Time Series Analysis in Python
In this four-hour course, you’ll learn the basics of analyzing time series data in Python.
Start Course for FreeCreate Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.Loved by learners at thousands of companies
Course Description
Learn How to Use Python for Time Series Analysis
From stock prices to climate data, you can find time series data in a wide variety of domains. Having the skills to work with such data effectively is an increasingly important skill for data scientists. This course will introduce you to time series analysis in Python.After learning what a time series is, you'll explore several time series models, ranging from autoregressive and moving average models to cointegration models. Along the way, you'll learn how to estimate, forecast, and simulate these models using statistical libraries in Python.
You'll see numerous examples of how these models are used, with a particular emphasis on applications in finance.
Discover How to Use Time Series Methods
You’ll start by covering the fundamentals of time series data, as well as simple linear regression. You’ll cover concepts of correlation and autocorrelation and how they apply to time series data before exploring some simple time series models, such as white noise and a random walk. Next, you’ll explore how autoregressive (AR) models are used for time series data to predict current values and how moving average models can combine with AR models to produce powerful ARMA models.Finally, you’ll look at how to use cointegration models to model two series jointly before looking at a real-life case study.
Explore Python Models and Libraries for Time Series Analysis By the end of this course, you’ll understand how time series analysis in Python works. You’ll know about some of the models, methods, and libraries that can assist you with the process and will know how to choose the appropriate ones for your own analysis.
This course is part of a wider Time Series with Python Track, which provides a set of five courses to help you master this data science skill.
- 1
Correlation and Autocorrelation
FreeIn this chapter you'll be introduced to the ideas of correlation and autocorrelation for time series. Correlation describes the relationship between two time series and autocorrelation describes the relationship of a time series with its past values.
Introduction to Course50 xpA "Thin" Application of Time Series100 xpMerging Time Series With Different Dates100 xpCorrelation of Two Time Series50 xpCorrelation of Stocks and Bonds100 xpFlying Saucers Aren't Correlated to Flying Markets100 xpSimple Linear Regression50 xpLooking at a Regression's R-Squared100 xpMatch Correlation with Regression Output50 xpAutocorrelation50 xpA Popular Strategy Using Autocorrelation100 xpAre Interest Rates Autocorrelated?100 xp - 2
Some Simple Time Series
In this chapter you'll learn about some simple time series models. These include white noise and a random walk.
Autocorrelation Function50 xpTaxing Exercise: Compute the ACF100 xpAre We Confident This Stock is Mean Reverting?100 xpWhite Noise50 xpCan't Forecast White Noise100 xpRandom Walk50 xpGenerate a Random Walk100 xpGet the Drift100 xpAre Stock Prices a Random Walk?100 xpHow About Stock Returns?100 xpStationarity50 xpIs it Stationary?50 xpSeasonal Adjustment During Tax Season100 xp - 3
Autoregressive (AR) Models
In this chapter you'll learn about autoregressive, or AR, models for time series. These models use past values of the series to predict the current value.
Describe AR Model50 xpSimulate AR(1) Time Series100 xpCompare the ACF for Several AR Time Series100 xpMatch AR Model with ACF50 xpEstimating and Forecasting AR Model50 xpEstimating an AR Model100 xpForecasting with an AR Model100 xpLet's Forecast Interest Rates100 xpCompare AR Model with Random Walk100 xpChoosing the Right Model50 xpEstimate Order of Model: PACF100 xpEstimate Order of Model: Information Criteria100 xp - 4
Moving Average (MA) and ARMA Models
In this chapter you'll learn about another kind of model, the moving average, or MA, model. You will also see how to combine AR and MA models into a powerful ARMA model.
Describe Model50 xpSimulate MA(1) Time Series100 xpCompute the ACF for Several MA Time Series100 xpMatch ACF with MA Model50 xpEstimation and Forecasting an MA Model50 xpEstimating an MA Model100 xpForecasting with MA Model100 xpARMA models50 xpHigh Frequency Stock Prices100 xpMore Data Cleaning: Missing Data100 xpApplying an MA Model100 xpEquivalence of AR(1) and MA(infinity)100 xp - 5
Putting It All Together
This chapter will show you how to model two series jointly using cointegration models. Then you'll wrap up with a case study where you look at a time series of temperature data from New York City.
Cointegration Models50 xpA Dog on a Leash? (Part 1)100 xpA Dog on a Leash? (Part 2)100 xpAre Bitcoin and Ethereum Cointegrated?100 xpCase Study: Climate Change50 xpIs Temperature a Random Walk (with Drift)?100 xpGetting "Warmed" Up: Look at Autocorrelations100 xpWhich ARMA Model is Best?100 xpDon't Throw Out That Winter Coat Yet100 xpCongratulations50 xp
In the following tracks
Time Series with PythonCollaborators
Prerequisites
Manipulating Time Series Data in Python
Rob Reider
Consultant at Quantopian and Adjunct Professor at NYU
Rob is an Adjunct Professor at NYU's Courant Institute where he co-teaches a course on Times Series Analysis and Statistical Arbitrage. He is also currently a Consultant to Quantopian. He has been a Portfolio Manager for over 15 years at Millennium Partners, JPMorgan, and Visium Asset Management. Rob received his Ph.D. in Finance from Wharton.
What do other learners have to say?
FAQs
Join over 11 million learners and start Time Series Analysis in Python today!
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.