I’ve tried a few forecasts with the Forecast Package but irrespective of the number of observations it appears that the last observed value has a dramatic impact on the results.

Just a short example with a few observations. This are revenues of an IT&S company with no seasonality impact.

The company had a fantastic 2015 result but in the recent history the numbers showed some volatility.

Hence I was wondering what the Forecast Package would come up with.

a=ts(c(3006,3658,3712,3575,3228,3845,4362), frequency = 1, start = c(2008, 2))

plot(forecast(a,h=5,level=c(80,95)),main=”XY 5 Year Forecast”)

Now, let’s assume the company did improve the numbers in 2015 but just on a more modest basis to let’s say 3900.

a=ts(c(3006,3658,3712,3575,3228,3845,3900), frequency = 1, start = c(2008, 2))

plot(forecast(a,h=5,level=c(80,95)),main=”XY 5 Year Forecast”)

Now, have a look at the 5 year Forecast. Revealing, isn’t it!

*Related*

To

**leave a comment** for the author, please follow the link and comment on their blog:

** Copula**.

R-bloggers.com offers

**daily e-mail updates** about

R news and

tutorials on topics such as:

Data science,

Big Data, R jobs, visualization (

ggplot2,

Boxplots,

maps,

animation), programming (

RStudio,

Sweave,

LaTeX,

SQL,

Eclipse,

git,

hadoop,

Web Scraping) statistics (

regression,

PCA,

time series,

trading) and more...

If you got this far, why not

__subscribe for updates__ from the site? Choose your flavor:

e-mail,

twitter,

RSS, or

facebook...