Geoscience Reference
In-Depth Information
[Var1,Var2] = meshgrid(0.20:0.01:0.45,0.17:0.01:0.23);
Var3 = 5.0222 - 45.307*Var1 + 239.8*Var2;
surf(Var1,Var2,Var3,'FaceAlpha',0.2), hold on
line(data(:,1), data(:,2), data(:,3),...
'LineStyle','none',...
'Marker','.',...
'MarkerSize',30)
grid on
view(70,30)
hold off
and observe some dif erences between the data and the regression plane if
we rotate the graph in three dimensions using the
Rotate 3D
tool on the
toolbar of the Figure Window.
As a second example we use laboratory data from the Sherwood Sandstone,
England, that suggest that intergranular permeability (as response variable)
is mainly inl uenced by porosity and matrix conductivity (as predictor
variables), while other variables have less inl uence. h is example has been
previously discussed in detail in an article by Olorunfemi (1985) and was
used as an example in the textbook by Swan and Sandilands (1995). h e data
for 40 rock samples from the Sherwood Sandstone were taken from M.O.
Olorunfemi's publication and are stored in the i le
sherwoodsandstone.txt
.
We load the data from the i le by typing
Movie
9.1
Fig. 9.8
Linear regression model for a synthetic data set with three variables and random
noise.
