SPSSX-L archives -- July 2007 (#412)

Date:	Thu, 26 Jul 2007 15:10:43 -0500
Reply-To:	Melissa Ives <mives@chestnut.org>
Sender:	"SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:	Melissa Ives <mives@chestnut.org>
Subject:	Re: SPSSX-L Digest - 24 Jul 2007 to 25 Jul 2007 (#2007-207)
Comments:	To: "Chelminski, Iwona" <IChelminski@lifespan.org>
Content-Type:	text/plain; charset="iso-8859-1"

Hmm, I would think about looking into Version 16 which is about to come out in a few months and promises to be less 'quirky' than 15.

Melissa

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Chelminski, Iwona Sent: Thursday, July 26, 2007 10:52 AM To: SPSSX-L@LISTSERV.UGA.EDU Subject: Re: [SPSSX-L] SPSSX-L Digest - 24 Jul 2007 to 25 Jul 2007 (#2007-207)

Hi Group, I'm thinking about buying the 15 version. Is it any good? They want over $1,500 for it so i want to make sure that it's not a piece of crap like the version 10 was. Any comments? Thanks in advance

Iwona

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU]On Behalf Of Automatic digest processor Sent: Thursday, July 26, 2007 12:01 AM To: Recipients of SPSSX-L digests Subject: SPSSX-L Digest - 24 Jul 2007 to 25 Jul 2007 (#2007-207)

There are 24 messages totalling 1629 lines in this issue.

Topics of the day:

1. SPSS 15 loses reg. with Vista 2. ANNOUNCE: SPSS USERS MEETING (INC BOOKING FORM) REMINDER 3. data dictionary (2) 4. include (2) 5. stepwise regression how to include all cases despite missing data (3) 6. Random date generator (6) 7. stepwise regression how to include all cases despite missing data 8. Old Sunflower Option (2) 9. AW: Re: Old Sunflower Option 10. Can someone please tell me how to unsubscribe from this forum, thanks in advance 11. Can someone please tell me how to unsubscribe 12. RENAME LOOP? 13. Aggregating with missing data 14. Matching files on one of three possible ID's

----------------------------------------------------------------------

Date: Wed, 25 Jul 2007 04:36:06 -0400 From: Nico Munting <nico.munting@CAPGEMINI.COM> Subject: Re: SPSS 15 loses reg. with Vista

I hope you have solved this problem by now, but if you haven't you might try the following.

I do not have experience with SPSS on Vista, but my guess is that SPSS is trying to store the registration information in C:\Program Files\ or the equivalent in your situation. However, because in Vista you are not running all programs as Administrator, SPSS does not have write-access to the Program Files directory.

To give SPSS write-access to the Program Files directory right click on the shortcut you are using to launch SPSS and select "Run As...". Choose an account with Administrative privileges and you might be prompted for a password or a confirmation. After this SPSS should start normally. Now complete the registration, and since SPSS was started in Administrative mode, it should be able to write the registration information to the Program Files directory.

If all is well you should be able to start SPSS normally from this point on, and hopefully it remembers your registration.

Good luck,

Nico

On Wed, 4 Jul 2007 06:33:47 +0100, David Hitchin <d.h.hitchin@sussex.ac.uk> wrote:

>I have installed SPSS 15.0, including the patch to take it to 15.0.1 and >the additional patch to cope with Vista problems. The new licence >procedure works, and SPSS functions as expected. > >At some point, either when SPSS is stopped or the machine is turned off, >the registration is lost; next time SPSS is started it has to be >re-registered. > >Any ideas? > >David Hitchin

------------------------------

Date: Wed, 25 Jul 2007 10:14:57 +0100 From: Peter Watson <peter.watson@mrc-cbu.cam.ac.uk> Subject: ANNOUNCE: SPSS USERS MEETING (INC BOOKING FORM) REMINDER

This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools.

---559023410-1804928587-1185354897=:4092 Content-Type: TEXT/PLAIN; charset=X-UNKNOWN; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE

A reminder of the ASSESS meeting in November:

ASSESS: SPSS USERS' GROUP 21st ANNUAL MEETING FRIDAY 9th NOVEMBER 2007 ALCUIN RESEARCH RESOURCE CENTRE AUDITORIUM=20 UNIVERSITY OF YORK, YORK

ASSESS is an independent user group for SPSS, a computer package for analys= ing=20 and presenting data. It is run by users, for users and is completely indepe= ndent of manufacturers of the software. The meeting is open to all users of SPS= S and=20 to anyone interested in SPSS.

Come along to: * hear SPSS users talk about applications,the problems and solutions * hear the latest news from SPSS UK staff about product developments, and put your questions to them * question a panel of experts about particular problems * exchange ideas with other SPSS users * plan for an even better user group.

The venue is the Alcuin Research Resource Centre (ARRC) on York University= =20 campus located in Heslington, 2 miles to the south-east of the city centre.= =20 It takes 10-15 minutes in a taxi from the railway station. The Number 4 bus= =20 runs regularly to the University from York railway station (see=20 http://www.yorkshiretravel.net/). Parking at the University is very difficu= lt.=20 Location details are at http://www.york.ac.uk/np/maps/. Accommodation is=20 bookable via tourist information on (01904) 621756 or (01904) 554455.

THE PROVISIONAL PROGRAMME**

* Welcome and introduction to meeting

* SPSS company and product news; SPSS software demonstrations

* How and why to document data for long-term storage, and what's special=20 about GI (geographical) data? by Allan Reese, CEFAS

* Making the world a better place with SPSS: analysing & predicting charity donor behaviour using SPSS Base by John Sauve-Rodd, Datapreneurs

* Applications of OMS by Gilbert MacKenzie, University of Limerick

* Multivariate aspects of testing the savannah hypothesis of shopping=20 by Charles Dennis, Brunel University

* Mousing with SPSS: useful point and click=20 by Frances Provan, University of Edinburgh

* Users" Question Time and Clinic

* Annual General Meeting of ASSESS.

