Other control charts

After observation day 10 a trend towards low results seems to appear. The Shewhart chart demonstrates only at day 20 that the measurements must be stopped (more than 9 times under the mean and 2 results under the 2s lower limit). The same data have been used to construct the Cusum chart of Fig. 2.11. 

In microbiology two fundamental types of measurements are used by the analyst. The simplest ones consist in counting colonies on culture media in a Petri dish. Another principle consists in evaluating the most probable number of microbes by inoculating sub-samples into multiple tubes. The result of the latter is given by statistical tables. For both types of methods results are only available after a few days. For the presence of very few microbes, so-called presence/absence tests have been developed by microbiologists. They are mainly used for the detection of pathogenic microbes. For the last two types 

R represents the difference between two duplicate measurements. The warning (2s dotted line) and the alarm limit (3s full line) are obtained from duplicate sets of results in a similar way as for X-charts. 

---

The Cusum Chart shows very clearly the point from which the process ran ont of control. The average mn length, i.e. the time needed to detect an ont-of-control sitnation is shorter than for other control charts. Fnrthermore, the size of a change in the process can be detected from the slope of the chart. 

The common values of constants c4 and A3 are tabulated in Table 4 for sample sizes from 2 to 10. Like other control charts, the values of x and s should be periodically verified to assure that they can be used to derive good estimators for the process average and process standard deviation. 

Were QSUM or other control charts used ... 

Is precision of production measuring equipment routinely monitored (via control charts or other similar techniques) ... 

The production of some products can be controlled simply by inspection after the product has been produced. In other cases, as with the continuous production of food and drugs, you may need to monitor certain process parameters to be sure of producing conforming product. By observing the variability of certain parameters using control charts, you can determine whether the process is under control within the specified limits. 

FIGURE 11.22 Control charts and outliers, (a) pEC50 values (ordinates) run as a quality control for a drug screen over the days on which the screen is run (abscissae). Dotted lines are the 95% c.l. and the solid lines the 99.7% c.l. Data points that drift beyond the action lines indicate significant concern over the quality of the data obtained from the screen on those days, (b) The effect of significant outliers on the criteria for rejection. For the data set shown, the inclusion of points A and B lead to a c.l. for 95% confidence that includes point B. Removal of point A causes the 95% limits to fall below points B, causing them to be suspect as well. Thus, the presence of the data to be possibly rejected affects the criteria for rejection of other data. 

Coordinated phosphate control charts assume either that all contribution to pH level is derived from phosphate or that the buffering action of phosphate is sufficient to overcome the presence of other alkaline species, such as amines. Neither assumption is true. This may lead operators to conclude perhaps that a higher than anticipated bulk water pH level (caused by the presence of amine) should be rectified by the addition of MSP. This action may lower localized Na P04 ratios below 2.2 1.0, producing acid phosphate corrosion (phosphate wastage) and resulting in tube thinning and ultimately tube failure. 

The quality control unit in a cosmetics company supervised the processing of the weekly batch of shampoo by determining, among other parameters, the viscosity and the dry residue. Control charts showed nothing spectacular. (See Fig. 4.10, top.) The cusum charts were just as uneventful, except for that displaying the dry residue (Fig. 4.10, middle and bottom) The change in trend in the middle of the chart was unmistakable. Since the analytical method was very simple and well-proven, no change in laboratory personnel had taken place in the period, and the calibration of the balances was done on a weekly basis, suspicions turned elsewhere. A first hypothesis,... 

Identify available information, including information from quality control charts, performance in proficiency testing rounds, literature and validation information on related methods and data concerning comparison with other methods. Use the available information and professional judgement to review each relevant validation issue and sign-off issues adequately addressed and documented. 

When using control charts, you should take action on any points which fall outside the action limits and be alert when points exceed the warning limits. There are three other situations which normally indicate a problem with the system, as follows ... 

The previous chapters of this book have discussed the many activities which laboratories undertake to help ensure the quality of the analytical results that are produced. There are many aspects of quality assurance and quality control that analysts carry out on a day-to-day basis to help them produce reliable results. Control charts are used to monitor method performance and identify when problems have arisen, and Certified Reference Materials are used to evaluate any bias in the results produced. These activities are sometimes referred to as internal quality control (IQC). In addition to all of these activities, it is extremely useful for laboratories to obtain an independent check of their performance and to be able to compare their performance with that of other laboratories carrying out similar types of analyses. This is achieved by taking part in interlaboratory studies. There are two main types of interlaboratory studies, namely proficiency testing (PT) schemes and collaborative studies (also known as collaborative trials). 

There are numerous approaches to the problem of capturing all the information in a set of multi endpoint data. When the data are continuous in nature, approaches such as the analog plot can be used (Chemoff, 1973 Chambers et al., 1983 Schmid, 1983). A form of control chart also can be derived for such uses when detecting effect rather than exploring relationships between variables is the goal. When the data are discontinuous, other forms of analysis must be used. Just as the control chart can be adapted to analyzing attribute data, an analog plot can be adapted. Other methods are also available. 

