Question

1. What is a ACF chart telling you?
2. How would you interpret the chart and its numbers?
3. How will this information help you to select the best forecasting model from the chapter 3 models we discussed in class?

Answer 1

Answer:

A correlogram (also called Auto correlation Function ACF plot ) is a visual way to show serial correlation in data that changes over time (i.e time series data) Serial Correlaion (also called autocorrelation) is where an error at one point in time travels to a subsequent point in time.

ACF is an auto-correlation function which gives us value of auto - correlation of any series with its lagged values. ACF considers all these components while finding correlation hance it's a complete auto-correlation plot. PACF is a partial auto-correlation function.

Reading ACF and PCF plots

• The negative values in the plot respond to a process of the form yt=k-t-1+t.
• In this example the ACF is significant in the first and second lags, while the Pacf follows a geaometry decay.
• Here the ACF deas geomatricall, and the pacf shows only one significant lag.