Accuracy, Precision

Download as pdf or txt
Download as pdf or txt
You are on page 1of 4

ACCURACY:

 Accuracy of an analytical procedure is the closeness of agreement between


the conventional true value (accepted reference value) and the value
found.
 Accuracy is the extent to which test results generated by the method and
the true value agree.
 It expresses the correctness of a measurement and closeness of the result
by comparing it to the absolute value.

Accuracy can be determined by two ways:

1. Absolute method
2. Comparative method

Absolute method

 A synthetic sample containing known amount of constituents is used.


 These substances, primary standard, may be available commercially or they
may be prepared by the analyst and subjected to rigorous purification.
 The test of accuracy of the method is carried out by taking varying amount
of the constituent and proceeding according to specified instructions.
 The amount of constituent must be varied , because the determinate error
in the procedure may be a function of the amount used.
 The difference between the mean of an adequate number of results and
the amount of constituent actually present is a measure of accuracy of the
method in the absence of foreign substances.

Comparative method:

 Sometimes, as in the analysis of a mineral it may be impossible to prepare


solid synthetic samples of desired composition.
 So these samples are further resorted so as to determine the content of the
constituents by one or more accurate method of analysis.
 This comparative method using secondary standards is very useful in
applied analysis.
PRECISION:
 It is the concordance of a series of measurements of the same quantity.
 Precision of an analytical procedure as the closeness of agreement between
a series of measurements obtained from multiple sampling of the same
homogeneous sample under the prescribed conditions.
 ie, Precision is how close the measured values are to each other.
 It represents the reproducibility or repeatability or uniformity in the
measurement
 Precision may be considered at three levels: repeatability, intermediate
precision and reproducibility.
 Precise results are not necessarily accurate.
 Precision may be considered at three levels:
 Repeatability expresses the precision under the same operating conditions
over a short interval of time.
 Repeatability is also termed intra-assay precision.
 Intermediate precision expresses variations within laboratories, such as
different days, different analysts, different equipment, etc.
 Reproducibility expresses the precision between laboratories.
 Precision is usually reported as the average deviation, standard deviation or
range.

Precision measures:

 Ruggedness test describes the influence of small but reasonable alterations


in the procedures of the quality of analysis. The minor variations can be due
to source and age of reagents, concentration and stability of solutions and
reagents, heating rate, humidity, voltage fluctuation, analyst to analyst and
instrument to instrument variation etc

1. Arithmetic Mean / Average


 Arithmetic Mean is obtained by adding together the results of the various
measurements and dividing the total by the number of measurements.
in which,

∑ stands for “sum of”

X1 is the individual measurement of the group

N is the number of values.

2. Median:
 The median is a value about which all the other are equally distributed.
 Half of the values are smaller and the other half are larger than the median
value.
 It is the central value of all the observations arranged fron the lowest to
highest.

 Other precision measures are relative mean deviation, standard deviation,


variance etc
ACCURACY PRECISION
Accuracy is the closeness with the Precision is a measure of
true value of the quantity being reproducibility of the measurement
measured
Degree of conformity or correctness Degree of reproducibility
Accurate values have to be precise in High degree of precision does not
most cases imply accuracy
It is determined with a single It needs several measurements to be
measurement determined
Accuracy may be affected with Precision may be affected with
systematic error random errors

You might also like