Hypothesis testing for the inverse Gaussian distribution mean based on ranked set sampling

In this study, the hypothesis test for the population mean of inverse Gaussian distribution using ranked set sampling is considered when the scale parameter is both known and unknown. In order to obtain critical values, a simulation study is conducted for different sample sizes and significance levels. Also, power comparisons are made between ranked set sampling and simple random sampling for the inverse Gaussian distribution. The simulation results show that ranked set sampling performs much better compared to simple random sampling when the underlying distribution is inverse Gaussian.