|
In a message dated 4/13/2004 1:15:50 PM Eastern Daylight Time, bpcs-l-request@xxxxxxxxxxxx writes: > Subj: BPCS-L Digest, Vol 2, Issue 80 > Date: 4/13/2004 1:15:50 PM Eastern Daylight Time > From: bpcs-l-request@xxxxxxxxxxxx > Reply-to: bpcs-l@xxxxxxxxxxxx > To: bpcs-l@xxxxxxxxxxxx > Sent from the Internet > > > > Send BPCS-L mailing list submissions to > bpcs-l@xxxxxxxxxxxx > > To subscribe or unsubscribe via the World Wide Web, visit > http://lists.midrange.com/mailman/listinfo/bpcs-l > or, via email, send a message with subject or body 'help' to > bpcs-l-request@xxxxxxxxxxxx > > You can reach the person managing the list at > bpcs-l-owner@xxxxxxxxxxxx > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of BPCS-L digest..." > > > Today's Topics: > > 1. creative product ideas welcome -- BPCS security software > (Milt Habeck) > 2. Forecasting (MisterBPCS@xxxxxxx) > 3. forecasting (MisterBPCS@xxxxxxx) > 4. Re: forecasting (Jim Black) > 5. Re: forecasting (Stewart Millar) > > > ---------------------------------------------------------------------- > > message: 1 > date: Mon, 12 Apr 2004 14:27:26 -0500 > from: "Milt Habeck" <mhabeck@xxxxxxxxxx> > subject: creative product ideas welcome -- BPCS security software > > Good afternoon ... > > Our "Stocking Stuffers (tm) for SOX" products have attracted > authentic interest in other security software products for BPCS. > Here is an example of an expressed client need that we don't > currently have a product for: > > >> User security at the field-by-field level so as to > improve internal controls over the maintenance > of key BPCS master files. > > If you have already developed such a product, please contact > me off-line. We could discuss a way to incorporate your > product into our collection of Bells &Whistles® software > enhancements for BPCS: > http://www.unbeatenpathintl.com/bells/source/1.html > > Peace to you, > > Milt Habeck > President > Unbeaten Path > > North America toll-free: (888) 874-8008 > International voice line: (262) 681-3151 > mhabeck@xxxxxxxxxx > www.unbeatenpathintl.com > > > > > > > ------------------------------ > > message: 2 > date: Tue, 13 Apr 2004 09:06:26 EDT > from: MisterBPCS@xxxxxxx > subject: Forecasting > > > > > ------------------------------ > > message: 3 > date: Tue, 13 Apr 2004 09:11:32 EDT > from: MisterBPCS@xxxxxxx > subject: forecasting > > Hey gang, > I have a client trying to use forecasting and the computations look > reasonable but when looking at the trend (which should be going down) are > going up. The > illustrations are: > > Period Start Date End Date Demand > 12 12/01/03 12/31/03 71.00 > 11 11/01/03 11/30/03 208.00 > 10 10/01/03 10/31/03 58.00 > 9 9/01/03 9/30/03 303.00 > 8 8/01/03 8/31/03 73.00 > 7 7/01/03 7/31/03 162.00 > 6 6/01/03 6/30/03 394.00 > 5 5/01/03 5/31/03 96.00 > 4 4/01/03 4/30/03 471.00 > 3 3/01/03 3/31/03 192.00 > 2 2/01/03 2/28/03 188.00 > 1 1/01/03 1/31/03 264.00 > 12 12/01/02 12/31/02 > > And > > > > > Any one have any suggestions as to why the issue? > Thanks, > Ric Weide > rcweide@xxxxxxx > or > MisterBPCS@xxxxxxx > > ------------------------------ > > message: 4 > date: Tue, 13 Apr 2004 09:56:31 -0400 > from: "Jim Black" <jrblack@xxxxxxxxxx> > subject: Re: forecasting > > Your data series is a bit confusing in that I'm not clear if the demand for > 71 was last period or 12 periods ago. If it was 12 periods ago, then > exponential smoothing would project demand for the next period to be about > 300 (depending on the weighting given). My comments on "trend" will assume > that the value of 71 begins the series. > > If you haven't already, input the data into MS Excel (or some such tool) and > graph it. With MS Excel, you can also add a trendline using various > techniques. A 3-month moving average will show a downward trend whereas > exponential smoothing will show an upward trend. Which is "right"? I'll tell > you after the next period ends. [smile] > > Imagine a series of data that shows 30 for each of the past 12 periods. What > is the projection for the next period and what is the trend? Well, most > people would project the next period to be 30 as they assume the trend to be > flat. In fact, the projection for the next period is ZERO! > > The point is, the witless box is asked to manipulate content (numbers) > without regard to their context. And content without context is pretext. Had > someone bothered to ask what the item was that registered 30 per period, > they would have learned that it was my consumption of cigarette packets per > month and had they asked further, they would have learned that I decided to > quit and so the trend is meaningless and the projection for the next month > ought to be ZERO. > > So, only you can know which trending technique to choose coz you know the > product and you know the business. > > > > ----- Original Message ----- > From: <MisterBPCS@xxxxxxx> > To: <bpcs-l@xxxxxxxxxxxx> > Sent: Tuesday, April 13, 2004 9:11 AM > Subject: forecasting > > > >Hey gang, > >I have a client trying to use forecasting and the computations look > >reasonable but when