A mesh is a grid of regularly spaced x- and y-values on which a 3D surface, 3D wireframe, or contour plot is based. Minitab plots response (z) values at the x-y intersections of the mesh.
Chooseto create a regular grid of x-y sample locations or factor combinations. You can then add your own z columns or choose from a list of functions.
Minitab plots response (z) values at the x-y intersections of an evenly-spaced mesh. If your x- and y-values are evenly spaced, Minitab plots the z-values at the x-y intersections. If your x- and y-values are not evenly spaced, Minitab interpolates (estimates) the z-values at the intersections of a regular 15 by 15 mesh with the same x- and y-ranges as your data.
Symbols and project lines always display the actual, not the interpolated, data points.
If your x- and y-values are not evenly spaced, Minitab interpolates (estimates) the z-values at the intersections of a regular 15 by 15 mesh with the same x- and y-ranges as your data. You can change the interpolation method that Minitab uses. If you are unsure of which method to use, you may want to try both and pick the one that works best for your data.
If your x- and y- values form an evenly-spaced grid, the interpolation method has no effect on your plot.
|Use the Distance method if the following are true||Use Akima's polynomial method if the following are true|
|Your surface has isolated extreme values or sudden transitions||Your surface smoothly changes over the x- and y-range of your data|
|Sampling is not intensive enough to capture smooth surface transitions||Sampling is intensive enough to catch smooth surface transitions|
|Sampling error is large||Sampling error is small relative to the surface|
Show the locations of your x- and y- data for the following reasons:
The number of x- and y-values on a mesh determines its resolution. A higher resolution mesh (one with more x- and y-values) will result in a finer interpolation of the surface or contours. The following wireframe and contour plots show the same data but use different mesh resolutions. (Gridlines on the contour plots show approximate mesh location.)
When x-y data do not form a regular grid, the mesh resolution could have a large effect on a contour or surface plot. If your data were sampled such that your x-y points are close to a regular grid, you might enhance the fit by specifying a mesh similar to that of your data.
For example, you want to investigate the effect of temperature and pressure on cook time. You have four temperature settings (325, 350, 375, 400) and three pressure settings (5, 10, 15). When you run the experiment, however, the temperature was slightly different than the desired setting for several runs; thus, the data won't quite form a regular grid. However, because your temperature values are close to regular, a 4 x 3 mesh (temperature x pressure) might give good results for your contour and 3D surface plots.
Using a mesh with more and smaller intervals than exist between data points may seem to add more resolution to the graph, but the detail is probably only background noise.