29.12.2013 Views

Base SAS 9.1.3 Procedures Guide - Acsu Buffalo

Base SAS 9.1.3 Procedures Guide - Acsu Buffalo

Base SAS 9.1.3 Procedures Guide - Acsu Buffalo

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

372 Chapter 3. The UNIVARIATE Procedure<br />

Output 3.31.4. Lognormal Quantile-Quantile Plot (σ =est, ζ =est, θ =5)<br />

From the plot in Output 3.31.2, σ can be estimated as 0.51, which is consistent with<br />

the estimate of 0.5 derived from the plot in Output 3.31.2. The next example illustrates<br />

how to estimate percentiles using lognormal Q-Q plots.<br />

A sample program, uniex18.sas, for this example is available in the <strong>SAS</strong> Sample<br />

Library for <strong>Base</strong> <strong>SAS</strong> software.<br />

Example 3.32. Estimating Percentiles from Lognormal<br />

Quantile Plots<br />

This example, which is a continuation of the previous example, shows how to use a Q-<br />

Q plot to estimate percentiles such as the 95th percentile of the lognormal distribution.<br />

A probability plot can also be used for this purpose, as illustrated in Example 3.26.<br />

The point pattern in Output 3.31.4 has a slope of approximately 0.39 and an intercept<br />

of 5. The following statements reproduce this plot, adding a lognormal reference line<br />

with this slope and intercept:<br />

symbol v=plus;<br />

title ’Lognormal Q-Q Plot for Diameters’;<br />

proc univariate data=Measures noprint;<br />

qqplot Diameter / lognormal(sigma=0.5 theta=5 slope=0.39 noprint)<br />

pctlaxis(grid)<br />

vref = 5.8 5.9 6.0<br />

square;<br />

run;<br />

The result is shown in Output 3.32.1:

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!