Time Series Analysis in Statistical Analysis of Big Data

By Alan Anderson, David Semmelroth

A time series is a set of observations of a single variable collected over time. With time series analysis, you can use the statistical properties of a time series to predict the future values of a variable. There are many types of models that may be developed to explain and predict the behavior of a time series.

The following are examples of time series:

  • The daily price of Apple stock over the past ten years.

  • The value of the Dow Jones Industrial Average at the end of each year for the past 20 years.

  • The daily price of gold over the past six months.

One place where time series analysis is used frequently is on Wall Street. Some analysts attempt to forecast the future value of an asset price, such as a stock, based entirely on the history of that stock’s price. This is known as technical analysis. Technical analysts do not attempt to use other variables to forecast a stock’s price — the only information they use is the stock’s own history.

Technical analysis can work only if there are inefficiencies in the market. Otherwise, all information about a stock’s history should already be reflected in its price, making technical trading strategies unprofitable.