The Museum of HP Calculators

HP Forum Archive 20

[ Return to Index | Top of Index ]

WP 34S x-hat bug
Message #1 Posted by Nigel J Dowrick on 26 Feb 2012, 6:03 a.m.

I'm running build 2562.

I enter a set of (x,y) points satisfying y = 2x + 1 (for example).

I then enter 7, execute y-hat (yellow-shift 6) and obtain 15 (correct).

If I then enter 15, execute y-hat (from the STAT menu) I obtain 0.142857... i.e., the reciprocal of the correct answer.

This problem seems to occur with any set of data, not just the set above. I have not checked any regression other than linear.

I am astonished at the sheer volume of work that you guys have been putting into this project, especially recently. Thank you all - and take care of yourselves!

Nigel (UK)

      
Re: WP 34S x-hat bug
Message #2 Posted by Paul Dale on 26 Feb 2012, 6:13 a.m.,
in response to message #1 by Nigel J Dowrick

Yeah, a bug that crept in somewhere during the statistical rearrangements. Reciprocal is the fix.

Next build will have the fix included.

- Pauli


[ Return to Index | Top of Index ]

Go back to the main exhibit hall