ISO 5667-14:1998 pdf download – Water quality — Sampling — Part 14: Guidance on quality assurance of environmental water sampling and handling.
3.9 recovery extent to which a known, added quantity of determinand in a sample can be measured by an analytical system. NOTE Recovery is calculated from the difference between results obtained from a spiked and an unspiked aliquot of sample and is usually expressed as a percentage. [ISO/TR 1 3530] 3.10 control chart chart, with upper and lower control limits, on which values of some statistical measure for a series of samples, spiked samples and blanks, are plotted, usually in date or sample number order NOTE 1 The chart frequently shows a central line to assist detection of a trend of plotted values toward either control limit. [ISO 3534-2] NOTE 2 In some control charts, the control limits are based on the within-batch data plotted on the chart; in others, the control limits are based on adopted standard or specified values applicable to the statistical measures used. NOTE 3 The cumulative sum (cusum) chart is a type of control chart. Cusum charts are used for detecting small permanent shifts in trends that may remain undetected when using the Shewhart control chart. The basic principle of the most common type of cusum chart is based on the plotted value, which is the cumulative sum of deviations of successive sample statistics from a target value. When a process change is made, the sum is returned to zero. The ordinate of each plotted point represents the algebraic sum of the previous ordinate and the most recent deviation from the target. Cusum charts are generally interpreted by masks superimposed on the chart, a signal occurring if the path of the cusum inter- sects or touches the boundary of the mask (ISO 3534-2). 3.11 Shewhart control chart control chart to show if a process is in statistical control [ISO 3534-2 and ISO 8258] NOTE It may be a chart using attributes (for example, proportion nonconforming) for evaluating a process, or it may be a chart using variables (for example, average and range) for evaluating a process.