Introduction

One way of generating hypotheses is to collect data and look for patterns. Often, however, it is difficult to see any pattern from a set of data, which may just be a list of numbers. Graphs and descriptive statistics are very useful for summarizing and displaying data in ways that may reveal patterns. This chapter describes the different types of data you are likely to encounter and discusses ways of displaying them.

Variables, sampling units and types of data

In earth science applications, we usually consider three different types of data:

1. (1) Data organized in a sequence along a continuum of distance or time. These data can be thought of as occurring in one dimension. For example, you might be analyzing the composition or mineralogy of a drill core and need to interpret spatial variation up and down the section.

2. (2) Data where sampling is done relative to some geographic or other type of spatial context. These are usually two-dimensional data. Geologic maps, contour diagrams, trend surface analyses and studies of spatial relationships in thin sections all present opportunities to relate data to a 2-D system.

3. (3) Multivariate data in which the 1- or 2-D locations of the sampled data are not relevant. Most types of chemical data fall into this category.

The particular attributes you measure when you collect data are called variables (e.g. a chemical analysis, observations of humidity and air temperature, the thickness of some geological strata).