0
Regression Target – Objective Function

Excerpt

Most engineering or science models provide a continuous-valued, deterministic response. These could either represent steady-state or transient phenomena. In contrast, models could predict a classification (nominal, class, text, or string variable) or a rank, but still a deterministic value. Alternately, Monte Carlo simulations predict a stochastic outcome, a range of possibilities, not a definitive value. There are diverse options to what you may be seeking to best fit, and you need to understand the application to choose the regression target.

7.1Introduction
7.2Experimental and Measurement Uncertainty – Static and Continuous Valued
7.3Likelihood
7.4Maximum Likelihood
7.5Estimating σx and σy Values
7.6Vertical SSD – A Limiting Consideration of Variability Only in the Response Measurement
7.7r-Square as a Measure of Fit
7.8Normal, Total, or Perpendicular SSD
7.9Akaho’s Method
7.10Using a Model Inverse for Regression
7.11Choosing the Dependent Variable
7.12Model Prediction with Dynamic Models
7.13Model Prediction with Classification Models
7.14Model Prediction with Rank Models
7.15Probabilistic Models
7.16Stochastic Models
7.17Takeaway
Exercises

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In