Data analysis is the foundation of scientific experimentation. Scientists ask questions; convert those questions into hypotheses; design experiments to test those hypotheses; collect, analyze, and interpret data; and communicate the results and interpretations of their experiments to their peers and ultimately to all interested individuals. There is almost an infinite number of data analysis techniques to choose from. However, only a very few analytical techniques are appropriate for a given data set and still fewer techniques will actually yield meaningful results. As a scientist, you must identify the most appropriate data analysis technique that will yield the maximum amount of information. Analysis techniques should be chosen during the experimental design phase of any study and certainly before data are collected.
In the early stages of your education as a scientist, analysis techniques will likely be chosen for you. As you progress through your scientific career, you will begin to identify appropriate analysis techniques. To assist in this development, a list of links for numerical, graphical, and simple statistical techniques is provided below.