Problems with the Forecasting Chapter

[Steve Prevette]

We went over the "Forecasting" chapter, which makes heavy use of moving averages and regression. I would also like you to review the attached paper and provide any comments or real life sagas with such misuse of statistical principles.

See http://elsmar.com/Forums/showthread.php?t=9081 for the paper.

Worth +1 point extra credit on the final.

[Lori Beeler]

Interesting how the same numbers can be manipulated to tell the story most adventageous at the time. A truly ethical and skilled manager should have the gumption to accept reality however difficult it is to accept but I know that is not typically the case.

Numbers can be manipulated as well as the written word. Take for instance a resume, written skillfully to include all the right key words. Not necessarily outright lies, but not exactly true either. "Experienced with excel, powerpoint and access" sounds great but what does "experienced" really encompass? One year, one month, one week of experience...it is hard to tell. Experience is experience but how useful is this information at face value?

My thoughts are our jobs as Managers are to lead by example; be truthful, ethical and honest is all our dealings. Stand up when it is time to stand firm, compromise when it is time to compromise and the wisdom to know what to do when.

Lori Beeler
MBA Student

[Icy Mountain]

Benjamin Disraeli , the prime minister of the British Empire from 1874-1880, was reported by Mark Twain to have uttered this brilliant quote on statistical analysis: “There are three kinds of lies: lies, d*** lies, and statistics.”
-Icy

[Jim Wynne]

Originally Posted by Icy Mountain

Benjamin Disraeli , the prime minister of the British Empire from 1874-1880, was reported by Mark Twain to have uttered this brilliant quote on statistical analysis: “There are three kinds of lies: lies, d*** lies, and statistics.”
-Icy

Icy,

This is one of the very few times I've ever seen this quote properly attributed. The attribution usually goes to Twain (who did say it) or Disraeli (there doesn't appear to be a reliable primary source) but hardly anyone reports it as Twain quoting Disraeli, which is more accurate, of course.

[Bill Pflanz]

I hope your MBA students are listening to you, Steve. Before I got into quality, I did budgeting and strategic planning that involved a lot of forecasting. Since I had an MBA, I used many of the techniques that are in your chapter. Even worse, I sometimes reset my "target" forecast based on the actual versus forecast. My forecasts started showing more and more variation from actual when I made this adjustment. If Steve has not shown you the funnel experiment yet, it will explain what happened to my forecasts.

I finally realized that by forecasting the average with some adjustments for known variation (e.g. new customers), I had better forecasts. Later when I learned SPC, I realized I should have done a control chart and used the average as my forecast with the control limits showing the most likely highest and lowest forecast. For teaching purposes, text books normally show examples where there is a steady increase or decrease in the data. Unfortunately, much of the business world data that the students will see is more like Steve's example.

Bill Pflanz

[Anita Alston]

I worked in Occupational Health for many years and had to keep records on all employee injuries, and turn in the injury numbers to OSHA at the end of every year. When I requested some data re. national injury trends and averages for the previous few years, (from an OSHA administrator at the federal level), I was told that, "He doesn't know where to locate such data."
There were wide variances in national injury numbers (stats) cited, depending upon which journal article(s) I read. Since, all lost-worktime injuries had to be reported to the federal Occupational Safety and Health Administration (OSHA), I thought one of their administrators would be able to send me some data on national averages and trends; HA!
Anita

[Howard Atkins]

Originally Posted by Icy Mountain

Benjamin Disraeli , the prime minister of the British Empire from 1874-1880, was reported by Mark Twain to have uttered this brilliant quote on statistical analysis: “There are three kinds of lies: lies, d*** lies, and statistics.”
-Icy

Unfortunately the BBC misattributes the quote but they have an interesting page here on How To Understand Statistics

[jneely]

I totally agree with Lori B. I too find it interesting how numbers (as well as words) can be manipulated to answer an array of questions. Steve has shown in his paper, Liars Figure, and Figures Lie, how data can answer a problem in more than one way. We need to remember this as managers and strive for the truth. A company's growth is dependent on competant forecasting and competant forecasting is dependent the ability to be honest, ethical and truthful in the interpetations of data.