*Chapter 12*: Working with Time Series Using the Centered Moving Average and a Trending Component

The concept behind making a forecast with a time series is that a factor variable for each period determines whether a trend value goes up or down. The constraint of this prediction is that values must be autocorrelated, meaning that present values are dependent on past values. A prerequisite of making a forecast is a test of autocorrelation, such as the **Durbin-Watson probe** that we reviewed in the previous chapter.

Once we have validated the autocorrelation of data, we smooth the peaks of the periods using the moving average and the **Centered Moving Average** (**CMA**). The distance between the data and the CMA determines the factor that will give the forecast combined with the trend or linear regression of the data.

In this chapter, we will learn how to detect autocorrelation by reviewing the timeline data chart and determining whether it is worth using the Durbin-Watson statistical test...