# Thread: Another Statistical Question (2000)

1. ## Another Statistical Question (2000)

Hi all,

In a worksheet, I have net sales by week for a restaurant for the year 2001. When charting, which of the trendline options best represent the picture, or indication of what net sales will be in the next year? My first choice was linear, but I am not so sure after looking at the other choices and the graph of the actual sales by week (Sept showed a sharp decline, but Oct bounced right back).

2. ## Re: Another Statistical Question (2000)

Hi Micheal,

You are stepping into the wilderness of extrapolation <g>. Without knowledge of the underlying systematics of the process, or at least some sort of assumed model of how those sales behave normally I would say *any* model would be correct.

That being said I'd suggest you to just try some of them and choose the one that shows the highest R-squared *and* looks most realistic to you. And make sure you cook up a proper disclaimer about the prediction <g>.

3. ## Re: Another Statistical Question (2000)

As Jan Karel told you extrapolation (or forecasting) is a very dangerous thing to do. Just read the words of Mark Twain:

[i]"In the space of one hundred and seventy-six years, the Lower Mississippi has shortened itself two hundred and forty-two miles. This is an average of a trifle over one mile and an third per year. Therefore, any calm person, who is not blind or idiotic, can see that in the Old O

4. ## Re: Another Statistical Question (2000)

Thanks Hans and Jan...will give the quote by Mark Twain to my boss when we begin forecasting sales for the next 12 months! <img src=/S/laugh.gif border=0 alt=laugh width=15 height=15>

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts
•