Date: Wed, 9 Feb 2005 10:46:03 -0600
Reply-To: "Peck, Jon" <firstname.lastname@example.org>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: "Peck, Jon" <email@example.com>
Subject: Re: Population Histograms
Content-Type: text/plain; charset="US-ASCII"
While this doesn't help with SPSS 12, the SPSS 13 population pyramid facility works with any (reasonable) number of categories. However, unless there is some useful structure to the categories, it isn't likely to make easily digested charts in that case. Paneling in general, though, works well even with many categories.
In SPSS 12, Interactive graphics can do paneled charts, although you cannot get the mirrored effect.
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of Howie Harshaw
Sent: Wednesday, February 09, 2005 10:20 AM
Subject: Re: [SPSSX-L] Population Histograms
I'm afraid that I don't have a SPSS solution, but you can use Excel
without the legend displaying negative values for age. I have found the
following link to be useful in explaining how to do this:
However, this doesn't address displaying all three years on the same
graph. As an aside, I think that displaying all three pyramids on one
graph might be difficult for readers to take in - perhaps displaying
them in three panels might get the information across?
Forest Resource Management
Faculty of Forestry
University of British Columbia
Tel: (604) 786-3141
Jason Carter wrote:
> I'm a neophyte to SPSS and to computing in general (despite the grey hair).
> I read with interest today (Feb 9) the thread on Overlaying Multiple Histograms. In particular, Mr. Peck's reply that version 13 enables population pyramids, which I assume is meant like this:
> I have version 12.0. I'm also using a file of about 45,000 records, composed of about 15,000 records for the years 2002, 2003, and 2004, with age and sex for each record. The file is being used for Kaplan-Meier analysis of duration in receipt of payment. I thought about trying to run this analysis with age and sex, but wanted to present the general pyramid first. I suppose it's possible to export the data to Excel and change men's ages to negatives (were it only possible in real life!), but the result would ask the reader to ignore the negatives. Ideally there would be some way of presenting all three years on one graph so that the changes can be seen over time, without resorting to animation - for instance a bar graph of 2002, with superimposed lines for 2003 and 2004..
> On the way out there front, it would be very interesting to forecast the population changes well into the future; however, I have no idea what function would be needed or is generally accepted for such a relatively small cohort.
> Any assistance on any of the issues mentioned would be appreciate.
> Many thanks,
> Jason Carter
> ***** The information contained in this transmission is confidential and intended only for the use of the individual or entity to whom it is addressed. If you are not the intended recipient, you are hereby notified that any distribution, copying, disclosure and use of, or reliance on, the contents of this transmission is strictly prohibited. If you have received this communication in error, please notify the sender immediately by telephone and permanently delete the original message, attachments, and all copies. Thank you. *****