A Decision Analytic Approach to Determining Sample Sizes in A Phase III Program
- PDF / 656,218 Bytes
- 13 Pages / 504 x 719.759 pts Page_size
- 76 Downloads / 167 Views
Drug Informution Journal. Vol. 34, pp. 365-311. 2000 Printed in the USA. All rights reserved.
A DECISION ANALYTIC APPROACH TO DETERMINING SAMPLE SIZES IN A PHASE I11 PROGRAM ALLANPALLAY,MS Department of Clinical Biostatistics, Wyeth-Ayerst Research, Philadelphia, Pennsylvania
In this paper we present a decision analytic approach to determining sample size in a set of Phase I l l drug eflcacy trials sponsored by a pharmaceutical company. In this approach we built a model to predict the expected netpresent value of the drug at varying sample sizes. We then chose the sample size that maximizes that value. We took into consideration effects that sample size had on the probability of approval, the cost of the studies, the time it takes the drug to reach the market, and a variety of other factors. We found that increasing the sample size increases the chance that the drug will be approved. On the other hand increasing the sample size increases the cost of the studies and the time it will take for the drug to reach the market. The model weighs these factors to produce the expected net present value. Key Words: Decision analysis; Sample size; Pharmaceutical industry
INTRODUCTION WE PRESENT A DECISION analytic approach to determining the sample size in a set of Phase I11 efficacy drug trials sponsored by a pharmaceutical company. This approach involves building a model using clinical trials data and postapproval behavior of the market, and using this model to predict the expected net present value (ENPV) of the drug at varying sample sizes. We then chose the sample size that maximized that value. (The ENPV is the current monetary value of a cash payment which will be received at some time in the future. X amount of dollars to be received in the future is worth less than the same amount of money received today because present cash can be invested to increase its value. A present value algorithm deter-
Reprint address: Allan Pallay, MS,Department of Clinical Biostatistics, Wyeth-Ayerst Research, P.O. Box 42528. Philadelphia, PA 19101. E-mail: pallaya8war. wyeth.com.
mines how much a future cash payment is worth in dollars that are received today. The net present value subtracts out any costs associated with receiving the cash payment. An expected net present value multiplies the net present value by the probability that the money will actually be received.) In the model, we considered the effects of sample size on the probability of approval, the cost of the studies, the time it takes the drug to reach the market, and a variety of other factors. Cost and time to market are important factors that affect the ENPV and are affected by sample size, but are not taken into consideration in the usual statistical method of determining sample size. Although the importance of the cost of the studies, the time to market, and the probability of approval are intuitively clear, it is not clear how to weigh them in arriving at a sample size. For this reason a decision analytic model is very useful. Decision theoretic approaches to deter
Data Loading...
