Search

The problems of constructing confidence intervals (CIs) for the proportions and functions of proportions in finite populations are considered. For estimating the proportion in a finite population, we propose a CI based on the generalized fiducial method and compare it with an exact CI and score CI. For the two-sample problems, we consider interval estimating the difference between two proportions, the ratio of two proportions and the ratio of odds. Our solutions for the two-sample problems are based on the fiducial approach and the method of variance estimate recovery. All the CIs are evaluated on the basis of their exact coverage probabilities and expected widths. The methods are illustrated using some practical examples. [ABSTRACT FROM AUTHOR]

A low-profile, wideband dual-polarized 1 × 2 multiple-input-multiple-output (MIMO) antenna with frequency selective surface (FSS) decoupling technique is presented. Low profile is realized with two different artificial magnetic conductor (AMC) cells out of which one operates at 3.5 GHz and other with dual band at 3.1 and 4.5 GHz. The proposed antenna height is maintained at 0.125λ0 which is significantly reduced when compared with the conventional perfect electric conductor (PEC) ground plane. Wideband dual polarization is enabled by two pairs of bow-tie antenna elements surrounded by a square ring placed in the orthogonal orientation. To mitigate the near-field coupling in 1 × 2 MIMO an FSS wall is constructed with wide band stop characteristics from 2.85 to 4.75 GHz. Measured results show by inserting FSS wall vertically, coupling reduction is improved by 27 dB over the existing coupling and the antenna exhibits a bandwidth of 57.14% (2.95–4.95 GHz) for VSWR<2 with port isolation of more than 25 dB for entire band of operation. [ABSTRACT FROM AUTHOR]

Methods for computing simultaneous tolerance limits and tolerance intervals (TIs) for several normal populations with a common unknown variance are proposed. We propose numerical methods that determine the confidence coefficient so that the simultaneous TIs include at least specified proportions of the populations with the intended confidence level. The methods are exact and as simple as the existing ones. They are also applicable when sample sizes are unequal and content levels of simultaneous TIs are unequal. Algorithms and R functions are provided to compute factors for constructing simultaneous one-sided tolerance limits, tolerance intervals and equal-tailed tolerance intervals. The methods are illustrated using an example with a real data set. [ABSTRACT FROM AUTHOR]