P Value from Pearson r

**Chrisb59** · 06-15-2011, 11:14 AM

I am not sure if this is the correct place to ask this question, but forgive me for having a try if wrong.

If have a fairly extensive spreadsheet from which I calculate Correlation/Pearson data, giving me an "r" number.

There are tables on the internet for "P" numbers for comparison. I cannot find anywhere either the formula/equation for these tables, or anything like it within Excel 2007.

I will attach below a table from the internet. My aim is to have a formula/equation that I can put in a cell to give me the table answers. In other words if by example a formula for if N=5 and CI = .05 then 0.80 etc.

I hope I have explained myself.

Many Thanks

**shg** · 06-15-2011, 12:50 PM

I thought it was CHIINV, but I couldn't make that work.

I am certain that among Excel's statistical functions you can duplicate the table. If you have a reference for how the table was derived, it could be mapped to one of them.

**Chrisb59** · 06-16-2011, 02:25 AM

Thanks SHG.
The tables on the internet have no reference points or formulas that I can find.
Will have to keep trying.

**zbor** · 06-16-2011, 03:37 AM

Here, try this:

Biggest difference is in last column..

Rest is more or less within 5%, if that's OK for you.

**zbor** · 06-16-2011, 05:00 AM

However, there is slightly deviation for smaller Cl values... Looks like they become numb to the left..

it would be nice to see how result behave for Cl --> 0 so I could modificate formula.
But there is no enough data.

From the picture you can see Table values approaching to 1 (or some other value) while Formula values going to infinity.

Of course, if you don't need lower values then you can use this but if you need higher precision (espetially in the middle of the table) then data should be separated for N over or below 10.