Building efficient sampling procedures to provide more accurate results with small sample sizes is one of the main goals in sampling surveys. The ranked set sampling (RSS) is a well‐known procedure for selecting representative samples and improving parametric estimation by employing ranking on observations. In order to have a more efficient sampling procedure, new sampling procedures are proposed and investigated in this article. The main focus of this article is to enhance the mean estimation of the study population using the proposed RSS procedures. The performance of the proposed sampling procedures is compared with their competitors in RSS, double RSS (DRSS), extreme RSS (ERSS), and double extreme RSS (DERSS) by conducting simulation studies for numerous (symmetric and asymmetric) distributions. An application to a real dataset is also considered to exemplify the achievement of the proposals. Numerical simulations show that the new modified estimators are unbiased for the population mean for symmetric distributions and they outperform their competitors in most of the cases investigated in this article.