Registration and coffee will start at 10am. Papers and other events will ru= n=20 from 10.30am to about 5.00pm. Morning coffee, lunch and afternoon tea are= =20 included in the registration fee. A timetable will be e-mailed to delegates in advance of the meeting.

______________________ ** The titles and order of events are subject to amendment. ---------------------------------------------------------------------------= -----

BOOKING FORM ASSESS : SPSS USERS' GROUP Friday 9th November 2007, ARRC auditorium, University of York

Important:

Bookings will not be treated as firm until a cheque or official (company) o= rder, payable to ASSESS, is received. Payment possible by BACS. Details on reques= t.

Name: ______________________________ Tel: ____________________ Email: ______________________________ Fax: ____________________

Job Title: ___________________________________ Organization: ___________________________________ Address: ___________________________________________________ ___________________________________________________ _______________________ Postcode _______________

Strike out the sections which do not apply to you, or otherwise amend as appropriate:

INDIVIDUAL BOOKING. Please reserve a place for me, at a cost of 65 GBP.

CORPORATE BOOKING. (Enter the appropriate amounts)

Please reserve ______ places, at a cost of =A3_____ (65 GBP, for the first = person,=20 and 55 GBP for each subsequent person) .

Names of attendees : 1. _______________________________________ (for badges) 2. _______________________________________ 3. _______________________________________ 4. _______________________________________ 5. _______________________________________

STUDENT (POST-GRADUATE) BOOKING. (Enclose photocopied evidence of status for 2007-2008 academic year). Please reserve for me one of the student places at a cost of 40 GBP.

Specify vegetarian or other dietary requirements, if any: ________________________________________________________________

Cheque or official order enclosed for _______GBP

For official orders please also give here the number and address for invoic= ing: ________________________________________________________________ ________________________________________________________________ ________________________________________________________________

(Please indicate if you require a receipt of payment)

Return completed forms to: Peter Watson, MRC Cognition and Brain Sciences Unit, 15 Chaucer Road, Cambridge, CB2 7EF.

Telephone enquiries about bookings: 01223 355294 x801 (has an answerphone)

E-mail enquiries about bookings: =09peter.watson@mrc-cbu.cam.ac.uk (important: put "ASSESS" in the Subject field)

---559023410-1804928587-1185354897=:4092--

------------------------------

Date: Wed, 25 Jul 2007 03:41:21 -0700 From: Albert-jan Roskam <fomcl@yahoo.com> Subject: Re: data dictionary

DISPLAY VARIABLES / VARIABLES = myvar1 myvar2. DISPLAY DICTIONARY / VARIABLES = myvar1 myvar2.

Will display only the variables of interest.

--- "Parry, James" <jparry@spss.com> wrote:

> Hi Ken, > > Try File . . . Display Data File Information . . . > Working File (if you have the data open). I believe > the only way to limit the variables displayed in > this command is to physically drop the variables. > > -HTH > > -----Original Message----- > From: SPSSX(r) Discussion > [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Ken > Wood > Sent: Tuesday, July 24, 2007 1:13 PM > To: SPSSX-L@LISTSERV.UGA.EDU > Subject: data dictionary > > How does one save (in order to print) the > information about all the variables in a given > dataset? That is, the information (or selected > information) that one sees in the Variable View? >

Cheers! Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Did you know that 87.166253% of all statistics claim a precision of results that is not justified by the method employed? [HELMUT RICHTER] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

____________________________________________________________________________________ Get the Yahoo! toolbar and be alerted to new email wherever you're surfing. http://new.toolbar.yahoo.com/toolbar/features/mail/index.php

------------------------------

Date: Wed, 25 Jul 2007 12:48:59 +0200 From: Maddalena Agonigi <m.agonigi@sns.it> Subject: include

I am new to SPSS programming and so any help will be deeply appreciated.

I use INSERT in a Script

INSERT FILE=3D'C:\Test.sps' SYNTAX=3DBATCH Error=3DStop CD=3DYES.

but spss give me following message

INSERT <qu=EC>FILE=3D'C:\Test.sps (0) Istruzione non valida.

Thank you all

------------------------------

Date: Wed, 25 Jul 2007 05:55:45 -0700 From: Albert-jan Roskam <fomcl@yahoo.com> Subject: Re: include

Hi,

--What SPSS version are you using? INSERT has been implemented relatively recently (spss v13+ (?)). Did you try using INCLUDE already? --Are you absolutely sure the sps file is where you say it is?

Albert-Jan

--- Maddalena Agonigi <m.agonigi@sns.it> wrote:

> I am new to SPSS programming and so any help will be > deeply appreciated. > > I use INSERT in a Script > > INSERT FILE='C:\Test.sps' > SYNTAX=BATCH Error=Stop CD=YES. > > but spss give me following message > > INSERT <qu�>FILE='C:\Test.sps > (0) Istruzione non valida. > > Thank you all >

Cheers! Albert-Jan

------------------------------

Date: Wed, 25 Jul 2007 09:49:25 -0400 From: Ken Wood <kwood@kmrrec.org> Subject: Re: data dictionary

Thank you for the many suggestions. For those interested, the suggestions I received are below.

you can go to File Menu and choose the option display information about the current working file or an external file. You will have an output that you can save in .spo format or even copy to word, excel or any other software.

