Strong Nonlinear Correlations, Conditional Entropy and Perfect Estimation

Jones, Christopher S.; Finn, John M.; Hengartner, Nicolas
November 2007
AIP Conference Proceedings;11/13/2007, Vol. 954 Issue 1, p293
Academic Journal
This paper deals with parameter estimation in which measurements subjected to highly correlated noise allow for very accurate estimation. For linear regression with normally distributed noise, this generically occurs when the noise becomes highly linearly correlated. For a linear model with nonnormal noise distributions, there may exist nonlinear regressions that allow for accurate estimation if a conditional entropy is small (analogous to linear correlations in the normal case approaching ±1.) Nonlinear regression may also yield an accurate estimate if a nonlinear model is subjected to strongly linearly correlated noise.


Related Articles

  • Application of linear stochastic models for drought forecasting in the Büyük Menderes river basin, western Turkey. Durdu, Ömer // Stochastic Environmental Research & Risk Assessment;Dec2010, Vol. 24 Issue 8, p1145 

    In the present study, a seasonal and non-seasonal prediction of the Standardized Precipitation Index (SPI) time series is addressed by means of linear stochastic models. The methodology presented here is to develop adequate linear stochastic models known as autoregressive integrated moving...

  • Comparison of catchment grouping methods for flow duration curve estimation at ungauged sites in France. Sauquet, E.; Catalogne, C. // Hydrology & Earth System Sciences Discussions;2011, Vol. 8 Issue 2, p3233 

    The study aims at estimating flow duration curves (FDC) at ungauged sites in France and quantifying the associated uncertainties using a large dataset of 1080 FDCs. The interpolation procedure focuses here on 15 percentiles standardised by the mean annual flow, which is supposed to be known at...

  • A NOTE ON TWO CURIOSITIES IN LINEAR REGRESSION. Poirier, Dale J. // American Economist;Spring78, Vol. 22 Issue 1, p77 

    Focuses on two relationships involving alternative estimators of beta in linear regression. Condition for the operationality of the linear estimator of beta with minimum mean square error; Approaches in dealing with unknown parameters.

  • Generalized empirical likelihood methods for analyzing longitudinal data. SUOJIN WANG; LIANFEN QIAN; CARROLL, RAYMOND J. // Biometrika;Mar2010, Vol. 97 Issue 1, p79 

    Efficient estimation of parameters is a major objective in analyzing longitudinal data. We propose two generalized empirical likelihood-based methods that take into consideration within-subject correlations. A nonparametric version of the Wilks theorem for the limiting distributions of the...

  • Difference-based ridge estimator of parameters in partial linear model. Tabakan, Gülin; Akdeniz, Fikri // Statistical Papers;Jun2010, Vol. 51 Issue 2, p357 

    The paper introduces a new difference-based ridge regression estimator $${\hat{\beta}(k)}$$ of the regression parameters β in the partial linear model. Its mean-squared error is compared analytically with the non-ridge version $${\hat{\beta}(0)}$$ . Finally, the performance of the new...

  • Improved Liu-Type Estimator of Parameters in Two Seemingly Unrelated Regressions. Jibo Wu // ISRN Otolaryngology;2014, p1 

    We consider the parameter estimation in two seemingly unrelated regression systems. To overcome the multicollinearity, we propose a Liu-type estimator in seemingly unrelated regression systems. The superiority of the new estimator over the classic estimator in the mean square error is discussed...

  • ALTERNATIVES FOR PUBLISHED AND CALCULATED BETA ESTIMATES. Balyeat, R. Brian; Cagle, Julie A. B.; Phan, Long // Journal of International Finance Studies;2011, Vol. 11 Issue 3, p110 

    Students and practitioners frequently use published betas rather than calculating their own betas. This paper documents that betas from Yahoo!, MSNBC and Value Line are inconsistent across the three sources. This variation is frequently significant and our results indicate the differences are...

  • PENALIZED LEAST SQUARES FOR SEMIPARAMETRIC REGRESSION. Wibowo, Wahyu; Haryatmi, Sri; Budiantara, Nyoman // International Journal of Academic Research;Nov2012, Vol. 4 Issue 6, p274 

    Semiparametric regression model contained both parametric and nonparametric components. Since spline function was used for nonparametric component, it obtained spline semiparametric regression. There were many points of view about the model to estimate parameter. This paper discussed the...

  • Unbiased Quasi-regression*. Guijun Yang; Lu Lin; Runchu Zhang // Chinese Annals of Mathematics;Apr2007, Vol. 28 Issue 2, p177 

    Quasi-regression, motivated by the problems arising in the computer experiments, focuses mainly on speeding up evaluation. However, its theoretical properties are unexplored systemically. This paper shows that quasi-regression is unbiased, strong convergent and asymptotic normal for parameter...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics