Multivariate dependence of spacings of generalized order statistics

Multivariate dependence of spacings of generalized order statistics is studied. It is shown that spacings of generalized order statistics from DFR (IFR) distributions have the CIS (CDS) property. By restricting the choice of the model parameters and strengthening the assumptions on the underlying distribution, stronger dependence relations are established. For instance, if the model parameters are decreasingly ordered and the underlying distribution has a log-convex decreasing (log-concave) hazard rate, then the spacings satisfy the MTP2 (S- MRR2) property. Some consequences of the results are given. In particular, conditions for non-negativity of the best linear unbiased estimator of the scale parameter in a location-scale family are obtained. By applying a result for dual generalized order statistics, we show that in the particular situation of usual order statistics the assumptions can be weakened.primary, 60E15 secondary, 62G30, 62H05, 62N02 Spacings of generalized order statistics Multivariate total positivity Strongly multivariate reverse regular rule Conditionally increasing in sequence Negative and positive orthant dependence Right tail increasing in sequence Increasing failure rate Reversed hazard rate Non-negativity of BLUE Dual generalized order statistics