Basic Classification schemes in GIS ▪ Natural breaks (arcview’s default classification) ▫ This method identifies breakpoints by looking for groupings and patterns that is inbuilt/available in the data by using an algorithm (Jenks optimization) ▫ This method groups values within a class resulting in classes of similar values separated by break points . This method works well with values that are not evenly distributed and that are not heavily skewed towards one end of the distribution or (this method seeks to partition data into classes based on the natural groups in the data distribution, so classes are defined according to natural groupings of your data values and breaks may be imposed on the basis of break points that are known to be relevant to a particular application) ▫ It can be used to discover patterns in data, however it can result in legends that are difficult to understand & strange number ranges can appear on the legend NATURAL BREAKS ▪Quantiles breaks: ▫Equal number of features & corresponding records are placed into each class, e.g. 20 records into five classes with four records ▫This is a good method for classifying evenly distributed data ▫Can also result in misleading legends because features with greatly different values can be placed into a single class (i.e.. low values can be in one class with high values) ▫Solution manually increase the number of classes QUANTILES Equal Interval • Divides total range of records from maximum to minimum say into equal sub ranges • E.g. say you have values that range from 12 to 351, the total range of these values is 339 & if you classify these into three groups, you get 12 -125. 126 -238 and 239 – 351. • This creates a legend that is easy to understand & it works well with continuously distributed data, e.g. precipitation, temp & percentages • If it is applied to certain data types, the legend can end up with few classes for one feature Equal interval Equal area (for polygon features): • It divides polygon features into groups so that the total area of the polygons in each group is approximately the same • is a very specialized ArcView method that divides the range of features in a polygon theme so that each subrange contains basically the same area. • Useful method for only a limited number of situations, e.g. allocating working areas to employees Equal area Standard Deviation • shows how an attribute’s value deviates from the mean of all values. Here, the software determines the mean value and then places breaks above and below the mean at intervals or deviations of either 1, 0.5 or 0.25 standard deviations until all values are included in a class Standard deviation • Natural breaks (arcview’s default classification)- – This method identifies breakpoints by looking for groupings and patterns that is inbuilt/available in the data by using an algorithm (Jenks optimization) so this method groups values within a class resulting in classes of similar values separated by break points . This method works well with value that are not evenly distributed and that are not heavily skewed towards one end of the distribution or (this method seeks to partition data into classes based on the natural groups in the data distribution, so classes are defined according to natural groupings of your data values and break may be imposed on the basis of break points that are known to be relevant to a particular application) – It can be used to discover patterns in data, however it can result in legends that are difficult to understand & strange number ranges can appear on the legend • Quantiles breaks: – Equal number of features & corresponding records are placed into each class, e.g. 20 records into five classes with four records – This is a good method for classifying evenly distributed data – Can also result in misleading legends because features with greatly different values can be placed into a single class (i.e.. low values can be in one class with high values) – Solution manually increase the number of classes • Equal Interval: – Divides total range of records from maximum to minimum say into equal sub ranges – E.g. say you have values that range from 12 to 351, the total range of these values is 339 & if you classify these into three groups, you get 12 -125. 126 -238 and 239 – 351. – This creates a legend that is easy to understand & it works well with continuously distributed data, e.g. ppt, temp & percentages – If it is applied to certain data types, the legend can end up with few classes for one feature • Equal area (for polygon features): – it divides polygon features into groups so that the total area of the polygons in each group is approximately the same – Useful method for only a limited number of situations, e.g. allocating working areas to employees • Standard Deviation: – shows how an attribute’s value deviates from the mean of all values. Here, the software determines the mean value and then places breaks above and below the mean at intervals or deviations of either 1, 0.5 or 0.25 standard deviations until all values are included in a class