looking at the trend (which should be going down) are > going up. The > >illustrations are: > > > >Period Start Date End Date Demand > > 12 12/01/03 12/31/03 71.00 > > 11 11/01/03 11/30/03 208.00 > > 10 10/01/03 10/31/03 58.00 > > 9 9/01/03 9/30/03 303.00 > > 8 8/01/03 8/31/03 73.00 > > 7 7/01/03 7/31/03 162.00 > > 6 6/01/03 6/30/03 394.00 > > 5 5/01/03 5/31/03 96.00 > > 4 4/01/03 4/30/03 471.00 > > 3 3/01/03 3/31/03 192.00 > > 2 2/01/03 2/28/03 188.00 > > 1 1/01/03 1/31/03 264.00 > > 12 12/01/02 12/31/02 > > > >And > > > > > > > > > >Any one have any suggestions as to why the issue? > >Thanks, > >Ric Weide > >rcweide@xxxxxxx > >or > >MisterBPCS@xxxxxxx > > > > > ---------------------------------------------------------------------------- > ---- > > > >_______________________________________________ > >This is the SSA's BPCS ERP System (BPCS-L) mailing list > >To post a message email: BPCS-L@xxxxxxxxxxxx > >To subscribe, unsubscribe, or change list options, > >visit: http://lists.midrange.com/mailman/listinfo/bpcs-l > >or email: BPCS-L-request@xxxxxxxxxxxx > >Before posting, please take a moment to review the archives > >at http://archive.midrange.com/bpcs-l. > > > > > > > > > ------------------------------ > > message: 5 > date: Tue, 13 Apr 2004 17:03:44 +0100 > from: "Stewart Millar" <stewart.millar@xxxxxxxxxxx> > subject: Re: forecasting > > A simple exponentially smoothed average on the figures you present does in > fact give a decreasing average over the last four periods. > > My own experience with the BPCS Forecasting module was that much of the > statistical coding was actually in error - calculations in the wrong sequence > and > coding in the programs that was not completed (abandoned) - the result was > that forecast numbers were produced but they clearly had not truly adhered to > the statistical method they were meant to be emulating. This was only > corrected by extensive re-programming of the statistical calculations by the > SSA > client concerned. I personally (whilst working for SSA) attempted to have the > corrections made but it was never high on anyone's priority in Chicago and I > would believe that no corrections have since been made to the erroneous > coding. > The only standard method that did not need correcting was the method that > uses the previous years actuals as a forecast. > > Note that the incorrect use of seasonality - when there is no statistical > seasonality present in the data can have unpredictable effects on your > forecast > results and trends. > > Regards, > > Stewart > > ----- Original Message ----- > From: MisterBPCS@xxxxxxx > To: bpcs-l@xxxxxxxxxxxx > Sent: Tuesday, April 13, 2004 2:11 PM > Subject: forecasting > > > Hey gang, > I have a client trying to use forecasting and the computations look > reasonable but when looking at the trend (which should be going down) are > going up. The > illustrations are: > > Period Start Date End Date Demand > 12 12/01/03 12/31/03 71.00 > 11 11/01/03 11/30/03 208.00 > 10 10/01/03 10/31/03 58.00 > 9 9/01/03 9/30/03 303.00 > 8 8/01/03 8/31/03 73.00 > 7 7/01/03 7/31/03 162.00 > 6 6/01/03 6/30/03 394.00 > 5 5/01/03 5/31/03 96.00 > 4 4/01/03 4/30/03 471.00 > 3 3/01/03 3/31/03 192.00 > 2 2/01/03 2/28/03 188.00 > 1 1/01/03 1/31/03 264.00 > 12 12/01/02 12/31/02 > > And > > > > > Any one have any suggestions as to why the issue? > Thanks, > Ric Weide > rcweide@xxxxxxx > or > MisterBPCS@xxxxxxx > > > > ----------------------------------------------------------------------------- > - > > > _______________________________________________ > This is the SSA's BPCS ERP System (BPCS-L) mailing list > To post a message email: BPCS-L@xxxxxxxxxxxx > To subscribe, unsubscribe, or change list options, > visit: http://lists.midrange.com/mailman/listinfo/bpcs-l > or email: BPCS-L-request@xxxxxxxxxxxx > Before posting, please take a moment to review the archives > at http://archive.midrange.com/bpcs-l. > > > > ------------------------------ > > _______________________________________________ > This is the SSA's BPCS ERP System (BPCS-L) digest list > To post a message email: BPCS-L@xxxxxxxxxxxx > To subscribe, unsubscribe, or change list options, > visit: http://lists.midrange.com/mailman/listinfo/bpcs-l > or email: BPCS-L-request@xxxxxxxxxxxx > Before posting, please take a moment to review the archives > at http://archive.midrange.com/bpcs-l. > > > > End of BPCS-L Digest, Vol 2, Issue 80 > ************************************* > In response to the response to my quest for forecasting info. It appears that part of my message was crunched since it was a screen print and I forgot they don't allow that. The print showed that the trend was still going uphill even though the data trend was going downhill. If anyone has any help they can offer, such as the specific code that anyone has developed to make the Forecasting trend properly. I sure could use that. Thanks. Ric Weide
As an Amazon Associate we earn from qualifying purchases.
This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].
Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.
midrange.com
