Chemometrics experimental factors

Several studies have employed chemometric designs in CZE method development. In most cases, central composite designs were selected with background electrolyte pH and concentration as well as buffer additives such as methanol as experimental factors and separation selectivity or peak resolution of one or more critical analyte pairs as responses. For example, method development and optimization employing a three-factor central composite design was performed for the analysis of related compounds of the tetracychne antibiotics doxycycline (17) and metacychne (18). The separation selectivity between three critical pairs of analytes were selected as responses in the case of doxycycline while four critical pairs served as responses in the case of metacychne. In both studies, the data were htted to a partial least square (PLS) model. The factors buffer pH and methanol concentration proved to affect the separation selectivity of the respective critical pairs differently so that the overall optimized methods represented a compromise for each individual response. Both methods were subsequently validated and applied to commercial samples. 

Thermoanalytical investigations of sedimented airborne particulates [EINAX and LUDWIG, 1991] confirm experimentally the chemometrically found interpretation that aluminum can serve as an indicator element for lignite combustion. Thermogravimetric analysis of mixed samples of sedimented dusts detect a loss of mass at a temperature of 714°C this can be interpreted as dehydration of aluminosilicates. This loss of mass exhibits a well defined summer minimum and a strong winter maximum. These findings also correspond to the results from factor analysis (see Section 7.2.1.2.4). 

Chemists and statisticians use the term mixture in different ways. To a chemist, any combination of several substances is a mixture. In more formal statistical terms, however, a mixture involves a series of factors whose total is a constant sum this property is often called closure and will be discussed in completely different contexts in the area of scaling data prior to principal components analysis (Chapter 4, Section 4.3.6.5 and Chapter 6, Section 6.2.3.1). Hence in statistics (and chemometrics) a solvent system in HPLC or a blend of components in products such as paints, drugs or food is considered a mixture, as each component can be expressed as a proportion and the total adds up to 1 or 100%. The response could be a chromatographic separation, the taste of a foodstuff or physical properties of a manufactured material. Often the aim of experimentation is to find an optimum blend of components that tastes best, or provide die best chromatographic separation, or die material diat is most durable. 

The function of RPS can aid setting up the chromatographic separation conditions. The optimization of a separation can be done experimentally based a chromatographer s experience and intuition, or with computer control based on the "Chemometrics", i.e., "Simplex" procedure (4,5). Although such approaches are reliable and promising enough to use for practical purposes, this is a time-consuming task because a number of experiments required with the increase factors for optimization. On the other hand, it is possible to optimize a separation in RPS with almost the same accuracy as obtained in the conventional Chemometrics approaches within a few minutes. 

The improvement in computer technology associated with spectroscopy has led to the expansion of quantitative infrared spectroscopy. The application of statistical methods to the analysis of experimental data is known as chemometrics [5-9]. A detailed description of this subject is beyond the scope of this present text, although several multivariate data analytical methods which are used for the analysis of FTIR spectroscopic data will be outlined here, without detailing the mathematics associated with these methods. The most conunonly used analytical methods in infrared spectroscopy are classical least-squares (CLS), inverse least-squares (ILS), partial least-squares (PLS), and principal component regression (PCR). CLS (also known as K-matrix methods) and PLS (also known as P-matrix methods) are least-squares methods involving matrix operations. These methods can be limited when very complex mixtures are investigated and factor analysis methods, such as PLS and PCR, can be more useful. The factor analysis methods use functions to model the variance in a data set. 

The second factor concerns control of automated systems what happens if there is a malfunction At present, few automated sample preparation systems offer overall control. The probability, in the event of a malfunction, is that the autosampler will complete its cycle and valuable samples will be lost. Thus, developers must consider feedback control mechanisms that are essential to monitor the operation of a complex instrument that would be sampling, preparing, and analyzing simultaneously. If an error in this operation were detected and if the fault could not be corrected, the unit could be shut down, thus preventing the further loss of any samples. The development of these workstations able to make decisions may involve chemometrics, where there will be feedback between the analytical measurement and the experimental design. 

Baseline separation was achieved between the candidate drug and the two metabohtes after extraction of the compounds from human plasma following protein precipitation. The LOQ was improved by a factor of 5 for the HPLC-MS/MS method after chemometric optimization. The UPLC-MS/MS method resulted in much lower operational cost, and therefore it was decided to optimize that method. Significant factors from the experimental screening were optimized via central com-... 

Since many factors will affect experimental results, quite complex experimental designs may be necessary. The choice of the best practical levels of these factors, i.e. the optimization of the experimental conditions, will also require detailed study. These methods, along with other multivariate methods covered in the next chapter, are amongst those given the general term chemometrics. 

---