LISTSERV at the University of Georgia
Menubar Imagemap
Home Browse Manage Request Manuals Register
Previous messageNext messagePrevious in topicNext in topicPrevious by same authorNext by same authorPrevious page (July 2003)Back to main SPSSX-L pageJoin or leave SPSSX-L (or change settings)ReplyPost a new messageSearchProportional fontNon-proportional font
Date:   Thu, 31 Jul 2003 11:11:41 -0500
Reply-To:   Michael Granaas <mgranaas@usd.edu>
Sender:   "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:   Michael Granaas <mgranaas@usd.edu>
Subject:   converting several items into a single item
Content-Type:   text/plain; charset=us-ascii

For myself I would favor clearer subject lines. Right now I delete most messages from the list without reading. They don't interest me right now, but the small effort of deleting unread messages about date conversions is a small price to pay for the knowledge that should I ever need to know about date conversions the information will be out there somewhere.

On that theme--converting several items into a single item has come across my desk. The folks who entered the data had questions with several possible responses (e.g., your primary training is...). They then created a separate variable for each possible response. So if there were 8 possible responses they created 8 variables. These variables are coded as endorsed (1) or not-endorsed (system missing). As far as I can tell only one of the 8 items is endorsed for any individual and the remaining 7 are missing.

I've started recoding these into a single varible using a long series of IF statements:

IF v8a = 1 new8 = 1. If v8b = 1 new8 = 2. IF v8c = 1 new8 = 3.

and so on.

Is there a command that can accomplish the same thing?

Michael

**************************************************** Michael Granaas mgranaas@usd.edu Assoc. Prof. Phone: 605 677 5295 Dept. of Psychology FAX: 605 677 3195 University of South Dakota 414 E. Clark St. Vermillion, SD 57069 *****************************************************

----- Original Message ----- From: "Paparodopoulos, Nikos" <NPaparodopoulos@ing.gr> Date: Thursday, July 31, 2003 2:46 am Subject: Re: The purpose of this list. . .

> I agree with Nels that List is used sometimes in a not appropriate > mannerbut I would like to ask him to reconsider unsubscribing from > the List since > I believe that advanced SPSS users are key for the List. I agree > that List > sould not be misused for manual-trivial questions but we should > keep in mind > that progress in a field is triggered quite often from "simple" > questions.The interaction between SPSS users, irrespective of > their level (expert, > regular user, beginner), at the end of the day only positive > balance will > generate for everybody. > > Best regards > > Nikos Paparodopoulos > > -----Original Message----- > From: Nels Tomlinson [mailto:nels_tomlinson@labor.state.ak.us] > Sent: Wednesday, July 30, 2003 10:25 PM > To: SPSSX-L@LISTSERV.UGA.EDU > Subject: Re: The purpose of this list. . . > > > Guess I didn't make myself clear enough. The problem I see isn't > that the > questioners are ignorant; I was certainly ignorant the first few > weeks I was > using SPSS. The problem is that I see, over and over, people > asking us to > read the manual to them. Worse yet, some don't even want to hear > about the > manual: they want us to simply give them a solution. > > When I was teaching (economics and calculus), I found that the > students who > brought me homework and asked: ``How do I do this one?'' didn't > gain much > from my answers. The ones who'd tried the problems and asked: > ``Why doesn't > this way work?'' gained far more. The ones who never asked > questions were > even worse off, of course! I don't want to intimidate, or keep > anyone from > asking questions, but some preparation before posting will make > questionsmore rewarding for all. > > Too many of the questions seem to be on the order of ``do my > homework for > me, please''. A few have been so blatant that I found them a bit > offensive.There was one fellow (I think it was on this list) who > claimed to be a > consultant hired to do some project, and asked the list how to do > the work > he had contracted to do. He didn't offer to share his fee, either! > > I joined this list because I thought it would let me see a lot of > usefulquestions and answers, and let me learn from the mistakes of > others. What > I've found is that the signal-to-noise ratio is very bad, so that I'm > getting loads of emails and not very much useful information. > I've been > considering unsubscribing from the list because of the huge volume > of emails > from it which I delete unread. That's why I thought that Betty's > commentswere timely. > > I mentioned that the list's welcome message should contain > pointers to a FAQ > and some other resources. I also think that it would help if we > would all > point to specific pages in the manual (usually with some > clarification,helpful hints or additional information) when > answering newbies' questions > about SPSS. That would help them learn to find their own answers > for the > stuff that they should soon learn to see as simple. > > I'm sure that the people who are answering questions on this list are > generally busier than the ones who are trying to economize their > time, at > our expense, by not reading the manual and experimenting. We > don't want to > carry this as far as the OpenBSD mailing lists have, but I do > think it's > appropriate to economize our time (both active answerers and > lurkers time) > by gently, politely helping people to learn, and gently, politely, > not spoon > feeding them. > > The other problem I mentioned, of statistical ignorance, is a much > deeperand more widespread problem. The space shuttle Challenger > was launched on a > cold morning, and crashed, in part because the people (all experts > in their > fields) who analyzed o-ring failure data had no statistical > training. I > don't know of any implement-able solution to this problem, but I > am sure > that GUI stats packages exacerbate it. > > Nels > > -----Original Message----- > From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]On > Behalf Of > Michael Solorza > Sent: Wednesday, July 30, 2003 9:26 AM > To: SPSSX-L@LISTSERV.UGA.EDU > Subject: The purpose of this list. . . > > > The eternal debate that surrounds ANY listserv community. .. what is > appropriate to post and what isn't? I understand where the author > of the > following is coming from. . . Unfortunately, if taken the wrong > way, this > type of post paints the picture that this list is designed only > for the > "expert" users of SPSS and only for the "experts" in statistics. . > . And > the rest of us should just sit back, be quiet, and watch the > adults do > their business. . . > > Sorry, but that's what academic journals are for. Listservs like > this were > created for -- and should continue to serve -- the "average" user > that may > not be an elite user of SPSS (whatever that means). Sniffing our > noses at > people -- like me -- who use GUI a majority of the time vs. scripting > doesn't do any good. .. > > Elitist attitudes like this only continue to deepen the chasm that > existsbetween those people who truly are experts in their field > and those of us > who could stand to learn a thing or two by just being around folks > likethis. . . I've always had the humble opinion that knowledge > should be > shared, not hoarded by the few so they could lord over the "less" > deserving. . . My 2 cents. > > >Thanks for saying what needed to be said. Too many questions > here could > >have been solved by a glance at the manual. Too many more show > that GUI > >statistics packages provide the dangerously wrong illusion that > anyone can > >correctly analyze data, no matter how little they know. > > > > *************************** > Michael A. Solorza > Graduate Housing Analyst > UC Irvine > 500 Housing Administrative Services > Irvine, CA 92697-3250 > > (949) 824-2490 (office) > (949) 824- 4181 (fax) > **************************** >


Back to: Top of message | Previous page | Main SPSSX-L page