Do Display Dictionary, then go to the Output, select the information displayed, and either print from there, or export to either RTF or Excel formats. Recent versions of SPSS provide information on variable names and structure separately from Value labels, which is a bit annoying.

try this command in syntax:

display dictionary.

DISPLAY VARIABLES / VARIABLES = myvar1 myvar2. DISPLAY DICTIONARY / VARIABLES = myvar1 myvar2.

Will display only the variables of interest.

*OMS * /SELECT TABLES * /EXCEPTIF LABELS =['Notes'] * /DESTINATION * Format = Text * OUTFILE = "dictionary.txt". *DISPLAY DICTIONARY. *OMSEND.

> > Try File . . . Display Data File Information . . . > Working File (if you have the data open). I believe > the only way to limit the variables displayed in > this command is to physically drop the variables. > > > > -----Original Message----- > From: SPSSX(r) Discussion > [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Ken > Wood > Sent: Tuesday, July 24, 2007 1:13 PM > To: SPSSX-L@LISTSERV.UGA.EDU > Subject: data dictionary > > How does one save (in order to print) the > information about all the variables in a given > dataset? That is, the information (or selected > information) that one sees in the Variable View? >

Ken Wood, PhD Research Scientist KMRREC West Orange, NJ 973-243-6871

------------------------------

Date: Wed, 25 Jul 2007 21:58:49 +0800 From: Hunna Watson <H.Watson@curtin.edu.au> Subject: stepwise regression how to include all cases despite missing data

Hi all,=20 =20 I'm running a stepwise regression of organizational practices on = construction projects that predict project cost growth. I have data for = 115 projects, yet some organizational practices were not applicable on = some projects (in a random fashion). the missing data is obviously = purposeful and not due to not filling in questionnaires etc. spss = automatically excludes cases with any missing values, or wants to = substitute a value, so I end up with a regression being carried out on = 10 projects, obviously not useful. Any suggestions for syntax to include = all cases or suggestions to rectify this problem? =20 Thanks in advance,=20 Hunna Watson

------------------------------

Date: Wed, 25 Jul 2007 09:12:37 -0500 From: Melissa Ives <mives@chestnut.org> Subject: Re: Random date generator

During the assessment process, interviewers are given these instructions for estimating a date when a client cannot remember specific days or months. Perhaps you could create a similar algorithm?

Date Guidelines (d/e): Use the following rules if the participant is unsure of the exact date: DAY: Use the 5th for the beginning of the month, 15th for the middle of the month, and 25th for the end of the month. MONTH: Use March for early in the year, July for middle of the year, and October for later in the year, but try to make it so the number of weeks is about right.

Melissa

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Syed Hashmi Sent: Thursday, July 19, 2007 9:48 PM To: SPSSX-L@LISTSERV.UGA.EDU Subject: [SPSSX-L] Random date generator

Dear co-listers,

A dataset that I'm analyzing has a set of dates for events (start and stop dates) as well as how long those events occured for. The data for each date is in three variables (month, day, year). The years are pretty complete if they are filled in but the month and day might are sometimes listed as the exact month or date and other times they're listed as beginning, middle or end of the year (for the month variable) or the month (for the day variable).

Thus, I have 7 vars (startm, startd, starty, stopm, stopd, stopy, duration) from which I can deduce the start and stop dates (startdt, stopdt). Unfortunately, I have the complete start and stop date for about half the cases. The rest are missing either parts of one of the dates (eg. day) or for both. If I have one of the dates and a duration, I can calculate the other date.

The reason for this post is that there is a small subset of the population where I have the complete stop date but am missing the start day (I have the year and month) and am also missing the duration. I had to come up with some way to impute a start date for these cases for analysis (which will be done with and without these specific cases). I know that the event could not be more than a month long. Therefore, what I was planning on doing was based on the information I have, calculate the earliest possible start date (e_startdt) up to a month before the stop date and then randomly pick a date between e_startdt and the stop date.

Therefore, my query here was this: how can I code for this. I have an idea of how to do it in SAS but since I'm working in SPSS that doesn't help much. I'm assuming that it will be something simple like:

startdt = e_startdt + RANDOM_DAYS.

where, RANDOM_DAYS is a random number chosen from DATEDIFF(stopdt, startdt, "days").

So how would I go about doing this? I tried using the help files and all but couldn't come up with something that worked. Is this the best way to do this? Any other way that I can do this? Does it matter what kind of seeding I use for the random number generator?

Thanks.

- Shahrukh

PRIVILEGED AND CONFIDENTIAL INFORMATION This transmittal and any attachments may contain PRIVILEGED AND CONFIDENTIAL information and is intended only for the use of the addressee. If you are not the designated recipient, or an employee or agent authorized to deliver such transmittals to the designated recipient, you are hereby notified that any dissemination, copying or publication of this transmittal is strictly prohibited. If you have received this transmittal in error, please notify us immediately by replying to the sender and delete this copy from your system. You may also call us at (309) 827-6026 for assistance.

