شماره ركورد كنفرانس :
3140
عنوان مقاله :
Shannon Information for Expected Net Gain of Sampling
عنوان به زبان ديگر :
Shannon Information for Expected Net Gain of Sampling
پديدآورندگان :
Pezeshk Hamid نويسنده School of Mathematics - Statistics and Computer Science - University of Tehran - and Institute for Research in Fundamental Sciences (IPM) - Tehran - Iran , Maroufoy Vahed نويسنده Department of Statistics and Actuarial Science - University of Waterloo - Ontario - Canada
كليدواژه :
Expected Net Gain of Sampling , Shannon information , Clinical trial , Bayesian approach , The Monte Carlo method
عنوان كنفرانس :
يازدهمين كنفرانس آمار ايران
چكيده لاتين :
The expected net gain of sampling. ENGS. is the difference between the expected value of sample information, EWSI. and the cost of Sampling. In this work we use the concept of the Shannon information to define the ENGS. Maximizing the ENGS, the optimal size of a clinical trial will be obtained. The parameter of interest is the difference between two sucécess probabilities of two binomial distributions. Å Bayesiain framework wi be considered. A Dirichlet prior distribution is assumed. To reduce the c putational complexity concerned with sample size determination we use the Monte Carlo Markov Chain. MCMC. method.
شماره مدرك كنفرانس :
4219389
