Let's look at Figure 3 again. About plant growth example. This figure represents plant growth as it is affected by the amount of water and sunlight. Plants are also affected by the amount of nutrients in the soil, which we will refer to as the rate of fertilizer application If we speculate that the rate of fertilizer application was constant at a medium level in Figure 3, then the whole plant growth experiment could be run again with a different levels of fertilizer. A new 2D graph could be generated from the new data.
The plant experiment could be conducted two, ten, or ten thousand at rates of fertilizer application. A 2D graph could be generated from the data at each of these specific nitrogen levels. If two or three different experiments are run, it is not difficult to compare their 2D graphs. Comparing 2D graphs becomes difficult when there are a large number of 2D graphs (ten or ten thousand).
The data is entered into the computer and a program turns the data into the 3D figure. How to actually do this is addressed later. Click to skip to that section.
Last revised July 13, 1996
http://www.sv.vt.edu/class/surp/surp96/laughlin/stat/3D_tutor/3Dtheory.html