AW: Re: PSPP Regression with /noorigin

. I could not see any difference. I attach the output as pdfs. Thanks again! Best wishes, Beat multregorigin-spss.pdf Description: multregorigin-spss.pdf multregorigin.pdf Description: multregorigin.pdf ___ Pspp-users mailing list Pspp-users@gnu.org

PSPP Regression with /noorigin

/noorigin option in the Regression procedure! Beat - * Regression through the origin: Ratio model with PSPP. * Assign y and x. compute y = Balance. compute x = ATM. * Regression y=beta*x. COMPUTE xx = x * x. COMPUTE yx = y * x. COMPUTE one = 1. EXECUTE. AGGREGATE OUTFILE=* MODE=ADDVARIABLES

AW: PSPP-BUG: PSPP on Mac

priority would be Mann-Whitney U-test. I appreciate that PSPP actually does a QQ-Plot in the examine procedure in spite of the command "npplot": Outliers are better detected with QQ-plots than with PP-plots. Thanks a lot for the port! It saved a lot of sweat and tears! Regards,

Scatterplot y vs. x

x" means that x is on the ordinate. This is the present implementation in PSPP. Note that the PSPP command to get x on the abscissa is "graph /scatterplot= x with y." The title of the scatterplot will be "Scatterplot x vs.

Scatterplot

bright yellow circles that mark the points. Beat ___ Pspp-users mailing list Pspp-users@gnu.org https://lists.gnu.org/mailman/listinfo/pspp-users

AW: scatterplot

Concerning output I tried out a few of the offered versions and the (only) one that worked was html. In addition to the html file it produces png files of the graph output which then can be processed further. Beat Von: pspp-users-bounces+beat.hulliger=fhnw...@gnu.org [mailto:pspp-users

AW: AW: scatterplot

You must use the syntax, e.g.: graph /scatterplot=y with x. With my version the dots are yellow, a bad choice for most screens, but still: it works! Good luck! Beat -Ursprüngliche Nachricht- Von: pspp-users-bounces+beat.hulliger=fhnw...@gnu.org [mailto:pspp-users-bounces

AW: scatterplot

I just realised that the graph command is available with the syntax but not yet in the PSPPIRE. Scatterplot and histograms work! Sorry for overlooking this! Still barcharts seem to be missing. Beat -Ursprüngliche Nachricht- Von: pspp-users-bounces+beat.hulliger=fhnw...@gnu.org

scatterplot

-Anscombe plot (residuals versus predicted) to the regression? The plots do not need to be interactive (like GGRAPH) but just decent static plots. Thanks Beat ___ Pspp-users mailing list Pspp-users@gnu.org https://lists.gnu.org/mailman/listinfo/pspp