PDA

View Full Version : StatPages.org WebPage



rewyllys
December 11th, 2011, 12:12 AM
I just happened across a Webpage that struck me as useful enough to post about here. It's

www.statpages.org

whose subtitle is "Web Pages that Perform Statistical Calculations!"

If you use statistics, this is well worth taking a look at.

Ludd1te
April 6th, 2012, 05:03 PM
Thanks for the post! Here're some more stat apps and good resources online, etc.:

Typology of Analytical and Interpretational Errors in Quantitative and Qualitative Educational Research (http://cie.asu.edu/volume6/number2/) by A. J. Onwuegbuzie and L. G. Daniel “The purpose of this paper is to identify and to discuss major analytical and interpretational errors that occur regularly in quantitative and qualitative educational research.”
Research Methods Knowledge Base (http://www.socialresearchmethods.net/kb/index.php)
Formatting a Paper-Based Survey Questionnaire: Best Practices (http://www.pareonline.net/pdf/v10n12.pdf)
StatPages.org (http://statpages.org/) “The web pages listed here comprise a powerful, conveniently-accessible, multi-platform statistical software package. There are also links to online statistics books, tutorials, downloadable software, and related resources.” Highlights of StatPages.org are:

A large list and description of free and nearly free statistical software (http://statpages.org/javasta2.html)
Statistical Decision Tree (http://www.microsiris.com/Statistical%20Decision%20Tree/)

Cautionary notes associated with the decision tree (http://www.microsiris.com/Statistical%20Decision%20Tree/cautionary_comments.htm)




Selecting Statistics (http://www.socialresearchmethods.net/selstat/ssstart.htm)
PsychNet UK List of Online Statistical Calculators (http://ww.psychnet-uk.com/x_new_site/experimental_design/online_calculators.html) A nice selection of online stat calculators, including some that conduct such advanced tests as multivariate regression.
Daniel Soper’s Statistical Calculators (http://www.danielsoper.com/statcalc/)
David Walker’s Statistical Calculators (http://www.cedu.niu.edu/%7Ewalker/calculators/)
Random Number Generator (http://www.randomizer.org/)
Lee Becker’s Effect Size Calculator (http://www.uccs.edu/%7Efaculty/lbecker/)
Creative Research Systems’ Sample Size Calculator (http://www.researchinfo.com/docs/calculators/samplesize.cfm)

Definitions of confidence interval and confidence level (http://www.surveysystem.com/sscalc.htm#one)


Harshbarger’s (1977) Introductory Statistics: A Decision Map (http://epm.sagepub.com/cgi/reprint/33/2/516)

SeijiSensei
April 6th, 2012, 05:11 PM
The two most useful packages for me have been:

gretl (http://gretl.sourceforge.net/) - a full-featured econometrics and time-series analysis package
PSPP (http://www.gnu.org/software/pspp/) - a clone of SPSS

Both are GPL and available in the Ubuntu repositories.

Ludd1te
April 6th, 2012, 08:21 PM
I have PSPP installed, but I haven't used it much. I'm mostly trying to get good at R instead. (But, I have and use SPSS at work, so do most of my stats there).

Anyway, PSPP does look good, I just haven't taken the time to learn that over R.

(BTW, for R, I mostly use RKward (http://sourceforge.net/apps/mediawiki/rkward/index.php?title=Main_Page), but supplement my GUI use with R Commander (http://socserv.mcmaster.ca/jfox/Misc/Rcmdr/), too. I feel RKward has a better output and workspace interface, but R Commander has easier access to more analysis packages--at least at my skill level).

What do you like especially about PSPP?

Cheers

SeijiSensei
April 6th, 2012, 09:40 PM
I needed to run a bunch of crosstabs and some regressions from survey data. The provider, SurveyMonkey, offers the data as an SPSS system file, so PSPP was the obvious choice.

I used to teach SPSS many years ago as part of my classes in statistics for political scientists.

PGScooter
April 7th, 2012, 08:17 AM
(BTW, for R, I mostly use RKward (http://sourceforge.net/apps/mediawiki/rkward/index.php?title=Main_Page), but supplement my GUI use with R Commander (http://socserv.mcmaster.ca/jfox/Misc/Rcmdr/), too. I feel RKward has a better output and workspace interface, but R Commander has easier access to more analysis packages--at least at my skill level).


Cheers

If you haven't tried Rstudio, you gotta give it a shot! It's a dream come true. You might not have heard about it because it's only a year or so old. But it's already very mature and I think it will be the choice of most users that don't use the prompt directly. www.rstudio.org

Ludd1te
April 7th, 2012, 07:44 PM
Thanks, PGScooter (http://ubuntuforums.org/member.php?u=253148). :p I just downloaded it and will play around with it. (I have some stats to do anyway, so why not have fun learning a new and recommended interface while doing them.)

R is great--nearly as powerful as SAS--but I have to admit my own weakness in benefiting from a friendly GUI interface.

PGScooter
April 7th, 2012, 08:12 PM
Thanks, PGScooter (http://ubuntuforums.org/member.php?u=253148). :p I just downloaded it and will play around with it. (I have some stats to do anyway, so why not have fun learning a new and recommended interface while doing them.)

R is great--nearly as powerful as SAS--but I have to admit my own weakness in benefiting from a friendly GUI interface.

Great, let us know what you think!

rewyllys
April 8th, 2012, 07:24 PM
If you haven't tried Rstudio, you gotta give it a shot! It's a dream come true. You might not have heard about it because it's only a year or so old. But it's already very mature and I think it will be the choice of most users that don't use the prompt directly. www.rstudio.org
Many thanks, PGScooter.

RStudio looks very interesting. And, though my trials of it have been only brief so far, at least it has NOT (yet) frozen on certain tasks, unlike both RCmdr and RKWard on the Linux Mint 11 installation on my desktop.

PGScooter
April 9th, 2012, 01:02 AM
Many thanks, PBScooter.

RStudio looks very interesting. And, though my trials of it have been only brief so far, at least it has NOT (yet) frozen on certain tasks, unlike both RCmdr and RKWard on the Linux Mint 11 installation on my desktop.

Good to hear! The best thing is that their programmers seem very interested in feedback.