Showing posts with label substitute function. Show all posts
Showing posts with label substitute function. Show all posts

Tuesday, June 5, 2012

Example 9.34: Bland-Altman type plot

The Bland-Altman plot is a visual aid for assessing differences between two ways of measuring something. For example, one might compare two scales this way, or two devices for measuring particulate matter.

The plot simply displays the difference between the measures against their average. Rather than a statistical test, it is intended to demonstrate both typical differences between the measures and any patterns such differences may take. The utility of the plot, as compared with linear regression or sample correlation is that the plot is not affected by the range, while the sample correlation will typically increase with the range. In contrast, linear regression shows the strength of the linear association but not how closely the two measures agree. The Bland-Altman plot allows the user to focus on differences between the measures, perhaps focusing on the clinical relevance of these differences.

A peer reviewer recently asked a colleague to consider a Bland-Altman plot for two methods of assessing fatness: the familiar BMI (kg/m^2) and the actual fat mass measured by a sophisticated DXA machine. These are obviously not measures of the same thing, so a Bland-Altman plot is not exactly appropriate. But since the BMI is so simple to calculate and the DXA machine is so expensive, it would be nice if the BMI could be substituted for DXA fat mass.

For this purpose, we'll generate a modified Bland-Altman plot in which each measure is first standardized to have mean 0 and standard deviation 1. The resulting plot should be assessed for pattern as usual, but typical differences must be considered on the standardized scale-- that is, differences of a unit should be considered large, and good agreement might require typical differences of 0.2 or less.

Since this is a job we might want to repeat, we'll build a SAS macro to do it. This will also demonstrate some useful features. The macro accepts a data set name and the names of two variables as input. We'll comment on interesting features in code comments. If you're an R coder, note that SAS macro variables are merely text, not objects. We have to manually assign "values" (i.e., numbers represented as text strings) to newly created macro variables.

%macro baplot(datain=,x=x,y=y);

/* proc standard standardizes the variables and saves the results in the
same variable names in the output data set. This means we can continue
using the input variable names throughout. */
proc standard data = &datain out=ba_std mean=0 std=1;
var &x &y;

/* calculate differences and averages */
data ba;
set ba_std;
bamean = (&x + &y)/2;;
badiff = &y-&x;

ods output summary=basumm;
ods select none;
proc means data = ba mean std;
var badiff;
ods select all;

/* In the following, we take values calculated from a data set for the
confidence limits and store them in macro variables. That's the
only way to use them later in code.
The syntax is: call symput('varname', value);
Note that 'bias' is purely nominal, as the standardization means that
the mean difference is 0. */
data lines;
set basumm;
call symput('bias',badiff_mean);
call symput('hici',badiff_mean+(1.96 * badiff_stddev));
call symput('loci',badiff_mean-(1.96 * badiff_stddev));

/* We use the macro variables just created in the vref= option below;
vref draws reference line(s) on the vertical axis. lvref specifies
a line type. */
symbol1 i = none v = dot h = .5;
title "Bland-Altman type plot of &x and &y";
title2 "&x and &y standardized";
proc gplot data=ba;
plot badiff * bamean / vref = &bias &hici &loci lvref=3;
label badiff = "difference" bamean="mean";
%mend baplot;

Here is a fake sample data set, with the plot resulting from the macro shown above. An analysis would suggest that despite the correlation of 0.59 and p-value for the linear association < .0001, that these two measures don't agree too well.

data fake;
do i = 1 to 50;
/* the "42" in the code below sets the seed for the pseudo-RNG
for this and later calls. See section 1.10.9. */
x = normal(42);
y = x + normal(0);

%baplot(datain=fake, x=x, y=y);

Paralleling SAS, we'll write a small function to draw the plot, annotating within to highlight some details. If you're primarily a SAS coder, note the syntax needed to find the name of an object submitted to a function. In contrast, assigning values to new objects created with the function is entirely natural. The resulting plot is shown below.

