Root mean squared error

The square root of the average squared forecast error. Squaring weights large errors heavily; the model with the lower value out of sample is preferred. Also used to judge models with continuous targets.

Where you will meet it

Root mean squared error appears in 3 learning outcomes on the CFA syllabus. A few of them:

• Distinguish forecasts made within the sample from those made outside it, and rank time-series models by forecast accuracy using root mean squared error
  CFA Level II · Quantitative Methods

  “Forecasting accuracy is compared with root mean squared error: square each forecast error, average the squares, and take the square root.”

• Choose a suitable time-series model for a given investment problem and give reasons for the choice
  CFA Level II · Quantitative Methods

  “Finally compare models on out-of-sample RMSE.”

• Judge how well a machine learning algorithm fits
  CFA Level II · Quantitative Methods

  “For continuous targets, root mean squared error is the usual measure.”

Practise it

• Today's practice question One question, with every wrong option explained.
• Free Level I diagnostic test Twelve questions that show which topics to start with.
• Free finance calculators Check your arithmetic on the exam's core formulas.

All terms beginning with R · Glossary