Data Envelopment Analysis (DEA), an efficiency measurement and benchmarking technique originated in 1978 with the publication of the seminal paper of Charnes et al (1978) has evolved into an important technique over the years. This paper attempts to critically review the various methodological aspects of DEA for application in any domain in the public or private sectors. In specific it reviews some of the important literature available on a) variable selection methods in DEA, b) Sensitivity analysis and ranking of DMUs and c) some of the applications it has been put into over the last four decades. The focus is on specific practical aspects of applying DEA in any particular field.