Near-Threshold Voltage Design in Nanoscale CMOS

Summary form only given. New technologies have led to an “explosion” of data available to document states and processes in very many fields. Tools of data mining are being used to extract relevant information. If this information is used in decision making, analytical statistics can provide formal tests comparing the outcomes of different scenarios. Statistics has traditionally dealt with limited information, both in terms of observations and numbers of variables explaining the states of these observations. Virtually all statistical hypothesis testing was developed for such scenarios, trying to make sense from limited data, often expensive to produce. Clinical trials and the steps in development of drugs before those clinical trials are a typical examples from human medicine.