bythemark

73 reputation

	73 reputation	bio	website		visits	member for	2 years, 1 month
5 badges		location			seen	42 secs ago

4 Comments

Aug 21	comment	Estimating maximum predictive power in noisy data Bayes error is the right theoretical view, but as noted we cannot know this in real data. There are approaches that try to estimate the noise ceiling from real data, e.g., Quantifying variability in neural responses and its application for the validation of model predictions. Network. 2004. Hsu A, Borst A, Theunissen FE.[link] (ahsu.psychol.ucl.ac.uk/ahsu/papers/quantifying_variability.PDF)
May 20	comment	Transformations of input variables to linearize a regression function Mapping to the cluster mean (numeric) is one possibility. Mapping to cluster ID (discrete category) is another.
May 18	comment	Transformations of input variables to linearize a regression function The terminology may differ between fields; for example, interaction terms could be thought of as 2nd order terms in a Volterra series expansion, which is a nonlinear transformation of the inputs. The response is modeled as a linear combination of the output of the nonlinear basis functions.
May 18	comment	Transformations of input variables to linearize a regression function agreed, I clarified the question asking for any specific examples used in practice