Analysis Methods In Sport And Exercise Psychology Flashcards
Correlation
Come from Co-relation
Co = two variables
Relation = how much they relate
Looking at how of the variance is shared with second variable - looking at the overlaps which gives the shares variance
Correlation Coefficient
If you have a lot of variance shared = large correlation coefficient
If you have just a little of shared variance = small correlation coefficient
+ +
- -
+ -
- +
+ + = + (positive relationship)
- - = +
+ - = - (negative relationship)
Direction of correction
Positive or negative
Positive relationship leads to positive correlation coefficient
Negative relationship leads to negative correlation coefficient
Standardise covariance
Z-score - how to standardise any variable eg to see if they are an outlier or is it close to the mean _ X-X —— SD
Co
Correlation standardised
Covariance
——————
Standard deviation
Correlation coefficient r
A measure of overlap between two variables
r varies from -1 to +1
0 = no relationship
+1 = perfect relationship (the stronger the correlation)
Positive / negative
The bigger the value is the larger the amount of shared variance
Asssumption for Pearson’s correlation
Two variables should be measured at the interval or ratio level
Needs to be a linear relationship between the two variables (check through scatterplot)
There should be no significant outliers
Data is normally distributed
Show that data has homoscedasticity (equal value of X for every value of Y
Example of a null hypothesis
P = 0; the population coefficient is equal to zero. There is no relationship between Variable X and Variable Y
Alternative hypothesis
P ≠ 0; the population correlation coefficient is not equal to zero. There is a relationship between Variable X and Variable Y