The results of the analysis of a control are often plotted on a control chart (Chapter 1) in order to visualize the history of the analysis in the laboratory so that a date and time can be identified as to when the problem was first detected. Thus, the problem can be traced to a bad reagent, instrument, or other component of the procedure if such a component was first put into use the day the problem was first detected. Your instructor may want you to use controls in various experiments in this text. 

A quality control chart is a visual aid for determining whether a given analytical result is outside the action limits determined for the results for that procedure. If it is outside the action limits, the cause may be a problem with the procedure, among other things. 

Here we cannot assume that a single value of standard deviation is applicable. Insert control materials in total numbers approximately as recommended above. However, there should be at least two levels of analyte represented, one close to the median level of typical test materials, and the other approximately at the upper or lower decile as appropriate. Enter values for the two control materials on separate control charts. Duplicate a minimum of five test materials, and insert one procedural blank per ten test materials. 

Copies of the control charts and duplicate value control charts or other agreed measures to monitor IQC. 

Several method performance indicators are tracked, monitored, and recorded, including the date of analysis, identification of equipment, identification of the analyst, number and type of samples analyzed, the system precision, the critical resolution or tailing factor, the recovery at the reporting threshold level, the recovery of a second reference weighing, the recovery for the control references (repeated reference injections for evaluation of system drift), the separation quality, blank issues, out of spec issues, carry over issues, and other nonconformances. The quantitative indicators are additionally visualized by plotting on control charts (Figure 23). 

We have seen two different approaches to estimate the measurement uncertainty. One was using data from control charts, CRM analysis, PT results and/or recoveiy tests and sometimes maybe also experience of the analyst, the other was just using the reproducibility standard deviations from interlaboratory tests. In most cases the second method delivers higher estimates. 

Some standards or decrees include the obligatory measurement of control samples or repeated measurement. This can be used for control charts with only little effort. Other values like calibration parameters are also available without additional woik. They also can be used for control charts, especially if the stability of calibration is known to be a weak point in the procedure. 

Real samples. The move to analyze real samples represents a move toward the unknown. Not only are the results of the analysis unknown ahead of time, but other variables relating to sample inhomogeneity, sample preparation variables, additional sources of error, etc. are introduced. A large number (>30) of duplicate samples should be analyzed so that a reliable standard deviation and a reliable control chart can be established. The ultimate purpose of this work is to characterize what is a typical analysis for this kind of sample so that one can know when the method is under statistical control and when... 

Many of the quality improvement goals for implementation of PAT in the pharmaceutical industry have been achieved by companies in other industries, such as automobile production and consumer electronics, as a direct result of adopting principles of quality management. The lineage of modern quality management can be traced to the work of Walter Shewhart, a statistician for Bell Laboratories in the mid-1920s [17]. His observation that statistical analysis of the dimensions of industrial products over time could be used to control the quality of production laid the foundation for modern control charts. Shewhart is considered to be the father of statistical process control (SPC) his work provides the first evidence of the transition from product quality (by inspection) to the concept of quality processes [18,19]. 

Trueness or exactness of an analytical method can be documented in a control chart. Either the difference between the mean and true value of an analyzed (C)RM together with confidence limits or the percentage recovery of the known, added amount can be plotted [56,62]. Here, again, special caution should be taken concerning the used reference. Control charts may be useful to achieve trueness only if a CRM, which is in principle traceable to SI units, is used. All other types of references only allow traceability to a consensus value, which however is assumed not to be necessarely equal to the true value [89]. The expected trueness or recovery percent values depend on the analyte concentration. Therefore, trueness should be estimated for at least three different concentrations. If recovery is measured, values should be compared to acceptable recovery rates as outlined by the AOAC Peer Verified Methods Program (Table 7) [56, 62]. Besides bias and percent recovery, another measure for the trueness is the z score (Table 5). It is important to note that a considerable component of the overall MU will be attributed to MU on the bias of a system, including uncertainties on reference materials (Figures 5 and 8) [2]. 

There is no mention of control charts or other graphical QC tools (see chapter 4). There is a note that the selected methods should be appropriate for the type and volume of the work undertaken. As part of the emphasis on the overall quality framework, the standard now requires a laboratory to analyze QC data and to implement corrective action if results are outside predefined criteria. 

An established external quality control (QC) scheme is not currently available. Pooled disease control CSF retained from other analyses is used. Aliquots of the pooled CSF are made and stored at -70°C. This CSF is analysed on five separate occasions and the mean and standard deviation determined. For an analytical/diagnostic run to proceed, analysis of QC material must provide concentration values that are within two standard deviations (plus and minus) of the calculated mean for that particular QC. Construction of Levy-Jennings type control charts provide historical information of overall performance and highlight potential deterioration in the performance of the system. 

---