Using two or three different modeling techniques on the same data and then comparing predicted outcomes across the different models is called ________.

• A. Triangulation
• B. Ensemble
• C. Cross-Validation
• D. Sampling

Answer: (A)

Triangulation is the practice of applying multiple modeling techniques to the same dataset and then comparing the results to see if they tell the same story. This approach strengthens confidence in findings because it shows whether conclusions hold across different assumptions and methods, rather than depending on a single model.

It differs from ensemble methods, which combine the outputs of several models to produce one final prediction. It also differs from cross-validation, which focuses on how well a single model generalizes by testing it on held-out data, and from sampling, which is about selecting a subset of data for analysis. For example, you might fit a linear regression, a decision tree, and a neural network on the same data and compare their predictions to assess robustness.