Regression Statistics are returned as Rounded to 1 vs. several dec
 

Hello,

I am trying to apply linear regression analysis to test the "effectiveness"
of swap transactions (but that's beside the point).

I have 2 columns of %'s as my x and y data, and I am trying to see if they
correlate. So I am interested in the R Square statistic. For some reason,
the resulting statistics are all rounded to 1 (hard-entered w/out decimals),
instead of formatted several decimal places (see below).
Regression Statistics
Multiple R 1
R Square 1
Adjusted R Square 1
Standard Error 2.40655E-18
Observations 20

Anyone know why or how I can adjust the resulting format?

Thanks in advance

Your standard error is minuscule, so you probably have a nearly perfect
fit that would require more than Excel's documented limit of 15 digits
to show a difference from 1 in R-square.

Jerry

DWright wrote:

Hello,

I am trying to apply linear regression analysis to test the "effectiveness"
of swap transactions (but that's beside the point).

I have 2 columns of %'s as my x and y data, and I am trying to see if they
correlate. So I am interested in the R Square statistic. For some reason,
the resulting statistics are all rounded to 1 (hard-entered w/out decimals),
instead of formatted several decimal places (see below).
Regression Statistics
Multiple R 1
R Square 1
Adjusted R Square 1
Standard Error 2.40655E-18
Observations 20

Anyone know why or how I can adjust the resulting format?

Thanks in advance

Yes, I had wondered if it was because the data was very closely correlated.
Thanks for confirming.

Much appreciated!

"Jerry W. Lewis" wrote:

Your standard error is minuscule, so you probably have a nearly perfect
fit that would require more than Excel's documented limit of 15 digits
to show a difference from 1 in R-square.

Jerry

DWright wrote:

Hello,

I am trying to apply linear regression analysis to test the "effectiveness"
of swap transactions (but that's beside the point).

I have 2 columns of %'s as my x and y data, and I am trying to see if they
correlate. So I am interested in the R Square statistic. For some reason,
the resulting statistics are all rounded to 1 (hard-entered w/out decimals),
instead of formatted several decimal places (see below).
Regression Statistics
Multiple R 1
R Square 1
Adjusted R Square 1
Standard Error 2.40655E-18
Observations 20

Anyone know why or how I can adjust the resulting format?

Thanks in advance