Control limit using statistical methods

Analytical laboratories establish the accuracy of the performed methods through the preparation and analysis of laboratory control samples, the same samples that are used for the determination of laboratory precision. Based on a statistical evaluation of the recoveries from these interference-free matrices, laboratories derive the recovery acceptance criteria, called laboratory control limits. 

For GC/MS analyses, some laboratories use surrogate standard recovery limits from outdated versions of EPA Methods 8260 and 8270. These recovery limits, shown in Example 4.18, are fairly close to the statistically derived control limits at most laboratories and can be safely used in the evaluation of data quality. The surrogate... 

Developmental effects were reported in one study in which female rats were treated orally during conception and pregnancy with approximately 18.3 mg barium/kg/day as barium carbonate (Tarasenko et al. 1977). Reported effects in offspring included increased mortality, increased leukocyte count, disturbances in liver function, and increased urinary excretion of hippuric acid. The later study is inadequate for evaluating developmental effects of oral barium exposure because of major study limitations. These limitations include a general lack of information provided by the authors regarding experimental methods, exposure conditions, and test results, and no information as to the number of animals tested, the purity of the test material, the statistical methods used, and whether or not controls were used. No other animal studies evaluating developmental effects were available. 

By using the 96-well microELIS A format and instituting the use of rephcates of the samples and controls, they enabled statistical evaluation of the validity of the tests. An accepted method of determining the LOD of EIAs is to determine the mean OD value of the replicates of the appropriate negative controls and adding 3 standard deviations of those replicates. The detection limit of the tests developed, depending on the antibody pool used, was determined to be between 100 and 500 ppm, more than adequate for the detection of economic adulteration. 

FIGURE 27.7 When using an NIR method for process control, statistical control charting can be used to set upper and lower control limits. This method clearly shows the difference between one sample with an unusual result vs. a series of samples that are trending toward the upper or lower control limit. 

Limitations. Irrespective of the statistical method selected, the goal must be to determine which peaks in the gas chromatographic profile are the best indicators of sensory quality. This peak selection together with a mathematical model are used to analytically monitor (or predict) sensory quality. Assuming that the analytical method is both accurate and precise, an instrumental method such as this can very effectively predict sensory quality. In a quality control laboratory, this analytical approach can serve as an untiring evaluator. 

This is a very basic method for calculating upper and lower control limits. Other methods can also be used to calculate these hmits. To ensure that the statistical control charts are as reliable as practical, keep several guidelines in mind. First, use accident rates that have as many sets of data as possible. For example, an aU injury/iUness frequency rate works better than a lost time frequency rate. Second, try to use at least twenty sets of data in calculating the base rate or average. In our example we only used five data points for practical purposes. However, they represented 60 individual monthly frequency rates. 

Analysis of Standards The analysis of a standard containing a known concentration of analyte also can be used to monitor a system s state of statistical control. Ideally, a standard reference material (SRM) should be used, provided that the matrix of the SRM is similar to that of the samples being analyzed. A variety of appropriate SRMs are available from the National Institute of Standards and Technology (NIST). If a suitable SRM is not available, then an independently prepared synthetic sample can be used if it is prepared from reagents of known purity. At a minimum, a standardization of the method is verified by periodically analyzing one of the calibration standards. In all cases, the analyte s experimentally determined concentration in the standard must fall within predetermined limits if the system is to be considered under statistical control. 

You should review the contract and the detail specifications to identify whether your existing controls will regulate quality within the limits required. You may need to change the limits, the standards, the techniques, the methods, the environment, and the instruments used to measure quality characteristics. One technique may be to introduce Just-in-time as a means of overcoming storage problems and eliminating receipt inspection. Another technique may be Statistical Process Control as a means of increasing the process yield. The introduction of these techniques needs to be planned and carefully implemented. 

---