------------------------------

Date: Wed, 25 Jul 2007 11:13:35 -0300 From: Hector Maletta <hmaletta@fibertel.com.ar> Subject: Re: stepwise regression how to include all cases despite missing data

Hunna, Your use of the stepwise method for regression instead of running with all the variables at once is immaterial for your problem. What you need is some way of dealing with projects where some organizational practice does not apply. You do not give many details about the variables, but I imagine that each organizational practice might be a dummy variable, either present or absent. In such case, you may posit its effect on costs not as a result of "choosing or not choosing it when it is adequate to choose it" but as a result of its mere presence. A project may benefit from a practice if (a) the practice is applicable and (b) it is actually used; otherwise the project does not benefit from that practice. The absence of a practice may thus be a result of deliberate choice or impossibility of application, but in either case it would result in its effect not being observed. In other words, you may (if your particular situation affords this interpretation) treat the "missing" cases as negative instances, as zeroes in the dummies, and proceed with the regression. If this road is not conceptually adequate, you're in trouble. Hector

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Hunna Watson Sent: 25 July 2007 10:59 To: SPSSX-L@LISTSERV.UGA.EDU Subject: stepwise regression how to include all cases despite missing data

Hi all,

I'm running a stepwise regression of organizational practices on construction projects that predict project cost growth. I have data for 115 projects, yet some organizational practices were not applicable on some projects (in a random fashion). the missing data is obviously purposeful and not due to not filling in questionnaires etc. spss automatically excludes cases with any missing values, or wants to substitute a value, so I end up with a regression being carried out on 10 projects, obviously not useful. Any suggestions for syntax to include all cases or suggestions to rectify this problem?

Thanks in advance, Hunna Watson

------------------------------

Date: Wed, 25 Jul 2007 10:24:27 -0400 From: Mark A Davenport MADAVENP <M_Davenport@uncg.edu> Subject: Re: stepwise regression how to include all cases despite missing data

Hector,

When I worked at ACT, Inc we often treated the student's school identifier this way, usually with great success. Granted, we had many thousands of cases to draw from. Hunna only has 115? She is going to run out of cases pretty quickly, don't you think?

*************************************************************************************************************************************************************** Mark A. Davenport Ph.D. Senior Research Analyst Office of Institutional Research The University of North Carolina at Greensboro 336.256.0395 M_Davenport@uncg.edu

'An approximate answer to the right question is worth a good deal more than an exact answer to an approximate question.' --a paraphrase of J. W. Tukey (1962)

Hector Maletta <hmaletta@fibertel.com.ar> Sent by: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU> 07/25/2007 10:15 AM Please respond to Hector Maletta <hmaletta@fibertel.com.ar>

To SPSSX-L@LISTSERV.UGA.EDU cc

Subject Re: stepwise regression how to include all cases despite missing data

Hi all,

Thanks in advance, Hunna Watson

------------------------------

Date: Wed, 25 Jul 2007 11:36:49 -0300 From: Hector Maletta <hmaletta@fibertel.com.ar> Subject: Re: stepwise regression how to include all cases despite missing data

Hunna:

Even with a scale, the "missing" responses can be reinterpreted as saying "This practice was not effective in this case because -for one reason or another- it was not used". This is not quite clean conceptually, but is your only choice unless you put up with working with 10 cases.

The problem, apparently, is in the design of the questionnaire, asking for the effectiveness of a practice that is not in universal use among the cases under analysis. In any case, a practice cannot have any effectiveness if it is not used, so I insist you can treat it as having zero effectiveness when it was not used.

On the other hand, since your variables seem to be many, and your cases seem to be few, perhaps you should consider a more artisanal approach for identifying effective strategies instead of your alli-in-one regression. With 87 predictors and 115 cases you don't have a chance even without a single missing value.

Hector

_____

From: Hunna Watson [mailto:H.Watson@curtin.edu.au] Sent: 25 July 2007 11:36 To: Hector Maletta Subject: FW: Re: stepwise regression how to include all cases despite missing data

thanks for your reply, i've just come on board this project in the past two weeks, the data has been collected already and, this is essentially what happened though i'm simplifying it, respondents rated how effective the use of the strategy was for preventing cost growth in the form of work that had to be done again on the project, so I have data on a scale and no possibility for coding absent or present :S

extra information....

yes I know all the horrible things about stepwise, but it is the only suitable method I can think of to answer the research questions, I have just come on board the project in the last two weeks. The research is very exploratory and the topic hasn't been examined before. Data has been collected on many different predictor variables (design-related sources, subcontractor sources, site management sources, contract documentation, the list goes on and on - up to a terrible 87 predictors). There are 115 projects, so each is a case if you like, and we want to first look at this data set (no options there), but after that we can merge it with another data set containing information on a further 160 projects. Some predictors weren't relevant to projects. for instance, some didn't use incentives, but we have ratings on scales of 1 to 5 (assessing raters perceptions of contribution of use of that method to costs) and we are seeking to predict costs from the predictor variables. IF a method wasn't applicable e.g., use of a particular incentive plan, it has been left blank on questionnaires. No logical ordering.

Hi all,

Thanks in advance, Hunna Watson

------------------------------

Date: Wed, 25 Jul 2007 11:48:56 -0400 From: "William B. Ware" <wbware@email.unc.edu> Subject: Old Sunflower Option

In the older versions of SPSS, there was something called the sunflower option to show multiple cases at the same point in a scatter plot. Does anyone know how to do that in Version 14 and up?

Bill

__________________________________________________________________________ William B. Ware, Professor Educational Psychology, CB# 3500 Measurement, and Evaluation University of North Carolina PHONE (919)-962-7848 Chapel Hill, NC 27599-3500 FAX: (919)-962-1533 Office: 118 Peabody Hall EMAIL: wbware@unc.edu Adjunct Professor School of Social Work __________________________________________________________________________

------------------------------

Date: Wed, 25 Jul 2007 10:31:24 -0600 From: ViAnn Beadle <vab88011@gmail.com> Subject: Re: Old Sunflower Option

The nearest equivalent I can think of to the old sunflower option is the binhex function in GPL. It groups together nearby points and then you use the summary.count function to count the number of hits within the bin to set the size of the point displayed. This produces a plot sometimes referred to as bubble plot.

