The scatterplots for dynamic response experiments show the responses plotted against the signal. Each cell shows all the data for one of the factor settings in the experiment. The cell contents are as follows:

·    The least squares regression line through the reference point is plotted.

·    The row number at the top of each cell refers to the worksheet row number, which is the first row in which the factor settings for that cell appear.

·    The signal-to-noise ratio, slope, and standard deviation for the run are located at the bottom of the cell.

The graphs are arranged in decreasing order of the signal-to-noise ratio, so that the "best" runs are plotted first. If the experiment has more than nine runs, more than one graph window of scatterplots will be displayed.

Some things to consider when looking at the scatterplots include:

·    Does the fitted line conform closely to the pattern of the data for the "best" runs? What type of deviations do you observe?

·    Is the pattern of the data a straight line or is it curved? If it is a line, does it follow the fitted line, or is it shifted?

·    Are there any unusual response values or outliers? Do you notice a substantial difference in the spread of the data about the line between the best and worst fits?

For the basil data, there is a substantial difference in the spread of the data between the best and worst fits.

·    In the plot in the first cell, for row 21, the data are very close to the line.

·    In the plot in the lower left corner, for row 9, the data vary much more widely.

In some cases, such as the row 9 plot, there seems to be one point at each signal level that diverges sharply below the others. It would be worthwhile to see if this divergence consistently occurs for the same noise condition across the data. The data do not exhibit curvature. As might be expected, the spread of the data increases with the signal level.