In one of his papers, J. Workman Jr.11 very efficiently depicts the advantages and disadvantages of multivariate thinking for scientists in industry.
From the eight advantages of chemometrics he clearly outlines, special relevance should be given to the following ones:
1. Chemometrics provides speed in obtaining real-time information from data.
2. It allows high quality information to be extracted from less resolved data.
3. It promises to improve measurements.
4. It improves knowledge of existing processes.
5. It has very low capital requirements, i.e., it is cheap.
The last point especially should convince people to give chemometrics a try. No extra equipment is required: just an ordinary computer and some chemometrical knowledge (or a chemometrical consultancy). It is certain that in the very worst cases the same information as found from a classical analysis will be obtained in a much shorter time and with much more evidence. In the great majority of cases, instead, even a simple PCA can provide much more information than what was previously collected. So, why are people so shy of applying chemometrics? In the same paper previously cited, Workman gives some very common reasons:
1. The perceived disadvantage of chemometrics is that there is widespread ignorance about what it is and what it can realistically accomplish.
2. This science is considered too complex for the average technician and analyst.
3. Chemometrics requires a change in one's approach to problem solving from univariate to multivariate thinking.
So, while chemometrics leads to several real advantages, its "disadvantages" lie only in the general reluctance to use it and accepting the idea that the approach followed over many years can turn out not to be the best one.
Was this article helpful?