Here's some sample syntax which produces a "bubble" plot using the employee data.sav sample file. The SCALE command constrains the minimum point size to 5 pixels. IMHO, the default sizing creates really, really small 1 pixel points which look like dust on my monitor--so this gets around that. The color.interior fills in the points (defaults to circles). I think the default hollow points are ugly--so this gets around that.

GGRAPH /GRAPHDATASET NAME="graphdataset" VARIABLES=prevexp jobtime MISSING= LISTWISE REPORTMISSING=NO /GRAPHSPEC SOURCE=INLINE. BEGIN GPL SOURCE: s=userSource(id("graphdataset")) DATA: prevexp=col(source(s), name("prevexp")) DATA: jobtime=col(source(s), name("jobtime")) GUIDE: axis(dim(1), label("Previous Experience (months)")) GUIDE: axis(dim(2), label("Months since Hire")) SCALE: linear(aesthetic(aesthetic.size), aestheticMinimum(size."5px")) ELEMENT: point(position(bin.hex(prevexp*jobtime, dim(1,2))), size(summary.count()), color.interior(color.blue)) END GPL.

The IGRAPH procedure also provides a jittering option which nudges the points slightly apart by adding a small amount of random variation, but I think the GPL binhex approach works much better.

-----Original Message----- From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of William B. Ware Sent: Wednesday, July 25, 2007 9:49 AM To: SPSSX-L@LISTSERV.UGA.EDU Subject: Old Sunflower Option

In the older versions of SPSS, there was something called the sunflower option to show multiple cases at the same point in a scatter plot. Does anyone know how to do that in Version 14 and up?

Bill

------------------------------

Date: Wed, 25 Jul 2007 18:39:32 +0200 From: Georg Maubach <Georg.Maubach@dpwnbc.net> Subject: AW: Re: Old Sunflower Option

Hi All,

We tried to run the syntax example on our "Employee data.sav" file. As we have a German version the variable names were translated to German. Does anybody know how we could obtain sample files in English?

Best regards

Georg Maubach Research Manager

-----Urspr�ngliche Nachricht----- Von: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] Im Auftrag von ViAnn Beadle Gesendet: Mittwoch, 25. Juli 2007 18:31 An: SPSSX-L@LISTSERV.UGA.EDU Betreff: Re: Old Sunflower Option

The IGRAPH procedure also provides a jittering option which nudges the points slightly apart by adding a small amount of random variation, but I think the GPL binhex approach works much better.

In the older versions of SPSS, there was something called the sunflower option to show multiple cases at the same point in a scatter plot. Does anyone know how to do that in Version 14 and up?

Bill

------------------------------

Date: Wed, 25 Jul 2007 13:28:22 -0500 From: "Hashmi, Syed S" <Syed.S.Hashmi.1@uth.tmc.edu> Subject: Re: Random date generator

Thanks Melissa,

I'm already doing something similar to what you said, using 1st, 10th and 20th as the dates for start, middle and end of the month. The Month is a bit trickier since my exposures are events during pregnancy so I have to be careful about just assigning a random month lest it falls outside the pregnancy duration.

They question I had asked concerned dates which had month and year but no day information - not even beginning, middle or end. Therefore, I couldn't even depend on the 1st-10th-20th coding.

My final solution for the problem where I had a start date and had a stop month was to pick a random date between the start date (or the first date of the stop month) and the last day of the stop month. Gene Maguin had emailed me earlier and suggested I use the UNIFORM function to randomly select a date. I don't think that message was posted on the list-serv, so the body is copied below. I've used the function since and it works nicely.

Thanks again for your help though. I agree that there should be some sort of algorithm in place at the interviewer level to minimize the frequency of incomplete data.

- S. Hashmi

*copy of email from Gene*

> -----Original Message----- > From: Gene Maguin [mailto:emaguin@buffalo.edu] > Sent: Friday, July 20, 2007 8:05 AM > To: Hashmi, Syed S > Subject: RE: Random date generator > > Syed, > > I'd like to be helpful to you but I don't have time to make up a full > solution. I think this would be a valid example of your question. > > Start date (mm/dd/yyyy): 5/x/2004 > Stop date (mm/dd/yyyy): 6/17/2004 > Possible duration range (6/17/2004)-(5/31/2004)=17 days to > (6/17/2004)-(5/18/2004)=30 days (I assume a 30 day month) > > So x has to be between 18 and 31 inclusive. > > So I think the trick to the random draw is this command. > > Compute x=uniform(14). > Compute x=trunc(x). > > Check this but I'm pretty sure that the range of x will be 0 to 13. > Your actual date is then > Compute x=x+18. > > There's lots of big 'little bits' to tidy up but this will get you want > you > want when the tidying up has been done. > > Best wishes, Gene Maguin >

