Some quality control experiments require destructive sampling in order to measure some particular characteristic of the product. The number of characters printed before a desktop printer fails has been found to be normally distributed. A sample of 15 desktop printers is selected and the number of characters printed (in millions) before each printer fails is recorded. The mean and standard deviation of the number of characters printed by the desktop printers in this sample are calculated in order to build a 99% confidence interval for the mean. State the positive critical value of the test statistic (z or t), exactly as found from the tables (3 decimal places).