We propose a Bayesian method to select groups of correlated explanatory variables in a linear regression framework. We do this by introducing in the prior distribution assigned to the regression coefficients a random matrix <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$$G$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <mi>G</mi> </math> </EquationSource> </InlineEquation> that encodes the group structure. The groups can thus be...</equationsource></equationsource></inlineequation>

In DSGE models, fiscal policy is typically described by simple rules in which tax rates respond to the level of output. We show that there is only weak empirical evidence in favor of such specifications in U.S. data. Instead, the cyclical movements of labor and capital income tax rates are...

An efficient algorithm is derived for solving the quantile regression problem combined with a group sparsity promoting penalty. The group sparsity of the regression parameters is achieved by using a <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$$\ell _{1,\infty }$$</EquationSource> <EquationSource Format="MATHML"> <math xmlns:xlink="http://www.w3.org/1999/xlink"> <msub> <mi>ℓ</mi> <mrow> <mn>1</mn> <mo>,</mo> <mi>∞</mi> </mrow> </msub> </math> </EquationSource> </InlineEquation>-norm penalty (or constraint) on the regression...</equationsource></equationsource></inlineequation>

For linear models with a diverging number of parameters, it has recently been shown that modified versions of Bayesian information criterion (BIC) can identify the true model consistently. However, in many cases there is little justification that the effects of the covariates are actually...