Arima
ARIMA is a statistical time-series model that combines autoregressive terms, differencing, and moving-average terms to represent temporal dependence and generate forecasts.
Statistics Every Programmer Needs
An ARIMA model is an autoregressive integrated moving-average time-series model that represents temporal dependence using autoregression, differencing, and moving averages.
- How it is used
- Forecasts time-ordered data by modeling dependence on past observations and errors after differencing.
- How deep it goes
- Defines the three components, selects an order through stationarity and correlation checks, fits a model, and evaluates residuals and held-out forecasts.
- Examples
- Fits ARIMA(1, 1, 0) to Apple closing prices through March 2024 and compares its April forecast with observed prices.
- What you can do after
- Apply it via Python statsmodels to fit an ARIMA model, forecast held-out observations, and inspect residuals.
Outlier Detection in Python
ARIMA is a time-series forecasting method that models a value using autoregression, differencing, and moving-average error terms.
- How it is used
- Uses forecasting errors to detect outliers in time-series data.
- How deep it goes
- Explains the intuition, fitting workflow, held-out prediction, and tuning need without deriving ARIMA internals.
- Examples
- Uses synthetic weekday-pattern data, a 60-point forecast, plotted quantiles, and a deliberately inserted outlier.
- What you can do after
- Apply it via Darts to fit forecasts, predict a held-out horizon, plot results, and inspect unusually large errors.
Also covered in
- Demand Forecasting Best Practices
- Machine Learning System Design
- Data-Driven Cybersecurity
- Time Series Forecasting Using Foundation Models
- Investing for Programmers
What to know first
- linear regressionLinear regression is a statistical method that models a numeric response as a linear function of one or more predictor variables with fitted parameters.
- overfittingOverfitting is a modeling condition in which a model adapts too closely to particular data, including its noise or idiosyncrasies, and consequently generalizes poorly to new data.
- seasonal patternSeasonality is a recurring pattern of variation in observations associated with regular temporal or calendar periods.
- trendA trend is a developing or persistent direction, pattern, or movement in observations, conditions, behavior, or attention.
Related concepts
- forecastingkind of · Forecasting is the process of predicting future values or outcomes from information available at the time of prediction.
- SARIMAincludes · SARIMA is a seasonal autoregressive integrated moving-average model for forecasting time series with recurring seasonal dependencies.
- generationuses · Generation is the production of an output by a computational model from supplied input or context, often using patterns learned from data.
- autoregressive modelhas part · An autoregressive model represents or predicts each value in a sequence based on preceding values in that sequence.
- integrationhas part · Integration in ARIMA is the differencing operation used to remove nonstationary temporal structure from a time series.
Questions about arima
What is arima?
ARIMA is a statistical time-series model that combines autoregressive terms, differencing, and moving-average terms to represent temporal dependence and generate forecasts.
Which Manning books explain arima?
Statistics Every Programmer Needs and Outlier Detection in Python.
What should I know before learning arima?
Manning books that teach arima usually introduce linear regression, overfitting, seasonal pattern and trend first.
What kinds of arima are there?
Kinds of arima include SARIMA.
What is arima a kind of?
Arima is a kind of forecasting. Forecasting is the process of predicting future values or outcomes from information available at the time of prediction.
What are the parts of arima?
Arima includes autoregressive model, integration and integration component.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.

