Chapter 16

When You’ve Got the Time: Time Series Analysis

In This Chapter

arrow Understanding the properties of a time series

arrow Forecasting a time series with decomposition methods and smoothing techniques

arrow Understanding how a time series may be modeled and forecasted with regression analysis

A time series is a sequence of values observed over a period of time. For example, the daily closing price of IBM stock over the past 30 trading days is a time series. The monthly rainfall in Seattle over the past five years is also a time series, as is the daily price of gold over the past two years.

For many applications, a time series is the most useful organization of data. For example, the properties of a stock could be best analyzed with a time series of historical prices. As another example, you might produce a forecast of the demand for a company’s products, based on the past buying patterns of the company’s customers.

This chapter covers the key statistical features needed to analyze a time series, along with three forecasting techniques: decomposition methods, smoothing techniques, and time series regression.

Key Properties of a Time Series

The properties of a time series may be modeled ...

Get Statistics for Big Data For Dummies now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.