# set seed, for replicability
x = rnorm(50)
y = x + rnorm(50)

baplot = function(x,y){
xstd = (x - mean(x))/sd(x)
ystd = (y - mean(y))/sd(y)

bamean = (xstd+ystd)/2
badiff = (ystd-xstd)

plot(badiff~bamean, pch=20, xlab="mean", ylab="difference")
# in the following, the deparse(substitute(varname)) is what retrieves the
# name of the argument as data
title(main=paste("Bland-Altman plot of x and y\n",
deparse(substitute(x)), "and", deparse(substitute(y)),
"standardized"), adj=".5")
#construct the reference lines on the fly: no need to save the values in new
# variable names
abline(h = c(mean(badiff), mean(badiff)+1.96 * sd(badiff),
mean(badiff)-1.96 * sd(badiff)), lty=2)


An unrelated note about aggregators:We love aggregators! Aggregators collect blogs that have similar coverage for the convenience of readers, and for blog authors they offer a way to reach new audiences. SAS and R is aggregated by R-bloggers, PROC-X, and statsblogs with our permission, and by at least 2 other aggregating services which have never contacted us. If you read this on an aggregator that does not credit the blogs it incorporates, please come visit us at SAS and R. We answer comments there and offer direct subscriptions if you like our content. In addition, no one is allowed to profit by this work under our license; if you see advertisements on this page, the aggregator is violating the terms by which we publish our work.

Tuesday, September 7, 2010

Example 8.4: Including subsetting conditions in output

A number of analyses perform operations on subsets. Making it clear what observations have been excluded or included is helpful to include in the output.


The where statement (section A.6.3) is a powerful and useful tool for subsetting on the fly. (Other options for subsetting typically require data steps or data set options in the proc statement.) But one problem with subsetting in SAS is that the output doesn't show the conditioning. This is a little macro to correct this problem:

%macro where(wherest, titleline);
where &wherest;
title&titleline "where %str(&wherest)";
%mend where;

If you use %where(condition, n); in place of where condition; the condition is both implemented and will appear in the output as the nth title line. This takes advantage of the fact that the title statements just need to appear before the procedure is run, as opposed to before the proc statement.

For example:

title "HELP data set";
proc means data="c:\book\help.sas7bdat";
%where (female eq 1,2);
var age;

Produces the output:

HELP data set
where female eq 1

The MEANS Procedure

Analysis Variable : AGE


Note that you need to use the testing forms such as eq and not the assignment = in your where statements for this to work.

This tip is cross-posted on my list of SAS tricks.


Within R, many functions (e.g. lm()) provide support for a subset option (as in example 3.7.5). Indexing can be used to restrict analyses (B.4.2). In addition, the subset() function can be embedded in a function call to make explicit what subset of observations will be included in the analysis. We demonstrate calculating the mean of female subjects all three ways below.

> ds = read.csv("")
> coef(lm(age ~ 1, subset=female==1, data=ds))
> mean(ds$age[ds$female==1])
[1] 36.25234
> mean(subset(ds,female==1,age))

In interactive R the code and output lie together and it is usually trivial to trace the subsetting used to produce output. But in literate programming settings, or when output may be cut-and-pasted from R to a document, it may be valuable to mirror the SAS macro presented above.

Here is a function to display the subsetting condition for simple functions. It requires some sophistication to turn expressions and variables into objects (and vice-versa). The use of deparse(substitute()) allows us to create a character variable with the name of the subset condition and function, while eval() is used to pass the name of the variable to the subset() function. A similar functionality for more complex functions (such as those requiring a formula, would require some tweaking; a generic explicit subsetting function could be difficult.

verbose.subset = function(ds, condition, variable, FUN=mean) {
cat(paste("subsetting with condition: ",
"\n", sep=""))
cat(paste("calling the function: ",
"\n", sep=""))
FUN(subset(ds, condition, select=eval(variable)))

This yields the following output:

> verbose.subset(ds, female==1, "age")
subsetting with condition: female == 1
calling the function: mean