Given this argument, we can conclude that type I and type II errors are, at any point in time, mutually exclusive events.
In hypothesis testing, the probability of type I and type II errors can be simultaneously reduced by increasing the sample size.
Next, we must find the probability of type I and type II errors in each parallel subsystem.
In Table 1 (Set A), I analyze the various R&QA structures first under the assumption that each component has a 15% chance of making type I and type II errors. The original Apollo structure had three serial units, reducing the change of a type I error to a remote .3%.
Type II Errors: Broadening program qualifications (increasing the set of people with standing) has offsetting effects on type I and type II errors. Broader criteria for eligibility should reduce uncompensated valid claims but increase compensated invalid claims.
Type I and Type II Errors: A connection exists between the effective standard of proof and the program's source of funding.
Type I and Type II Errors: Increasing the compensation for successful claims has offsetting effects on type I and type II errors.
In evaluating a compensation system, there are several important empirical magnitudes to consider: (1) the responsiveness of the number of claims filed to changes in the standard of proof, the source of funding, or the level of compensation; (2) the responsiveness of both the plaintiff-borne and defendant-borne costs to changes in program parameters; (3) the responsiveness of type I and type II errors to changes in program parameters; and (4) the responsiveness of employer and employee incentives for investments in safety to changes in program parameters.