A comparison of two statistical estimators in inverse prediction

Kuo, Ching Chung

doi:10.1504/ijams.2012.046232

Cited by 2 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature regarding this comparison is somewhat underdeveloped, but an understanding of the difference is important. The work of [10,11] and reverse regression, where they point out that the solution of reverse regression is more biased than the solution of inverse regression. While many data scientists naively perform a reverse regression due to the simplicity or due to the lack of awareness of the difference, an inverse regression should be preferred in anticausal prediction problems to minimize the risk of wrong conclusions.…”

Section: Optimal Design For Inverse Predictions: Inverse Vs Reverse R...mentioning

confidence: 99%

Error asymmetry in causal and anticausal regression

2017

View full text Add to dashboard Cite

It is generally difficult to make any statements about the expected prediction error in an univariate setting without further knowledge about how the data were generated. Recent work showed that knowledge about the real underlying causal structure of a data generation process has implications for various machine learning settings. Assuming an additive noise and an independence between data generating mechanism and its input, we draw a novel connection between the intrinsic causal relationship of two variables and the expected prediction error. We formulate the theorem that the expected error of the true data generating function as prediction model is generally smaller when the effect is predicted from its cause and, on the contrary, greater when the cause is predicted from its effect. The theorem implies an asymmetry in the error depending on the prediction direction. This is further corroborated with empirical evaluations in artificial and real-world data sets.

show abstract

Section: Optimal Design For Inverse Predictions: Inverse Vs Reverse R...mentioning

confidence: 99%