> -----Original Message----- > From: Melissa Ives [mailto:mives@chestnut.org] > Sent: Wednesday, July 25, 2007 9:13 AM > To: Hashmi, Syed S; SPSSX-L@LISTSERV.UGA.EDU > Subject: RE: [SPSSX-L] Random date generator > > During the assessment process, interviewers are given these instructions > for estimating a date when a client cannot remember specific days or > months. Perhaps you could create a similar algorithm? > > Date Guidelines (d/e): Use the following rules if the participant is > unsure of the exact date: > DAY: Use the 5th for the beginning of the month, 15th for the middle of > the month, and 25th for the end of the month. > MONTH: Use March for early in the year, July for middle of the year, and > October for later in the year, but try to make it so the number of weeks > is about right. > > Melissa > > -----Original Message----- > From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of > Syed Hashmi > Sent: Thursday, July 19, 2007 9:48 PM > To: SPSSX-L@LISTSERV.UGA.EDU > Subject: [SPSSX-L] Random date generator > > Dear co-listers, > > A dataset that I'm analyzing has a set of dates for events (start and > stop > dates) as well as how long those events occured for. The data for each > date is in three variables (month, day, year). The years are pretty > complete if they are filled in but the month and day might are sometimes > listed as the exact month or date and other times they're listed as > beginning, middle or end of the year (for the month variable) or the > month (for the day variable). > > Thus, I have 7 vars (startm, startd, starty, stopm, stopd, stopy, > duration) from which I can deduce the start and stop dates (startdt, > stopdt). > Unfortunately, I have the complete start and stop date for about half > the cases. The rest are missing either parts of one of the dates (eg. > day) or for both. If I have one of the dates and a duration, I can > calculate the other date. > > The reason for this post is that there is a small subset of the > population where I have the complete stop date but am missing the start > day (I have the year and month) and am also missing the duration. I had > to come up with some way to impute a start date for these cases for > analysis (which will be done with and without these specific cases). I > know that the event could not be more than a month long. Therefore, what > I was planning on doing was based on the information I have, calculate > the earliest possible start date (e_startdt) up to a month before the > stop date and then randomly pick a date between e_startdt and the stop > date. > > Therefore, my query here was this: how can I code for this. I have an > idea of how to do it in SAS but since I'm working in SPSS that doesn't > help much. I'm assuming that it will be something simple like: > > startdt = e_startdt + RANDOM_DAYS. > > where, RANDOM_DAYS is a random number chosen from DATEDIFF(stopdt, > startdt, "days"). > > So how would I go about doing this? I tried using the help files and all > but couldn't come up with something that worked. Is this the best way to > do this? Any other way that I can do this? Does it matter what kind of > seeding I use for the random number generator? > > Thanks. > > - Shahrukh > > > PRIVILEGED AND CONFIDENTIAL INFORMATION > This transmittal and any attachments may contain PRIVILEGED AND > CONFIDENTIAL information and is intended only for the use of the > addressee. If you are not the designated recipient, or an employee > or agent authorized to deliver such transmittals to the designated > recipient, you are hereby notified that any dissemination, > copying or publication of this transmittal is strictly prohibited. If > you have received this transmittal in error, please notify us > immediately by replying to the sender and delete this copy from your > system. You may also call us at (309) 827-6026 for assistance.

------------------------------

Date: Wed, 25 Jul 2007 15:05:07 -0400 From: Richard Ristow <wrristow@mindspring.com> Subject: Re: Random date generator

Somehow I missed or deleted the original posting in this thread. Anyway, on Thursday, July 19, 2007 9:48 PM Hashmi, Syed S asked,

>A dataset that I'm analyzing has a set of dates for events (start and >stop dates) as well as how long those events occured for. The data >for each date is in three variables (month, day, year). The years are >pretty complete if they are filled in but the month and day might are >sometimes listed as the exact month or date and other times they're >listed as beginning, middle or end of the year (for the month >variable) or the month (for the day variable). > >I have [two dates as three variables each, plus a duration] duration). >I have the complete start and stop date for about half the cases. The >rest are missing either parts of one of the dates (eg. day) or for >both. If I have one of the dates and a duration, I can calculate the >other date.

So far, so good, though be careful about how precise your 'durations' are.

>There is a small subset of the population where I have the complete >stop date but am missing the start day (I have the year and month) and >am also missing the duration. I had to come up with some way to >impute a start date for these cases for analysis. (which will be done >with and without these specific cases). I know that the event could >not be more than a month long. I was planning calculate the earliest >possible start date (e_startdt) up to a month before the stop date and >then randomly pick a date between e_startdt and the stop date.

OUCH! I would not do this. Period.

*MAYBE* the start dates and durations you get this way will be vaguely representative of the population of events, though I doubt it. Are your durations roughly uniformly distributed from 0 to 30 days? For goodness sake, you ought to check that before proceeding.

But even if they're representative of the population, they have nothing to do with the individual cases for which they're 'imputed'. No analysis using those 'dates' will be the least trustworthy.

A far better approach is to use true missing-value interpolation on the *durations*, not the dates. (See SPSS 'MVA'.) I'm not clear how many durations you'd have to impute. If it's near 50%, that won't be at all reliable, either.

-Good luck, Richard

------------------------------

Date: Wed, 25 Jul 2007 15:09:53 -0500 From: "Hashmi, Syed S" <Syed.S.Hashmi.1@uth.tmc.edu> Subject: Re: Random date generator

> -----Original Message----- > From: Richard Ristow [mailto:wrristow@mindspring.com] > Sent: Wednesday, July 25, 2007 2:05 PM > > >There is a small subset of the population where I have the complete > >stop date but am missing the start day (I have the year and month) and > >am also missing the duration. I had to come up with some way to > >impute a start date for these cases for analysis. (which will be done > >with and without these specific cases). I know that the event could > >not be more than a month long. I was planning calculate the earliest > >possible start date (e_startdt) up to a month before the stop date and > >then randomly pick a date between e_startdt and the stop date. > > OUCH! I would not do this. Period. > > *MAYBE* the start dates and durations you get this way will be vaguely > representative of the population of events, though I doubt it. Are your > durations roughly uniformly distributed from 0 to 30 days? For goodness > sake, you ought to check that before proceeding. > > But even if they're representative of the population, they have nothing > to do with the individual cases for which they're 'imputed'. No > analysis using those 'dates' will be the least trustworthy. > > A far better approach is to use true missing-value interpolation on the > *durations*, not the dates. (See SPSS 'MVA'.) I'm not clear how many > durations you'd have to impute. If it's near 50%, that won't be at all > reliable, either. > > -Good luck, > Richard

Richard,

Thanks for your input. I realize that I was stepping into extremely treacherous territory when I decide to impute dates and select random ones. As for the durations being roughly uniformly distributed, that's what it looks like from the data I do have. Initially, I'd assumed that durations would have a mean of about 7 days but somehow the data I do have doesn't seem to show that. It's more or less uniformly distributed. There were some durations that were >30 days but I doubt if they're true. Therefore, I decided to go ahead with the uniform distribution (although, the whole imputation and random selection still bothers me).

