Home : Correlation Calculations for Variable
Q14229 - INFO: Correlation Calculations for Variable

The Correlation Calculations form shows what variables correlate to a variable.   It provides four different line/curve fits to the data and calculates the Coefficient of Correlation (Coeff of Cor) for each. The correlation coefficients of correlation are a measurement of the goodness of fit. The higher the Coefficient, the better the fit (1.0 being a perfect fit). The list is sorted by the Linear Regression Coefficient of Correlation by default.

The Corrleaiton Calculations form is available from the following Graph Pac Forms:

Correlation Graph - Used to suggest an independent variable:

Multiple Linear Regression Graph - Used to suggest independent variables:

Variable Analysis Graphs - Used to suggest a variable to compare to:

 

Example: Find variables that correlate to Effluent BOD.

1. Go to Graph Pac, Variable Analysis Graphs

2. Choose Effluent BOD as the Variable to Analyze.

3. Click the button. This will display the Correlation Calculations for Effluent BOD:

In this example, we find that the Eff BOD Duplicate correlates to Eff BOD the best. However, while this makes perfect sense statistically, this give us no insight into what affects our Eff BOD. However, MLSS is second on the list and something we can control.


4. Click on the MLSS row, the Selected Independent Variable will be updated and click OK.  MLSS will be chosen as the variable to compare Effluent BOD to.


Related Articles
No Related Articles Available.

Article Attachments
No Attachments Available.

Related External Links
No Related Links Available.
Help us improve this article...
What did you think of this article?

poor 
1
2
3
4
5
6
7
8
9
10

 excellent
Tell us why you rated the content this way. (optional)
 
Approved Comments...
No user comments available for this article.
Created on 6/23/2014 4:49 PM.
Last Modified on 6/23/2014 4:58 PM.
Last Modified by Scott Dorner.
Article has been viewed 2135 times.
Rated 0 out of 10 based on 0 votes.
Print Article
Email Article