Three Types of Error

Here we discuss the concepts of error and uncertainty. In the world the word error implies a failure of some kind—synonyms include mistake, blunder, slip, and lapse. In metrology, error is defined as the result of a measurement minus a true value of the measurand and is free of such negative connotations. Error in an analysis is a particular value that may be known if the true value is given. 

Always the same value and sign Normally distributed with mean of zero 

Considering why we might not deliver exactly 10 mL using a 10 mL pipette is instructive (figure 1.1). 

We shall identify three contributing factors to the problem. There are more, and as an exercise the reader might try to think of everything that can go wrong with this apparently straightforward operation in analytical chemistry. 

The manufacturer will admit that the pipette you are using, when filled properly to the mark at 20°C, is only guaranteed to have a volume somewhere between 9.98 and 10.02mL. Perhaps you are lucky and have a 10.00 mL pipette, but perhaps not. Note that any error of this type is a systematic error. 

---

The boundaries of these regions may be computed from Equations A-23 and A-24. The region where the predominant decision is OK lies to the left of the contour defined by Equation A-23. The region where the predominant decision is NOT OK lies to the right of the contour defined by Equation A-24. The region between these two contours is the region where the decision rule makes most of its errors. Note that there are three types of error no decision when one should be made NOT OK when the decision should be OK and OK when the decision should be NOT OK. 

Experimental scientists generally consider there to be three types of error ... 

The first use of a bromate-bromide mixture as a source of bromine was by Koppescbaar, who devised the classical bromination method for phenol. The method is still in use today and has been applied to a wide variety of organic com-poimds. Three types of error can be recognized (7) oxidation of readily oxidized substances such as o- and p-aminophenols (2) precipitation of incompletely bromin-ated products, which occurs especially with parasubstituted compounds such as p-nitroaniline and p-iodoaniline and (5) replacement of certain groups such as —COOH, —CHO, or —SO3H by bromine. 

One aspect of data checkout is finding errors in the data. Errors can occur either in the database(s) from which the data file is constructed or in the transcription from that database. The latter type of error can be of two types, either in individual values or in the structure of the data file as such. All three types of errors may pass unrecognized by NONMEM and additional data checkout is therefore necessary. The structure of the data set informs NONMEM where and when the doses and... 

An experimental program designed to yield accurate Mdssbauer data will provide for the independent estimation of the three types of errors referred to above, to the extent that this is possible, and should lead ultimately to a realistic assessment of the accuracy and precision of the reported results. The errors commonly encountered in Mdssbauer effect experimentation will be illustrated by several examples in the following discussions. 

For transmittance measurements three types of error are recognized as being due to the instrument. These are of independent origin and are potentially accumulative (Figure 9.28) ... 

Three types of error amplifier compensation schemes are used most often — called the Type 1, Type 2, and Type 3 in order of increasing complexity and flexibility. The former two are just a subset of the latter, so we prefer to do a Type 3 compensation to demonstrate the full scope (though often, a Type 2 compensation should suffice). 

There are three classes of errors systematic errors are reproducible and the cause is related to some physical law and may be eliminated by appropriate corrective actions random errors are unpredictable and irreproducible and can be characterized by the laws of statistics finally, inadmissible errors occur as a result of mishandling, incorrect instrument operation, or even poor record keeping. Figure 2.6 shows a hierarchical chart that outlines the three types of errors (Chaouki et al., 2007). Most treatments of error consider systematic and random errors. Inadmissible errors might somehow be related to outliers, which are values that appear to be completely unrelated to a rational data set. 

There is some uncertainty in all data, and model building must take this error into account. The first step in error management is error detection, error reduction, and error quantification. There are three types of error systematic error, random error, and blunders. Improved experimental protocol can reduce all these, but designing progressively better experiments eventually leads to diminishing returns so that at some point it is necessary to use some kind of error analysis to manage the uncertainty in the variable being quantified. 

As we have just done, people often talk of breaches or violations of procedures. But it needs to be borne in mind, as noted in Chapter 11 that there are three types of error according to Rasmussen (see Further Reading at the end of this chapter) - skill-based, rale-based and knowledge-based (s, r and k) and so the reasons for the breaches of procedure can be quite different. As an example, we tend to use skill-based and rule-based decisions a thousand times more than knowledge-based decisions in driving a car. 

Three types of errors have been defined ... 

The three types of errors enumerated above match with those defined in the Human Factors Analysis and Classification System (HFACS), which is a general human error framework for classifying aviation accidents. It has been developed and used within the U.S. military, applied to commercial aviation accident records and proved to be a valuable tool in the civil aviation area. But it makes also sense to apply the classification scheme in other areas, like in COOPERS. 

Miscellaneous errors. These are those errors that cannot be grouped under the above three types of errors. In this study, this type of errors accounted for approximately 10% of the total pilot-controller communication errors. 

In principle all scientific information should be correct inside the given standard uncertainty. But there are three types of errors ... 

Three types of errors are made when replacing a periodic solid by a finite piece for the purpose of a quantum mechanical calculation ... 

---