we develop a two phase sampling procedure to determine the sample size necessary to estimatethe population mean of a normally distributed random variable and show that the resulting estimator has preassigned variance and is unbiased under a regular condition. we present a necessary and sufficient condition under which the final sample mean is an unbiased estimator for the population mean.

Abstract Adjusted plus-minus (APM) can sometimes lack common sense. This happens, for instance, when mediocre players move into the top ten, and superstars fall out of 100. These occasional outliers hurt credibility APM, mask benefits, such as increased prediction accuracy. We address this problem with a new method, called Augmented APM. APM incorporates external player ratings methodology. The...

Traditional data envelopment analysis (DEA) models evaluate two-stage decision making unit (DMU) as a black box and neglect the connectivity may exist among the stages. This paper looks inside the system by considering the intermediate activities between the stages where the first stage uses inputs to produce outputs which are the inputs to the second stage along with its own inputs. Additional...