How to get the most accurate trending

**coolzero** · 07-21-2010, 12:54 PM

Hello guys,

I just want to know if there's a way better way than getting the average to get the trending for 4 weeks trending based on AHT values? The format would be h:mm.

Thanks.

**shg** · 07-21-2010, 01:04 PM

Moving average?

**coolzero** · 07-21-2010, 04:14 PM

Given 4 weeks data of AHT, what would be the AHT for the 5th week?

**shg** · 07-21-2010, 04:17 PM

The average of the last seven days?

**coolzero** · 07-21-2010, 04:34 PM

yes, what would be for 5th week?

**shg** · 07-21-2010, 04:37 PM

=average(a22:a28)

**coolzero** · 07-21-2010, 04:42 PM

so, its just the average?

**shg** · 07-21-2010, 05:23 PM

I'm sorry, I don't know what you're data looks like or what you're trying to do.

You can plot the data and add a trendline (linear or moving average), or use the SLOPE function to get the slope of the linear trendline, or ...

What is the question you're trying to answer with the data?

**coolzero** · 07-22-2010, 02:20 PM

for example i have 5, 9, 2, 6 for 4 days respectively. and i would like to assume what is the value for the 5 day? how could i get it?

**shg** · 07-22-2010, 03:09 PM

Look at the TREND and FORECAST functions. If you need further help, post an example workbook and explain in context.

**coolzero** · 07-22-2010, 03:21 PM

Shown below is a part of the data. I'm trying to use TREND and FORECAST even before i post a question in this forum but i'm getting #N/A value. Could you fill me in with these two? Thank you for your time...

Date Ave. Handling Time
13-Jun-10 4:25
20-Jun-10 4:29
27-Jun-10 4:57
04-Jul-10 4:54
11-Jul-10 ?

**shg** · 07-22-2010, 03:32 PM

Could you *please* post a workbook as an example?

**coolzero** · 07-22-2010, 03:57 PM

Please see attached file. That's what i currently have and i believe you could give me much better figures using the two formulas you gave.

Thank you...

**shg** · 07-22-2010, 04:29 PM

See J38 in attachment.

**ChemistB** · 07-22-2010, 05:12 PM

Your correlation coefficient is 0.111. Pretty poor linearity. kinda like throwing darts at a dartboard.

**shg** · 07-22-2010, 05:16 PM

An excellent point. The numbers are very noisy -- it would be more meaningful to look at the trend over a period of months, accounting for seasonal variation.