How to evaluate models : Observed vs. predicted or predicted vs. observed?

By G. Piñeiro, S. Perelman, J. Guerschman, J. Paruelo. 2008

874 citations recorded by the source corpus.

Subfields: Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/96a7a90e0283877444178a1e838696a197d2534c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

Citations in the corpus

Comparison of five modelling techniques to predict the spatial distribution and abundance of seabirds (2012, methodology): “For density models, we used the Pearson correlation coefficient and the slope and intercept of a major axis regression of observed over predicted values to evaluate the bias and consistency of model predictions (Pineiro et al., 2008; Potts and Elith, 2006).”
Performance testing of energy models: are we using the right statistical metrics? (2018, methodology): “Scatter plots of modelled vs. baseline values is a common and reliable way to evaluate model predictions (Piñeiro et al. 2008).”
Increased productivity through integrated soil fertility management in cassava–legume intercropping systems in the highlands of Sud-Kivu, DR Congo (2011, methodology): “the goodness-of-fit was evaluated by comparison against the 1:1 line (Piñeiro et al., 2008).”
Modeling in vitro gas production kinetics: Derivation of Logistic–Exponential (LE) equations and comparison of models (2011, methodology): “The significance of the regression parameters were statistically analyzed to test the hypothesis of ‘slope = 1’ and ‘intercept = 0’ according to Pineiro et al. (2008).”
A distributed brain network predicts general intelligence from resting-state human neuroimaging data (2018, background): “The regression line has a slope close to 1, as expected theoretically [98].”
Predicting the future of species diversity: macroecological theory, climate change, and direct tests of alternative forecasting methods (2009, methodology): “We directly selected among approaches by comparing their predictions of richness in the recent time period to the actual pattern by regressing observed recent richness (dependent variable) against predicted recent richness (independent variable), following Piñeiro et al. (2008).”