The reason that I'm trying to get an idea about the dates, especially the event start dates, is due to the nature of the study question. I'm looking at the occurrence of certain events during pregnancy. However, these events of interest have to occur within the first trimester, or if I narrow it down further, the first two months of pregnancy. Therefore, I have to know if an event occurred within a certain period of time after the last menstrual date as reported by the woman. At the end of the day, the variables for all the events get filtered down to a single dichotomous variable - Y/N did the event occur during the period of interest?

I will do the analysis with and without the cases where the dates have been imputed from incomplete data. I hadn't previously thought of using true-missing value interpolation on the durations but I'll look into it. I've never done that before so will have to read up a bit on it. I might have an issue with number of missings though, since more cases have at least some part of the date then a duration value.

Thanks again for your advice. It's always nice to get a fresh look at an issue.

- Shahurkh

------------------------------

Date: Wed, 25 Jul 2007 16:24:09 -0400 From: Gene Maguin <emaguin@buffalo.edu> Subject: Re: Random date generator

Syed,

It sounds like you are going to use the imputed dates to decide if something happended or not. The new variable, 'something happened or not' might be a dependent variable or it might be an independent variable. There's a literature on estimating relationships in the presence of missing data. To correctly estimate relationships (or, at least, come very close), you should use either multiple imputation or a maximum likelihood estimation method that incorporates the EM algorithm. So far as I know, SPSS has neither. The key person here is Donald Rubin. But, there are other, more recent articles.

Gene Maguin

------------------------------

Date: Wed, 25 Jul 2007 20:43:06 +0000 From: Hamish Travers <hamish_travers@hotmail.com> Subject: Can someone please tell me how to unsubscribe from this forum, thanks in advance

_________________________________________________________________ Invite your mail contacts to join your friends list with Windows Live Space= s. It's easy! http://spaces.live.com/spacesapi.aspx?wx_action=3Dcreate&wx_url=3D/friends.= aspx&mkt=3Den-us=

------------------------------

Date: Wed, 25 Jul 2007 16:41:18 -0500 From: "Hashmi, Syed S" <Syed.S.Hashmi.1@uth.tmc.edu> Subject: Re: Random date generator

Thanks Gene,

After the comments that you and Richard made I'm thinking real hard of rethinking the whole thing. Maximum likelihood estimation was something that I had thought of initially but didn't follow up on. I guess it's time that I do. Thanks again for your help.

- Shahrukh

> -----Original Message----- > From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of > Gene Maguin > Sent: Wednesday, July 25, 2007 3:24 PM > To: SPSSX-L@LISTSERV.UGA.EDU > Subject: Re: Random date generator > > Syed, > > It sounds like you are going to use the imputed dates to decide if > something > happended or not. The new variable, 'something happened or not' might be a > dependent variable or it might be an independent variable. There's a > literature on estimating relationships in the presence of missing data. To > correctly estimate relationships (or, at least, come very close), you > should > use either multiple imputation or a maximum likelihood estimation method > that incorporates the EM algorithm. So far as I know, SPSS has neither. > The > key person here is Donald Rubin. But, there are other, more recent > articles. > > Gene Maguin

------------------------------

Date: Wed, 25 Jul 2007 18:33:35 -0400 From: Richard Ristow <wrristow@mindspring.com> Subject: Re: Can someone please tell me how to unsubscribe

FAQ: How to unsubscribe, or leave list SPSSX-L:

Requests to unsubscribe that are posted to the list, will never be acted on.

You must send the request to LISTSERV@LISTSERV.UGA.EDU.

From the E-mail address from which you're subscribed to the list, send a message to LISTSERV@LISTSERV.UGA.EDU with the following words in the body of the message:

SIGNOFF SPSSX-L

Don't put anything else (your name, etc.) in the body of the message.

It should work. If it doesn't, go to the following Web page:

http://www.listserv.uga.edu/cgi-bin/wa?SUBED1=spssx-l&A=1

and unsubscribe from there.

........................... More information:

When you subscribed to the list, you received a welcome message (I'm copying it below) with instructions (including asking you to save it).

From the welcome message:

>Your subscription to the SPSSX-L list (SPSSX(r) Discussion) >has been accepted. > >Please save this message for future reference, [...] > >You may leave the list at any time by sending a "SIGNOFF SPSSX-L" >command to LISTSERV@LISTSERV.UGA.EDU.

There are many other commands that can be sent to the same address, to manage your subscription. If you send mail to LISTSERV@LISTSERV.UGA.EDU with the text

INFO REFCARD

and no other text, you will be mailed a file describing those commands.

------------------------------

Date: Wed, 25 Jul 2007 16:00:22 -0700 From: Karen Powers <kmpowers@u.washington.edu> Subject: RENAME LOOP?

Hello SPSS list, I have a dataset in which the variable names are var002, var003 ... var3477.

