Page 16 - MATLAB Recipes for Earth Sciences

6 1 Data Analysis in Earth Sciences

2. ordinal data – These are numerical data representing observations that
can be ranked, but the intervals along the scale are not constant. Mohs·
hardness scale is one example for an ordinal scale. The Mohs· hardness
value indicates the materials resistance to scratching. Diamond has a hard-
ness of 10, whereas this value for talc is 1. In terms of absolute hardness,
diamond (hardness 10) is four times harder than corundum (hardness 9)

and six times harder than topaz (hardness 8). The Modified Mercalli Scale
to categorize the size of earthquakes is another example for an ordinal
scale. It ranks earthquakes from intensity I (barely felt) to XII (total de-
struction).

3. ratio data – The data are characterized by a constant length of successive
intervals. This quality of ratio data offers a great advantage in comparison
to ordinal data. However, the zero point is the natural termination of the
data scale. Examples of such data sets include length or weight data. This
data type allows either a discrete or continuous data sampling.

4. interval data – These are ordered data that have a constant length of suc-
cessive intervals. The data scale is not terminated by zero. Temperatures
C and F represent an example of this data type although zero points exist
for both scales. This data type may be sampled continuously or in discrete
intervals.

Besides these standard data types, earth scientists frequently encounter spe-
cial kinds of data, such as

1. closed data – These data are expressed as proportions and add to a fi xed
total such as 100 percent. Compositional data represent the majority of
closed data, such as element compositions of rock samples.

2. spatial data – These are collected in a 2D or 3D study area. The spatial
distribution of a certain fossil species, the spatial variation of the sand-
stone bed thickness and the 3D tracer concentration in groundwater are
examples for this data type. This is likely to be the most important data
type in earth sciences.

3. directional data – These data are expressed in angles. Examples include
the strike and dip of a bedding, the orientation of elongated fossils or the

flow direction of lava. This is a very frequent data type in earth sciences.