Page 253 - RISK Management IC 86

The Insurance Times

(ii) The next step is to collate the data and sort them as
per requirement.

(iii) Next, in order to highlight possible trends or patterns
in the data, losses can be grouped into classes of
different sizes, and the number of observations falling
into each class is recorded. The number of
observations in each class is known as class
frequency, and the resulting table is known as
frequency distribution table.

(iv) The total range of data is then subdivided into equal
class intervals, the number chosen depending on the
amount of data available and the use to which it will
be put. The larger the number of class intervals, the
less will be gained from grouping the data, whereas
by choosing only a small number of classes, a large
number of information will be lost.

(v) To decide on the size and number of class intervals,
the total range within which the data falls must first
be defined.

(vi) The degree of accuracy assigned to the limits of each
class interval is determined by the accuracy of
measurement of the original data.

Website: www.bimabazaar.com Call: 033-22184184 / 40078428 254

Copyright@ The Insurance Times. 09883398055 / 09883380339