Time Series model nugget output

After you create a Time Series model, the following information is available in the Output viewer. Note that there's a limit of 10 models that can be displayed in the Output viewer for Time Series models.

Temporal Information Summary

The summary shows the following information:

  • The Time field
  • The increment
  • The start and end point
  • The number of unique points

The summary applies to all targets.

Model information table

Repeated for each target, the Model information table provides key information about the model. The table always includes the following high-level model settings:
  • The name of the target field that is selected in either the Type node or the Time Series node Fields tab.
  • The model building method - for example, Exponential Smoothing, or ARIMA.
  • The number of predictors input into the model.
  • The number of records that were used to fit the model type. Examples of the different types of models might include: RMSE, MAE, AIC, BIC, and R Square.

In addition, the Ljunq-Box Q statistic might also be shown if your data meets the required conditions. This statistic is not available under the following conditions:

  • If the number of non-missing data points is less than or equal to the number of summation terms desired (fixed at 18).
  • If the number of parameters is greater than or equal to the number of summation terms desired.
  • If the number of summation terms that are computed is less than the smallest acceptable k value (fixed at 7).
  • If the table repeats for each target.

Predictor Importance

Repeated for each target, the Predictor Importance graph shows the importance of the top 10 inputs (predictors) in the model as a bar chart.

If there are more than 10 fields in the chart, you can change the selection of predictors that are included in the chart by using the slider beneath the chart. The indicator marks on the slider are a fixed width, and each mark on the slider represents 10 fields. You can move the indicator marks along the slider to display the next or previous 10 fields, ordered by predictor importance.

You can double-click the chart to open a separate dialog box in which you can edit the graph settings. For example, you can amend items such as the size of the graph, and the size and color of the fonts used. When you close this separate editing dialog box, the changes are applied to the chart that is displayed in the Output tab.

Correlogram

A correlogram, or autocorrelation plot, is shown for each target and shows the autocorrelation function (ACF), or partial autocorrelation function (PACF), of the residuals (the differences between expected and actual values) versus the time lags. The confidence interval is shown as a highlight across the chart.

Parameter Estimates

Repeated for each target, the Parameter Estimates table shows (where applicable) the following details:

  • Target name
  • The transformation applied
  • The lags used for this parameter in the model (ARIMA)
  • The coefficient value
  • The standard error of the parameter estimate
  • The value of the parameter estimate divided by the standard error
  • The significance level for the parameter estimate.