Equal interval, Equal frequency, Jenks natural breaks, Geometric interval, Standard deviation

Equal interval. This classification method is used to group data in ranges of equal sizes. A class interval is determined and added to the lowest value in a data set to get the first class interval. This interval is added repeatedly to determine the number of predefined classes. The range of the data is among categories involved, however many they may be. It is used in data spread across an entire range.

Equal frequency (Quantiles)-this method uses a defined number of classes which consists of categories with an equal number of units. The advantage is that classes are easy to compute and every class is equally represented in a mapping. However this method has disadvantages in that the gaps within the mapping are not accounted for thus it may result in overweighting some parameters. It’s easier since little steps are involved in computation; it has little gaps in the groups hence reliable for data mapping. The disadvantage is that it does not cater for the distribution of data laterally in a number line. They are used to create maps that have classes with equal number of observations (Gentle).

 Jenks natural breaks- it is a method that is used to statistically group data into various classes considering the grouping of data in values on the base of their distribution. The advantage is that it minimizes the squared deviations of individual classes hence enabling data to be represented in contiguous classes. Natural breaks are used to map ranges (saeed).


Geometric interval-this method is used to express data that cannot be distributed normally in a visually understandable way. It involves getting a geometric coefficient through dividing a previous interval by the current one. The advantage is that it minimizes variances it is used to classify survey squares, excavation grids and site locations using different colors. It helps visualize data with repetitive values (Gentle).


Standard deviation-it is statistical analysis tool used to measure how data is spread within a given set; it has the disadvantage that it reduces generalization of data. It can be calculated by finding the square root of variance. It is used as a measure of confidence in statistical data. The advantage is that it takes into account of all the values in a sample. The disadvantage is that it’s lengthy to calculate (Mathai and Rathie).
References
Gentle, James E. Computational Satistics. Dordretch: Springer Publishers, 2009.
Mathai, A M and P N Rathie. Probability and Satistics. london: Macmillan Publishers, 1977.
saeed, Gharhamani and. Fundamentals of probability. New Jersey: prentice Hall publishers, 2000.