# Lab 2 - Copying data directly into the data step

We will work with the billionaire dataset again today. You may either download it and read it in from the file on disk, or you may copy it directly into your data step.

Here is the code for including the data in the data step.

```
data billion ; * gives dataset a name for SAS ;
input wlth age region $ ; * names the variables in each row ;
* $ after region identifies character vbl;
datalines ;
37 50 M
24 88 U
14 64 A
.
.
.
1 59 E
1 . E
1 . O
;
run ; * end of data step;
```

## Using SAS procedures to list and tabulate the dataset

Once the dataset is created, you may run SAS *procedures* to analyze it.

To list the entire dataset:

```
proc print data = billion ;
run ;
```

To get a frequency distribution of the regions in which billionaires lived:

```
proc freq data = billion ;
tables region ;
run ;
```

Note that `tables`

is a keyword. `region`

is the name of the variable for which you want counts.

The output is:

```
The FREQ Procedure
Cumulative Cumulative
region Frequency Percent Frequency Percent
-----------------------------------------------------------
A 38 16.31 38 16.31
E 80 34.33 118 50.64
M 22 9.44 140 60.09
O 29 12.45 169 72.53
U 64 27.47 233 100.00
```

## Proc univariate: SAS workhorse of descriptive statistics

Use `proc univariate`

for quantitative variables when you want the
following:

- means
- medians
- quartiles
- 5-number summary
- stem plots (for small datasets) or histograms (large datasets)
- boxplots

```
* ods listing;
* ods graphics off ; Use these two if you don't see stem and leaf plot ;
proc univariate plot data = billion ;
var wlth ;
run ;
```

The output is:

```
The UNIVARIATE Procedure
Variable: wlth
Moments
N 233 Sum Weights 233
Mean 2.68154506 Sum Observations 624.8
Std Deviation 3.31884032 Variance 11.0147011
Skewness 6.57544276 Kurtosis 56.9655987
Uncorrected SS 4230.84 Corrected SS 2555.41064
Coeff Variation 123.765972 Std Error Mean 0.21742446
Basic Statistical Measures
Location Variability
Mean 2.681545 Std Deviation 3.31884
Median 1.800000 Variance 11.01470
Mode 1.000000 Range 36.00000
Interquartile Range 1.70000
Tests for Location: Mu0=0
Test -Statistic- -----p Value------
Student's t t 12.33323 Pr > |t| <.0001
Sign M 116.5 Pr >= |M| <.0001
Signed Rank S 13630.5 Pr >= |S| <.0001
Quantiles (Definition 5)
Quantile Estimate
100% Max 37.0
99% 14.0
95% 6.2
90% 4.5
75% Q3 3.0
50% Median 1.8
25% Q1 1.3
10% 1.1
5% 1.0
1% 1.0
0% Min 1.0
Extreme Observations
----Lowest---- ----Highest---
Value Obs Value Obs
1 233 13 4
1 232 13 5
1 231 14 3
1 230 24 2
1 229 37 1
```

```
Histogram # Boxplot
37+* 1 *
.
.
.
.
.
.* 1 *
.
.
19+
.
.* 1 *
.* 2 *
.* 2 *
.* 2 0
.* 3 0
.******** 23 0
.************************ 72 +--+--+
1+****************************************** 126 *-----*
----+----+----+----+----+----+----+----+--
* may represent up to 3 counts
-2 -1 0 +1 +2
```

## Bar graphs and pie charts

```
goptions device = win ;
pattern v = solid color = gray ;
proc gchart data = billion ;
vbar region ;
title 'Billionaires in 1992; Regions ' ;
run ;
proc gchart data = billion ;
pie region ;
title 'Billionaires in 1992; Regions ' ;
run ;
```

## Histograms for quantitative variables

```
proc gchart data = billion ;
vbar wlth / space = 0 ;
title 'Billionaires in 1992; Wealth in Billions ' ;
run ;
```

## Printing and Saving Files

Copying output from SAS windows into Microsoft Word will enable you to edit the SAS output and incorporate it into your homework writeups. You can then print from Word. When you highlight a block of text in the SAS output window in order to copy it, do not highlight all the way to the right margin of the last line. Due to a bug in SAS, that prevents the copy from working.

To save a file, click in the window whose contents you want to save. Go to the file menu and choose `Save as`

. Navigate to where you wish to save the file. Your H: drive is a good choice, since SAS can see it from the Virtual Desktop. SAS will automatically give the file extension `.sas`

to SAS commands and programs. For example, to name a SAS program `myprog`

, you would type

`myprog`

in the box for the name of the file.