Statistics- Correlations
- Created by: Jadepw
- Created on: 08-03-15 10:43
View mindmap
- Correlations
- Correlation Vs Causation
- Just because two variables are highly correlated does not mean that one has caused the other.
- CORRELATION DOES NOT IMPLY CAUSATION
- Responses
- Common response- Both X and Y respond to changes in some unobserved variable. •Ice cream sales and shark attacks both increase during summer.
- Causation-
Changes in X cause changes in Y. For example, football weekends cause heavier traffic
-
•Ice cream sales and the number of shark attacks on
swimmers are correlated.
- CORRELATION DOES NOT IMPLY CAUSATION
-
•Ice cream sales and the number of shark attacks on
swimmers are correlated.
- Confounding- The effect of X on Y is hopelessly mixed up with the effects of other explanatory variables
- Just because two variables are highly correlated does not mean that one has caused the other.
- Pearsons (r)
- This measures the strength of the linear relationship between two variables
- Pearsons r is always between -1 (\) and 1 (/) r=0
- when there seems to be no relationship between x and y to create a linear line, r=0
- explanation of correlations
- •It is called “product-moment” because it is calculated by multiplying the z-scores of two variables by one another to get their “product” and then calculating the mean value, which is called a “moment” of these products. –However, the Pearson’s r is rarely computed this way
- When should Pearsons r be used ?
- measures the relationship between any two variables on an interval or ratio scale
- What is a correlation ?
- •Scatterplots are made up of paired X and Y values.
- it expresses quantitatively the magnitude and direction of a relationship
- To describe the relationship with a straight line (linear correlation),
-
Spearman (rs)
-
A statistic
that shows the degree of relationship between 2 variables that are arranged in
rank order
- measured on an ordinal scale
-
A statistic
that shows the degree of relationship between 2 variables that are arranged in
rank order
-
Interpreting
Coefficient Magnitude
- We have discovered the different ways correlation can be expressed numerically.
- Often 1/-1 is described as a strong coreelation with the closer the number is to zero being described as a weaker correlation
- This is not the case as the context must be taken into consideration before this assumption is made.
- Correlation Vs Causation
Comments
No comments have yet been made