Which time series analyses are included in Minitab Statistic Software?

Minitab Statistical Software offers several simple forecasting and smoothing methods, correlation analysis methods, and ARIMA modeling techniques to analyze your time series data.
Time series plot
To plot the data in time order to determine whether there is a trend or seasonal pattern, create a time series plot. In Minitab, choose Stat > Time Series > Time Series Plot.
Trend analysis
To fit trend lines using a linear, quadratic, growth, or S curve trend model, perform a trend analysis. In Minitab, choose Stat > Time Series > Trend Analysis.
Decomposition
To fit a model that weights all observations equally to determine the best regression fit, perform a decomposition analysis. Use when your series exhibits a seasonal pattern, with or without a trend. In Minitab, choose Stat > Time Series > Decomposition.
Moving average
To smooth your series using a method that averages recent observations and excludes older observations, use a moving average method. Do not use when your series exhibits a trend. In Minitab, choose Stat > Time Series > Moving Average.
Single exponential smoothing
To smooth your series using a method that gives decreasing weights to older observations when your time series does not exhibit a trend or a seasonal pattern, use a single exponential smoothing method. In Minitab, choose Stat > Time Series > Single Exp Smoothing.
Double exponential smoothing
To smooth your series using a method that gives decreasing weights to older observations when your time series exhibits a trend but not a seasonal pattern, use a double exponential smoothing method. In Minitab, choose Stat > Time Series > Double Exp Smoothing.
Winters' method
To smooth your series using a method that gives decreasing weights to older observations when your time series exhibits a seasonal pattern, with or without a trend, use the Winters' smoothing method. In Minitab, choose Stat > Time Series > Winters’ Method.
Differences
Create a new column of data for custom analyses and plots and store the differences between observations within a series. In Minitab, choose Stat > Time Series > Differences.
Lag
Create a new column of data for custom analyses and plots and shift a series down by a specific number of rows in the worksheet. In Minitab, choose Stat > Time Series > Lag.
Autocorrelation
To measure how well observations at different points time correlate with each other and look for a seasonal pattern, perform an autocorrelation analysis. Use this analysis in conjunction with the Partial autocorrelation function to identify the components for an ARIMA model. In Minitab, choose Stat > Time Series > Autocorrelation.
Partial autocorrelation
To measure how well past observations in a time series correlate with future observations, while accounting for observations that are between the correlation pair, perform a partial autocorrelation analysis. Use this analysis in conjunction with the Autocorrelation function to identify the components for an ARIMA model. In Minitab, choose Stat > Time Series > Partial Autocorrelation.
Cross correlation
To determine whether one series predicts another by plotting the correlations between the two series at different points in time, perform a cross correlation analysis. In Minitab, choose Stat > Time Series > Cross Correlation.
Box-Cox Transformation for Time Series
Use a Box-Cox transformation of a time series to try to make the variance of the series stationary. Stationary variance is a requirement for an ARIMA model. Use a time series plot to determine if the variance of a time series is stationary. If the time series has a pattern in the spread of the points, then the variance is not stationary. In Minitab, choose Stat > Time Series > Box-Cox Transformation.
Augmented Dickey-Fuller Test
Use the augmented Dickey-Fuller test on time series data to determine whether differencing makes the mean of the data stationary. Usually, you use the augmented Dickey-Fuller test to determine the nonseasonal differencing order when you analyze your time series data with an ARIMA model. Use a time series plot to determine if the mean of a time series is stationary. If the time series shows a non-seasonal pattern in the mean, like a trend, then the mean is not stationary. In Minitab, choose Stat > Time Series > Augmented Dickey-Fuller Test.
Forecast with Best ARIMA Model
Use Forecast with Best ARIMA Model to significantly speed up the model identification process by automatically selecting the best ARIMA model from a candidate set with one of the three commonly-used model-selection criteria: Akaike Information Criterion (AIC), Corrected Akaike Information Criterion (AICc), and Bayesian Information Criterion (BIC). In Minitab, choose Stat > Time Series > Forecast with Best ARIMA Model.
ARIMA
To fit a model with autoregressive, difference, and moving average components, perform an ARIMA. To fit an ARIMA model, you must understand the autocorrelation and partial autocorrelation structure of your series. In Minitab, choose Stat > Time Series > ARIMA.