I would like to RENAME each variable with the number listed in row 1 of each respective column. The first number in var002 is 6951030. I would like var002 renamed "rs6951030". The command for doing this once that runs nicely is:

RENAME VARS var002 = "rs"+ "6951030". EXE.

Now I would like to do this for all vars through var3477. I have tried DO REPEAT and LOOP commands but they both say >Warning # 141. Command name: RENAME VARS >DO REPEAT has no effect on this command.

Any ideas on how I can do this (3477 times)?

Thanks, Karen

------------------------------

Date: Wed, 25 Jul 2007 19:27:19 -0400 From: Richard Ristow <wrristow@mindspring.com> Subject: Re: Aggregating with missing data

At 03:30 AM 7/14/2007, Marco wrote:

>When using the aggregate (mean) function in SPSS, cells that contain >missing data become empty. Thus, a cell that should contain the mean >of multiple cells (one of which is empty/missing), turns to zero >because it contains one missing datum.

I'm not sure what's happening to you, but you shouldn't be seeing what you say you're seeing.

From your description, it sounds like you're doing one of two things: a) Using the MEAN function with command AGGREGATE to average over a set of variables b) Using the MEAN function in the transformation language to average over a set of variables.

BOTH of those, however, ignore missing values when averaging, and take the mean of the non-missing values; they don't make a value 0 because there's a missing value in the list. (That would be a very dangerous thing to do anyway.) So I'm not sure what's happening.

Could you post the syntax, some test data, what output you get, and tell us what output you want?

..................................... Here are demonstrations of averaging across cases with AGGREGATE, and averaging across variables. It's SPSS 15 draft output (WRR-not saved separately). ..................................... Using AGGREGATE to average over cases: List |-----------------------------|---------------------------| |Output Created |25-JUL-2007 19:16:03 | |-----------------------------|---------------------------| [Aggregate]

Group Value

1 1 1 2 1 3 2 4 2 5 2 . 2 7 3 . 3 9 3 10

Number of cases read: 10 Number of cases listed: 10

AGGREGATE OUTFILE=* /BREAK=GROUP /Members 'Size of group' = NU /MEAN 'Mean of "value"' = MEAN(VALUE).

LIST.

List |-----------------------------|---------------------------| |Output Created |25-JUL-2007 19:16:03 | |-----------------------------|---------------------------| Group Members MEAN

1 3 2.00 2 4 5.33 3 3 9.50

Number of cases read: 3 Number of cases listed: 3 ..................................... Using MEAN to average over variables: List |-----------------------------|---------------------------| |Output Created |25-JUL-2007 19:16:04 | |-----------------------------|---------------------------| [Wide]

Group Members Value.1 Value.2 Value.3 Value.4

1 3 1 2 3 . 2 4 4 5 . 7 3 3 . 9 10 .

Number of cases read: 3 Number of cases listed: 3

NUMERIC Mean (F6.2). COMPUTE Mean = MEAN(Value.1 TO Value.4). LIST.

List |-----------------------------|---------------------------| |Output Created |25-JUL-2007 19:16:26 | |-----------------------------|---------------------------| [Wide]

Group Members Value.1 Value.2 Value.3 Value.4 Mean

1 3 1 2 3 . 2.00 2 4 4 5 . 7 5.33 3 3 . 9 10 . 9.50

Number of cases read: 3 Number of cases listed: 3

=================== APPENDIX: All code =================== I keyed the test data into the Data Editor; however, it can be recovered from the LIST output fairly easily. Here's all the code:

DATASET ACTIVATE TestData. DATASET COPY Aggregate. DATASET ACTIVATE Aggregate WINDOW=FRONT.

LIST.

AGGREGATE OUTFILE=* /BREAK=GROUP /Members 'Size of group' = NU /MEAN 'Mean of "value"' = MEAN(VALUE).

LIST.

DATASET ACTIVATE TestData. DATASET COPY Wide. DATASET ACTIVATE Wide WINDOW=FRONT.

SORT CASES BY Group . CASESTOVARS /ID = Group /GROUPBY = VARIABLE /COUNT = Members "Size of group" .

LIST.

NUMERIC Mean (F6.2). COMPUTE Mean = MEAN(Value.1 TO Value.4).

LIST.

------------------------------

Date: Wed, 25 Jul 2007 20:24:54 -0400 From: Richard Ristow <wrristow@mindspring.com> Subject: Re: Matching files on one of three possible ID's

At 09:29 AM 7/12/2007, Daniel Robertson wrote:

>I have two database extracts that I am trying to merge, one of which >contains enrolled students and the other contains approximately the >same group of students when they were applicants. In the Enrollment >file students are uniquely identified by 'enroll_id'. In the Applicant >file there is a primary ID, 'applicant_id1', but there may be up to >two other IDs which were issued and updated provisionally as the >student was going through the application process. The rub is that >'enroll_id' may match any one of the applicant IDs, not necessarily >the primary one.

Gene's given you a workable solution. It requires sorting the data three times; but with three keys, something like that is inevitable.

You *can* combine the three sorting operations into one step, by using XSAVE to create three copies of each Applicant record, one each in which 'enroll_id' is loaded from each of the three candidate key variables in the Applicant file. Then sort the resulting file by that 'enroll_id', MATCH FILES with the Enrollment file, and discard any Applicant records that don't match.

Now, that's the simplest possible case. You may need logic in case, say, the same ID value occurs in more than one of the Applicant-record fields. But it's another way to go.

Sorry; no code this time.

------------------------------

End of SPSSX-L Digest - 24 Jul 2007 to 25 Jul 2007 (#2007-207) **************************************************************

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

listserv.uga.edu
Enterprise Information Technology Services
The University of Georgia
listhelp@uga.edu