Advent of Code is back! Unwrap daily challenges to sharpen your Alteryx skills and earn badges along the way! Learn more now.
Free Trial

Alteryx Designer Desktop Discussions

Find answers, ask questions, and share expertise about Alteryx Designer Desktop and Intelligence Suite.
SOLVED

Forcasting

Feras95p
8 - Asteroid

Dear all,

 

I have attached one workflow with a solution, but I need your help to give me in a simple way what does the percentage value of the larger confidence interval mean?

Also what does the percentage value of the smaller confidence interval mean?

t.PNG5.PNG

 

Also in the output what does the forecast high 95/80 and low 95/80  I don't understand the meaning.

 

So any help in that?

3 REPLIES 3
ImadZidan
12 - Quasar

Hello @Feras95p ,

 

My take on it and simply put. first two terms:

 

population: your whole data

Sample: is a proportion of your data.

 

95% represents the certainty that you have included a good range of your data to perform the prediction. in your case 95% confidence interval is basically telling that you can be certain your the sample included in the calculation represents 95% of the true mean of the population.

 

the higher the confidence, the more representative of your data.

 

hope this helps.

Feras95p
8 - Asteroid

@ImadZidan  Thanks for replying !

 

Still I'm confuse about the output I have 7 output  what are the difference between each! 

ImadZidan
12 - Quasar

Hello @Feras95p ,

 

Fair enough.

 

Your configuration shows that you want to forecast 6 periods a head using two confidence intervals 95% and 80%.

 

Now, the I would read the result is as follows:

 

1- For period 3 that I have in my dataset, the result is showing 6 periods which I have specified in my configuration 6 periods.

2- the output is showing the forecast value which is the expected value which looking at the first record is 344.738

3- the output is also showing the likely that the expected value will fall in the range of the confidence interval

 

In other words. and the first record as an example;

 

The 95% prediction interval suggested that the real observation was highly likely to fall within the range of values between

202.937 and 466.538

 

The 80% prediction interval suggested that the real observation was highly likely to fall within the range of values between

248.558 and 420.918.

 

I hope this makes sense.

Labels
Top Solution Authors