Interval estimation for the shape and scale parameters of the Birnbaum-Saunders distribution (Q2010175)

The two-parameter Birnbaum-Saunders distribution has probability density function \[ f(t)=\frac{1}{2\alpha\beta\sqrt{2\pi}}\left[\left(\frac{\beta}{t}\right)^{1/2}+\left(\frac{\beta}{t}\right)^{3/2}\right]\exp\left\{-\frac{1}{2\alpha^2}\left(\frac{t}{\beta}+\frac{\beta}{t}-2\right)\right\}\,, \] for \(t>0\), where \(\alpha>0\) and \(\beta>0\) are parameters. The authors propose two techniques for the construction of confidence intervals for these two parameters. The first is based on a generalized pivotal approach, and the second on the percentile bootstrap. Numerical studies compare these two approaches with others available in the literature.