Dennis Robert Gorrie <GORRIEDE@max.cc.uregina.ca> (06/25/91)
paul@ersys.edmonton.ab.ca (Paul Wolodko) writes: > > I'm looking for a package/software a friend can use on the > Amiga which allows her to do phys. lab plots. She's trying to cut > down the time she's spending on those graphs ... she isn't > looking for any high level stat. functions, just figures the best > fit curve ... max/min/best fit linear lines too I suppose; but > nothing viciously technical. I don't see anything really tough, > except the actual stats. stuff, but there is probably something > out there already (he says hopefully); but I don't really have > the time to figure it out (life is complex). Anyway, any suggestions > or know of any packages? (Thanks) > > Paul Wolodko paul@ersys.edmonton.ab.ca > Edmonton Remote Systems: Serving Northern Alberta since 1982 I was looking for a similar program. I tried Math-Amation, but I was not impressed. So I use a spread sheet program, Analyse. You could use any spreadsheet program. You just have to type in your data, and know the formulas for the Least Squares approximation, (Best Fit Line) and Pearson's product moment r. Look them up in any stats book. If you use a spreadsheet, then you can apply the formula to your all your data, get the best fit points, and then plot them. Plus, a good spreadsheet program will be able to import/export data in LOTUS format for using your same data on an pc-clone. P.S. Physics data is not always linear, so you have to apply Log or Ln to your data to make it linear. When you finally calculate the best fit equation of the Log(y) vs x graph, or Ln (y) vs x, you then have to integrate it to get the equation of your original non-linear graph. +-----------------------------------------------------------------------+ |Dennis Gorrie 'Chain-Saw Tag... | |gorriede@max.cc.uregina.ca Try It, You'll Like It!'| |gorrie@meena.cc.uregina.ca | +-----------------------------------------------------------------------+
GORRIEDE@max.cc.uregina.ca (Dennis Robert Gorrie) (06/25/91)
As someone noticed, Analyse does do a poor job of graphs, in my opinion. They look clunky, low-res, and you can't make very nice titles or legends. But, my original post, I just wanted to show that a person can do good regression analysis without having to spend the bucks on a special program for it, assuming they already have a spreadsheet program of some kind. How about using shareware programs to do the job? Perhaps Analyticalc to to find the best fit line and data points. Then use one of the shareware plotting programs for the output. It might produce better output than the commercial spreadsheet programs. Maybe I will try it myself. Right now, I use IntroCAD, which does amazing printing on a 9-pin dot matrix. Which brings me to this question: Does anyone know if IntroCAD PLUS is much better than the original IntroCAD? +-----------------------------------------------------------------------+ |Dennis Gorrie 'Chain-Saw Tag... | |gorriede@max.cc.uregina.ca Try It, You'll Like It!'| |gorrie@meena.cc.uregina.ca | +-----------------------------------------------------------------------+
rg20+@andrew.cmu.edu (Rick Francis Golembiewski) (06/26/91)
paul@ersys.edmonton.ab.ca (Paul Wolodko) writes: > > I'm looking for a package/software a friend can use on the > Amiga which allows her to do phys. lab plots. She's trying to cut > down the time she's spending on those graphs ... she isn't > looking for any high level stat. functions, just figures the best > fit curve ... max/min/best fit linear lines too I suppose; but > nothing viciously technical. I don't see anything really tough, Try out psgraph, it is a graphing program with a spread sheet like interface it has polynomial least squares fitting (it also has coulumn math built in that does error propagation, including ln so that you can do exponential fitting by transforming the data so that it is linear). It is available via anonymous ftp from drycas.club.cc.cmu.edu (128.2.232.11) it should be posted to binaries.amiga RSN. // Rick Golembiewski rg20+@andrew.cmu.edu \\ \\ #include stddisclaimer.h // \\ "I never respected a man who could spell" // \\ -M. Twain //
baxter_a@wehi.dn.mu.oz (06/26/91)
In article <57096@nigel.ee.udel.edu>, GORRIEDE@max.cc.uregina.ca (Dennis Robert Gorrie) writes: > > I was looking for a similar program. I tried Math-Amation, but > I was not impressed. So I use a spread sheet program, Analyse. > You could use any spreadsheet program. You just have to type > in your data, and know the formulas for the Least Squares > approximation, (Best Fit Line) and Pearson's product moment r. > > Look them up in any stats book. If you use a spreadsheet, then you > can apply the formula to your all your data, get the best fit points, > and then plot them. Plus, a good spreadsheet program will > be able to import/export data in LOTUS format for using your same > data on an pc-clone. > > P.S. Physics data is not always linear, so you have to apply > Log or Ln to your data to make it linear. When you finally calculate > the best fit equation of the Log(y) vs x graph, or Ln (y) vs x, you > then have to integrate it to get the equation of your original > non-linear graph. Multiplot does all this automatically. I am currently looking at improving the curve fitting function. The latest version uses an iterative method. Regards Alan
clcp16@vaxa.strath.ac.uk (Stewart C. Russell) (06/26/91)
In article <57096@nigel.ee.udel.edu>, GORRIEDE@max.cc.uregina.ca (Dennis Robert Gorrie) writes: > paul@ersys.edmonton.ab.ca (Paul Wolodko) writes: >> >> I'm looking for a package/software a friend can use on the >> Amiga which allows her to do phys. lab plots. She's trying to cut >> down the time she's spending on those graphs ... she isn't >> looking for any high level stat. functions, just figures the best >> fit curve ... max/min/best fit linear lines too I suppose; but >> nothing viciously technical. I don't see anything really tough, >> except the actual stats. stuff, but there is probably something >> out there already (he says hopefully); but I don't really have >> the time to figure it out (life is complex). Anyway, any suggestions >> or know of any packages? (Thanks) >> Sounds like a job for MultiPlot XLNd (or better). It can do polynomial fits up to order 5, linear fitting, and any flavour of log scale you want. It'll output to any device known to humankind; plotter, Preferences printer (via the wonderful PLT: plotter emulator), PostScript, various CAD formats. Wonderful stuff; and its file format is plain ascii. Fish Disk 467, methinks, or an FTP site somewhere; dunno which. Stewart C. Russell (this account is pretty near closed, so no replies please) -- |Stewart C. Russell | University of Strathclyde, Glasgow, Scotland, UK| |clcp16@vaxa.strath.ac.uk | (opinions my own, not theirs) | | Also known as scruss@cix.compulink.co.uk | | "Beauty is truth, truth beauty" - Keats | | "You lying get!" - The Living Carpets, Vic Reeves Big Night Out |