Beefy Boxes and Bandwidth Generously Provided by pair Networks
Welcome to the Monastery
 
PerlMonks  

Re: Statistics::LineFit versus gnuplot, results differ

by sn1987a (Chaplain)
on Apr 25, 2014 at 19:04 UTC ( #1083838=note: print w/replies, xml ) Need Help??


in reply to Statistics::LineFit versus gnuplot, results differ

Using LibreOffice to graph the data as reported by your perl program and fit a line, I get the same result as the perl module.

I don't know enough Gnuplot to know what is going on there, but notice that the Asymptotic Standard Error is many times the values of the parameters. Event the perl data has a correlation coefficient of 0.02

You also have an error in the time conversion in the perl code.
return timelocal( '59', '59', '23', $d, $m, $y );
should be
return timelocal( '59', '59', '23', $d, $m-1, $y );.
This will not effect the slope, just the y-intercept.

Log In?
Username:
Password:

What's my password?
Create A New User
Node Status?
node history
Node Type: note [id://1083838]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this? | Other CB clients
Other Users?
Others taking refuge in the Monastery: (4)
As of 2019-04-22 00:10 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?
    I am most likely to install a new module from CPAN if:
















    Results (111 votes). Check out past polls.

    Notices?