Introduction to Data Science

Time series analysis

Data Obtained from observations collected sequentially over time are common these days. Time is a crucial factor in those data. We observe hourly wind speed, daily high and low temperatures, daily closing stock prices, and yearly sales figures. In biological science, we observe the electrical activity of the heart at millisecond intervals. The list of areas in which time series are studied is virtually endless.

What is time series?

Time series refers to a chain of data points observed and recorded in a time order over a specific period. It represents the output obtained from monitoring and tracking specific events or processes.

The purposes of time series analysis are to understand or model the stochastic mechanism that gives rise to an observed series and to predict or forecast the future values of a series based on the history of that series and, other related series and factors.

A model-building strategy

Finding an appropriate model for given time series is not a trivial task. There are three main steps in the process of time series model building.

1.     Model Specification (or identification)

2. Model fitting

3.     Model diagnostics

Model Specification: The classes of time series models that may be appropriate for a given observed series are selected. In this step, we look at the time plot of the series, compute many different statistics from the data, and apply any knowledge of the subject matter in which data arises.

Common Time series models

AR - Autoregression

MA - Moving Average

ARMA - Autoregressive Moving Average

ARIMA - Autoregressive Integrated Moving Average

ARMAX - Autoregressive Moving Average with exogenous variables

ARIMAX - Autoregressive integrated moving average with exogenous variables

ARCH - Autoregressive conditional heteroskedasticity

We will go through fundamental concepts and each model and more in future blogs.