Correlation coeff vs. Logistic Regression Coeff.

Vatsa

New Member
#1
From a bunch of data points which look like:
Code:
1	1	1
1	1	1
1	1	1
1	0	1
1	0	1
1	0	0
1	0	1
1	0	0
1	0	1
1	0	0
0	1	0
0	1	0
0	1	0
0	1	0
0	1	0
0	1	1
0	0	1
0	0	1
0	0	1
0	0	1
I get correlation coefficients as:
Code:
1	    -0.301511345	    0.204124145
-0.301511345	    1	    	    -0.287213479
0.204124145	    -0.287213479	    1
and after paired logistic regression the non-constant coefficients look like the following:
Code:
xx	                -1.258	                0.8473
-1.258	                xx	                -1.204
0.8473	                -1.204	                xx
In above, by regressing column 1 on column 2 I get non-constant coeff as -1.258 and after regression column 1 on column 3, I get 0.8473 and so on.

How do I interpret the above numbers?

Edit: I have a system which sends signal to 3 locations every 10 seconds. It gather information about they are active or not. I am trying to understand if there is any relation between those systems in terms of when they are alive.

I calculated correlation using the corr function in matlab.

Thanks
 
Last edited:

hlsmith

Less is more. Stay pure. Stay poor.
#2
You just need to look up how to interpret beta coefficients in logistic model for the second part. why did you use the correlation coefficients in the logistic model. Also the formatting in the latter two code boxes is skewed, making interpretations difficult.

What procedure did you use to get the correlation coefficients?

What is your purpose in doing this?