative relationship
- r = +1 perfect positive relationship
- r = 0 no relationship
-
Scatterplot
correlation
when the correlation is r= +1, the scatterplot appears in a straight line
as the correlation approaches 0, the variability of scores increases
-
Covariance
correlation
measures of relationship between two variables in raw units (unstandardized correlation)
possible range is -infinity to +infinity
-
Types of Research Questions
correlation
1. Is there a significant relationship between x and y?
2. Is there a significant difference in the relationship of x and y between group 1 and group 2?
3. What is the (1-alpha)%CI of the correlation?
-
Sampling Distribution Correlation
correlation
- in not normal except when r=0 due to restricted range of the correlation
- -bound between -1 & +1
-
One-sample t-test for correlation
correlation
For testing H0: p = 0, Greek letter rho - population correltaion
df = N - 2
affected not only by N but also by r. Depends on the # of subjects & relationship
-
When to us r-critical
correlation
when testing more than one correlation becomes tedious
easier to compute r-critical value as long as there are same N
-
Fisher's r-to-z transformation
when to use
correlation
For testing a H0: p = p0
For difference in a correlation between groups
For confidence interval of a correlation
Convert r to z-score
|
|