Bootstrap estimation of sound power level determined by the survey method

The possibility of using the bootstrap method to determine the sound power level for the survey method was presented in this paper. Minimum values of the bootstrap algorithm input parameters have been determined for the estimation of sound power level. Two independent simulation experiments have been performed for that purpose. The first experiment served to determine the impact of the original random sample size, and the second to determine the impact of a number of the bootstrap replications on the accuracy of estimation of sound power level. The inference has been carried out based on the results of non-parametric statistical tests at significance level α = 0.05. The statistical analysis has shown that the minimum size of the original random sample n used to estimate the value of sound power level should be 4 elements for the survey method. The minimum number of bootstrap replications necessary for the estimation of sound power level should be B = 5100. The study on the usefulness and effectiveness of the bootstrap method in the determination of sound power level in real-life situation was carried out with the use of data representing actual results. The data used to illustrate the proposed solutions and carry out the analysis were the results of sound power levels of reference sound power source B&K 4205 were used.