Results 241 to 250 of about 4,395,518 (296)
Some of the next articles are maybe not open access.
2017
This chapter deals with the most relevant multi-dimensional random effects panel data models, where, unlike the case of fixed effects, the number of parameters to be estimated does not increase with the sample size. First, optimal (F)GLS estimators are presented for the textbook-style complete data case, paying special attention to asymptotics.
Balazsi, Laszlo +3 more
openaire +2 more sources
This chapter deals with the most relevant multi-dimensional random effects panel data models, where, unlike the case of fixed effects, the number of parameters to be estimated does not increase with the sample size. First, optimal (F)GLS estimators are presented for the textbook-style complete data case, paying special attention to asymptotics.
Balazsi, Laszlo +3 more
openaire +2 more sources
A note regarding ‘random effects’
Statistics in Medicine, 2014zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire +3 more sources
Fixed Effects and Random Effects
2008One of the major benefits from using panel data as compared to cross-section data on individuals is that it enables us to control for individual heterogeneity. Not controlling for these unobserved individual specific effects leads to bias in the resulting estimates.
openaire +1 more source
2002
Abstract Chapter 8 has dealt with marginal models whose regression parameters have population average interpretations. In this chapter we consider random effects models in which the regression coeficients measure the more direct infiuence of explanatory variables on the responses for heterogeneous individuals.
Peter J Diggle +3 more
openaire +1 more source
Abstract Chapter 8 has dealt with marginal models whose regression parameters have population average interpretations. In this chapter we consider random effects models in which the regression coeficients measure the more direct infiuence of explanatory variables on the responses for heterogeneous individuals.
Peter J Diggle +3 more
openaire +1 more source
Effective Properties of Random Composites
SIAM Journal on Scientific Computing, 2004Summary: We propose a new concept of effective properties of composites with uncertain spatial arrangements of constitutive materials and within-material properties. Rather than replacing a heterogeneous property with a constant effective parameter, we seek to preserve the internal macrostructure of a composite.
TARTAKOVSKY D. M., GUADAGNINI, ALBERTO
openaire +3 more sources
2009
Abstract In Chapter 5 we found overdispersion in the fabric fault data; the Poisson GLM did not fit or represent the data adequately. The failure of a generalized linear model to fit may be due to several causes. The distribution of Y may not be the specified exponential family member, or the regression model fitted may be mis-specified.
Murray Aitkin +3 more
openaire +1 more source
Abstract In Chapter 5 we found overdispersion in the fabric fault data; the Poisson GLM did not fit or represent the data adequately. The failure of a generalized linear model to fit may be due to several causes. The distribution of Y may not be the specified exponential family member, or the regression model fitted may be mis-specified.
Murray Aitkin +3 more
openaire +1 more source
Fixed- and Random-Effects Models
2021Deciding whether to use a fixed-effect model or a random-effects model is a primary decision an analyst must make when combining the results from multiple studies through meta-analysis. Both modeling approaches estimate a single effect size of interest.
openaire +2 more sources
2005
Abstract In Chapter 5 we found overdispersion in the fabric fault data; the Poisson GLM did not fit or represent the data adequately. The failure of a GLM to fit may be due to several causes. The distribution of Ymay not be the specified exponential family member, or the regression model fitted may be mis-specified.
Murray Aitkin, Brain Francis, John Hinde
openaire +1 more source
Abstract In Chapter 5 we found overdispersion in the fabric fault data; the Poisson GLM did not fit or represent the data adequately. The failure of a GLM to fit may be due to several causes. The distribution of Ymay not be the specified exponential family member, or the regression model fitted may be mis-specified.
Murray Aitkin, Brain Francis, John Hinde
openaire +1 more source
Nature, 1969
The appearance of circular Moire fringes when a random dot pattern is superimposed on itself provides new evidence that the human visual process may include the computation of local autocorrelations by excitation of line detectors.
openaire +2 more sources
The appearance of circular Moire fringes when a random dot pattern is superimposed on itself provides new evidence that the human visual process may include the computation of local autocorrelations by excitation of line detectors.
openaire +2 more sources
Random Effects, Fixed Effects, Convolution, and Separation
Econometrica, 1981Mundlak, Yair, Yahav, Joseph A
openaire +2 more sources