Multistage quartile ranked set sampling (MQRSS) method is suggested for estimating the population mean. The MQRSS is compared with the simple random sampling (SRS), ranked set sampling (RSS) suggested by McIntyre (1952) and quartile ranked set sampling (QRSS) suggested by Muttlak (2003) based on the same sample size. We show that MQRSS estimator is an unbiased of the population mean and more efficient than SRS, QRSS and RSS (r > 1, r is the number of stage) when the underlying distribution is symmetric about its mean. Also, by MQRSS we can increase the efficiency of mean estimator for specific value of the sample size. For asymmetric distributions considered in this study, MQRSS estimator has a smaller bias. A collection of a real data is used to illustrate the method.