topic Re: probability and Correlation can we combine them in Statistical Procedures

probability and Correlation can we combine them

pearsoninst — Fri, 06 Nov 2015 13:33:20 GMT

Hi All,

Hope you are doing great.

I have a question i dont know if this is a right question to ask.

Is there a way to combine Correlation and Probability . My idea is that if something is correlated to something then what is the probability that will be exactly that much correlated.

For Example Y is depended Variable and X is Dependent .

Correlation = .70

What would be the probability that it will be .70 all the time ..is it a silly thought ?

Regards

Kanchan

Re: probability and Correlation can we combine them

slangan — Fri, 06 Nov 2015 13:45:22 GMT

This post might help: Understanding your data- the difference between correlation and conditional probability

http://versionone.vc/correlation-probability/

Re: probability and Correlation can we combine them

pearsoninst — Fri, 06 Nov 2015 14:23:23 GMT

Thanks this helped

Re: probability and Correlation can we combine them

Rick_SAS — Fri, 06 Nov 2015 15:54:14 GMT

I think you are asking about a parameter in the population and how it is "realized" in a sample taken from the population.

If you have two variables X and Y that are correlated with R=0.7, the question to ask is "if I draw a sample of N pairs of (x,y), what will the correlation be in this sample?" The field of statistics is essentially dedicated to this question and its generalizations. The basic answer is that if N is very large, then the sample correlation will be very close to 0.7. Statistics uses tools from mathematics to answer "how close." In general, the answer doesn't just depend on N, but also on the joint distribution of X and Y.