Effect of resolution of measurements in the behavior of exponentially weighted moving average control charts.

Unlabelled: Process behavior is known through measurement. All measurements are discrete and transform a continuous process distribution into a discrete (multinomial) measurement distribution. In this article, properties of exponentially weighted moving average control charts (EWMA charts) of measurements are studied through Monte Carlo simulations.

Effect of the resolution of measurements in the behavior of the shewhart control charts for means.

Unlabelled: Measurements of limited resolution change the behavior of a Shewhart average chart in two ways. The standard deviation of measurements differs from process standard deviation due to rounded values and discreteness of values of subgroup averages. The probability of getting a point in control depends on the position of accessible values relative to the position of control limits.

Statistical properties of the USP dissolution test with pooled samples.

The Montecarlo simulation method is used to study the statistical properties of the USP pooled dissolution test. In this paper, the statistical behavior of the dissolution test for pooled samples is studied, including: a) the operating characteristic curve showing the probability of passing the test versus the mean amount dissolved, b) the influence of measurement uncertainty on the result of the test, c) an analysis of the dependence of the statistical behavior on the underlying distribution of the individual amounts dissolved, d) a comparison of the statistical behavior of the unit dissolution test versus the pooled dissolution test, e) the average number of stages needed to reach a decision presented as a function of parameters of the lot, f) the relative influence of the three stages of the test on the probability of acceptance.