Statistical evaluation of data

As mentioned previously, uncertainty estimates which have not been obtained directly by statistical evaluation of data may need converting into the correct form before the final combination of the individual uncertainty estimates can be carried out. This is discussed in the next section. 

JA Bietz, DG Simpson. Electrophoresis and chromatography of wheat proteins available methods, and procedures for statistical evaluation of data. J Chromatogr 624 53-80, 1992. 

We find the answers to the four questions in the course of the data quality assessment, which is the scientific and statistical evaluation of data to determine if data obtained from environmental data operations are of the right type, quality, and quantity to support their intended use (EPA, 1997a). Part of DQA is data evaluation that enables us to find out whether the collected data are valid. Another part of the DQA, the reconciliation of the collected data with the DQOs, allows us to establish data relevancy. Thus, the application of the entire DQA process to collected data enables us to determine the effect of total error on data usability. 

Statistical evaluations of data are warranted by the fact that the true mean concentration // (the population mean) will never be known and that we can only estimate it with a sample mean x. As a reflection of this fact, there are two parallel systems of symbols. The attributes of the theoretical distribution of mean concentrations are called parameters (true mean p, variance a2, and standard deviation sample results are called statistic (sample mean x, variance s2, and standard deviation 5). 

Changes in constitution and conformation also have significant effects on the statistical evaluation of data sets. The following examples of small molecule data sets... 

Furthermore, the method must be tested by several laboratories to verify that it meets criteria for validation that were previously established.322 The utilization of standard solutions and samples is a very important condition to accept the quality of the analytical information obtained and to validate the method. Comparison between the quality of the analytical information and the uncertainty of the proposed method with the quality and uncertainty of a standard method used for the same type of analyte from the the same type of matrix is necessary. Only a statistical evaluation of data obtained from both methods (standard and proposed methods) can conclude if the qualities obtained for the analytical information are in concordance with each other, and if the method can be validated from this point of view. 

Based on epidemiological data of radiation-induced cancer occurrences, various authors agree that low dose is below 200 mGy as under this level the statistical evaluation of data becomes more and more uncertain. 

Method development, statistical evaluation of data, and validation and control of analytical procedures are covered in a new chapter (Chapter 14). 

Table 4 Statistical evaluation of data of coefficient of restitution.

The next section deals with method validation of quantitative TLC methods. Two questions should, however, be answered prior to discussing the validation experiments namely, whether the statistical evaluation of data elements, such as precision, accuracy, and reproducibility should be calculated on the basis of measured peak heights or peak areas, and whether the internal or external standard methods, or area normalization should be used to yield quantitative results for the assay. Without going into detail, the most important advantages and limitations of peak height and peak area measurements, and those of the different methods of quantification are summarized in Table 4. 

Julia Burdge did most of her undergraduate work at Iowa State University and completed her degree in Chemistry at the University of South Florida in Tampa. Julia received her Ph.D. (1994) from the University of Idaho in Moscow, Idaho. Her research and dissertation focused on instrument development for analysis of trace sulfur compounds in air and the statistical evaluation of data near the detection limit. 

---