# Example of Predict Taguchi Results

An agricultural engineer studies the effect of five factors on the growth of basil plants. The engineer designs a 2-level Taguchi experiment to determine which factor settings increase the plant's rate of growth without increasing the variability in growth. The engineer also manipulates two noise factors to determine which settings for the five factors increase plant growth across the true range of temperature and humidity conditions.

To increase the plant's rate of growth (slope) without increasing the variability in growth, the engineer chooses the following factor settings:
• Variety, high level
• Light, low level
• Fertilizer, high level
• Water, high level

The engineer does not include Spraying or the interaction terms because they are not significant in the Analyze Taguchi Design results. For more information on the original analysis, go to Example of Analyze Taguchi Design (Dynamic).

1. Open the sample data, BasilGrowth_model.MTW.
2. Choose Stat > DOE > Taguchi > Predict Taguchi Results.
3. Under Predict, deselect Standard deviation and Ln of standard deviation.
4. Click Terms.
5. Verify that A: Variety, B: Light, C: Fertilizer, and D: Water are in Selected Terms. Move E: Spraying and AC from Selected Terms to Available Terms. Click OK. The engineer does not include Spraying or the interaction terms because they were not found to be statistically significant in analysis.
6. Click Levels.
7. Under Method of specifying new factor levels, select Select levels from a list.
8. Complete the Levels, column as shown below.
Factor Levels
Variety 2
Light 1
Fertilizer 2
Water 2
9. Click OK in each dialog box.

## Interpret the results

The predicted values show the fitted values of selected characteristics at the specified factor settings. Use the predicted values to determine which factor settings lead to the best result for your product or process. The fitted values are based on the model that you specified.

In these results, the output shows the predicted values for the signal-to-noise ratio (S/N) and the slope that corresponds to the factor levels that the engineer selected.

The S/N ratio is predicted to be 7.68268 and the slope is predicted to be approximately 0.9935. Next, the engineer plans to run follow-up runs using these factor settings to test the accuracy of the model.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy