The following query raises the question: What is it that students learn from point and click dialogs?" Date: Fri, 03 Oct 2003 16:57:42 -0400 From: To: s-news at lists.biostat.wustl.edu Subject: Splus question Message-ID: <BAY9-F52Q7OoK42LpqI000238f3 at hotmail.com> I don't know if this is the right list to post this question. If not, please let me know where I should post this. I have a dataframe with 3 variables: ID, Y, Group Group is either 1, 2, 3. I am trying to run a t-test to compare the three groups on outcome Y. I know how to do this using the point and click dialogs. But can't get it to work on the command line. When I type: t.test(y, group) it just compares y and group as though they represent the two samples. I tried doing something with tapply(y, group) but don't know how that works. If someone knows, please email me. Thanks. ********************************************************** Cliff Lunneborg, Professor Emeritus, Statistics & Psychology, University of Washington, Seattle cliff at ms.washington.edu
On 04-Oct-03 Cliff Lunneborg wrote:> The following query raises the question: What is it that students learn > from point and click dialogs?"Two things, I think. 1. How not to think. 2. How to be unaware of possible error. Maybe others. Ted.> > Date: Fri, 03 Oct 2003 16:57:42 -0400 > From: > To: s-news at lists.biostat.wustl.edu > Subject: Splus question > Message-ID: <BAY9-F52Q7OoK42LpqI000238f3 at hotmail.com> > > I don't know if this is the right list to post this question. If not, > please let me know where I should post this. I have a dataframe with 3 > variables: ID, Y, Group Group is either 1, 2, 3. I am trying to run a > t-test to compare the three groups on outcome Y. I know how to do this > using the point and click dialogs. But can't get it to work on the > command line. When I type: t.test(y, group) it just compares y and > group > as though they represent the two samples. I tried doing something with > tapply(y, group) but don't know how that works. If someone knows, > please > email me. Thanks. > > ********************************************************** > Cliff Lunneborg, Professor Emeritus, Statistics & > Psychology, University of Washington, Seattle > cliff at ms.washington.edu > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://www.stat.math.ethz.ch/mailman/listinfo/r-help-------------------------------------------------------------------- E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk> Fax-to-email: +44 (0)870 167 1972 Date: 04-Oct-03 Time: 20:20:29 ------------------------------ XFMail ------------------------------
Hi , you wrote on 04.10.03 at 21:20:29> On 04-Oct-03 Cliff Lunneborg wrote: > > The following query raises the question: What is it that students learn > > from point and click dialogs?" > > Two things, I think. > > 1. How not to think. > 2. How to be unaware of possible error.Maybe they learn this at University, and not from point and click dialogs? Sorry, couldn't resist stefan (a professional student since years ;-)
Cliff Lunneborg wrote:> The following query raises the question: What is it that students learn > from point and click dialogs?"[long boring ramble - I'm sure you know how to find the delete key when it gets tedious ;) ] I think it's fair to say that they don't learn the software, or its internal structures/methods/etc at all (Mac users have always told me that this is the point; I'm not getting into that holy war). I will state one thing - the point and click interface *can* teach about the underlying software mechanisms, but it has to be a well thought-out interface. Example - I never used a computer that had a heirarchical filesystem until I went to university. I then had to learn two: IBM PC clones were used to teach us AutoCAD (ever seen AutoCAD run on an 8086 with 640K of RAM? It's not pretty ;). I also worked on the student newspaper, which was a Mac-only shop. The Macs came later; I was working in layout initially, back when layout really involved printouts, big cardboard sheets, and wax to stick the articles to the cardboard. I did not understand directory structure on the PCs at all. It never clicked. I simply "parroted" the commands I was taught to use, and managed to stay out of trouble. "Polly wanna .dwg file." Then I worked on the Macs. The display of folders made it clear to me, in about five seconds. I realised right away what I'd been missing, and flew back into the PC world with a bit more insight. As a result, I know that nice point-and-drool GUIs can educate about the underlying design and approach, but the design really must be considered very carefully. It's also important to take away the "crutch" from time to time, too (going back to PCs, in the above example). I've yet to see a GUI for a statistical software system that meets this criteria, and I can't imagine what one would look like (I'm an engineer, not a designer ;). I don't even know if it can be done. I'm sure anybody who understood heirarchical filesystems prior to GUIs would've thought similar things - that if one can't understand something so basic, there's really no simplifying or alternate explanation that'll work. Had that thinking prevailed, I might've been another engineer who doesn't know a thing about how computers actually work (there's no shortage, believe me). Just my $0.05 NZ (exchange rates, and all) Cheers Jason -- Indigo Industrial Controls Ltd. http://www.indigoindustrial.co.nz 64-21-343-545 jasont at indigoindustrial.co.nz
On Sat, 4 Oct 2003, Cliff Lunneborg wrote:> The following query raises the question: What is it that students learn > from point and click dialogs?"If the dialog constructs the same command line that you would type and shows you what it is, they can learn a lot. SPSS and Stata do this (IMO Stata does it better: SPSS tends to include unnecessary options, and doesn't default to showing you the command line). More importantly, the *point* of interface design is to prevent people from having to learn things that they don't need to know. The fact that a comparison of two means is called a t-test and a comparison of three means is called ANOVA would not ideally be on my list of the top fifty most important ideas in statistics. If the software and textbooks were better, this fact would be of purely historical interest even to statisticians. -thomas> > Date: Fri, 03 Oct 2003 16:57:42 -0400 > From: > To: s-news at lists.biostat.wustl.edu > Subject: Splus question > Message-ID: <BAY9-F52Q7OoK42LpqI000238f3 at hotmail.com> > > I don't know if this is the right list to post this question. If not, > please let me know where I should post this. I have a dataframe with 3 > variables: ID, Y, Group Group is either 1, 2, 3. I am trying to run a > t-test to compare the three groups on outcome Y. I know how to do this > using the point and click dialogs. But can't get it to work on the > command line. When I type: t.test(y, group) it just compares y and > group > as though they represent the two samples. I tried doing something with > tapply(y, group) but don't know how that works. If someone knows, please > email me. Thanks. > > ********************************************************** > Cliff Lunneborg, Professor Emeritus, Statistics & > Psychology, University of Washington, Seattle > cliff at ms.washington.edu > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://www.stat.math.ethz.ch/mailman/listinfo/r-help >Thomas Lumley Assoc. Professor, Biostatistics tlumley at u.washington.edu University of Washington, Seattle