[Joachim Engel]

How can I compute a correlation coefficient with CODAP?

Joachim Engel

[Bill Finzer]

Hello Joachim,

One way is to define an attribute that has the formula

correlation(attribute1,attribute2)

as shown in the attached screenshot. Notice that by dragging the new attribute all the way to the left to promote it, you get a single value that is less confusing than if you left it in the “flat” part of the table.

Another way is to make a scatterplot of the two attributes and, with the ruler icon on its inspector, add a least squares regression line. On the line you will see the value of r-squared.

Bill Finzer

Attachments:

1. 

   correlation.png
   

[stephanie.machado@abcusd.us]

Preface: I am very new to CODAP.  I am trying to find ways to use this in my classroom since we have chromebooks and can’t use R or Minitab.

I found how to make an LSRL and find r, but is there a way to make other regression models (such as exponential)?

[Bill Finzer]

There are no built-in regression models in CODAP other than linear (yet). This is a consequence of no funded collaborating projects having yet requested such a feature.

Bill

[Author]

Posts