Introduction to sas

What is SAS?
• SAS (Statistical Analysis System
• Software suite developed by SAS Institute for
advanced analytics, business intelligence, data
management, and predictive analytics
• Developed at North Carolina State University from
1966 until 1976, when SAS Institute was
incorporated.
• Further developed in the 1980s and 1990s with
the additional statistical procedures and
components

Components of SAS
Currently, SAS has more than 200 components,
some of them are –
• Base SAS – Basic procedures and data
management
• SAS/STAT – Statistical analysis
• SAS/GRAPH – Graphics and presentation
• SAS/OR – Operations research
• SAS/ETS – Econometrics and Time Series Analysis
• SAS/IML – Interactive matrix language

SAS University Edition
http://www.sas.com/en_in/software/university-edition/download-software.html
https://welcomedata.wordpress.com/2015/03/13/downloading-and-installing-sas-university-edition/

SAS Interface
• Code Editor where we write and modify mode
• Log is a record of everything that we do in SAS
session or SAS program :-
– Program statements identified by line numbers
– Messages that begin with NOTE, INFO, WARNING,
ERROR, or an error number
– Process time
• Result displays printed output

SAS Explorer
• All libraries, folders ,
files that include data,
saved code and saved
output can be found
here

SAS Language
• SAS program consists of SAS Statements
• Each SAS Statement end with a semi-colon (;)
• Basic SAS Statements are :
– Data Step
– Proc Step
DATA Step – used to create or modify data sets
PROC Step (Procedure) - pre-written rules that analyze
and process data in a SAS dataset and then produce a
report

SAS Language
• A SAS program can consist of a DATA step or a
PROC step or any combination of DATA and
PROC steps.
• Data Step and Proc Step are followed by Run
Statement.
• SAS statements are free-format –
– they can begin and end anywhere on a line
– one statement can continue over several lines
• To Comment use (/*Comment*/)

Class Assignment
Create a cheat sheet for yourself of the code
that you run in the class.
Add short comments for each program or each
new step.
Submit the cheat sheet at the end of the class.

Create Temporary Data set
i. There are six SAS statements.
ii. DATA step – creates a new dataset
called first.
iii. PROC step – prints/displays that dataset in
the results/output window.

PROC Step
• Proc PRINT
• Proc DATASETS
• Proc CONTENTS
• Proc SORT
• Proc FREQ
• Proc MEANS
• Proc UNIVARIATE
• Proc CORR

• Input Statement –
– Input variable names,
– Describes arrangement of values in the
input data record and assigns
• Datalines/Cards Statement indicates
that existence of data lines below
In the above program:
i. There are seven SAS statements;
ii. The INPUT statement defines the variables to
be read in each line of data.
iii. The DATALINES statement indicates to SAS
that DATA step statements are completed and
the next line contains real data.
iv. Notice that the lines of data do not end in a
semicolon.

Missing values for Character variable o?
Let us check Log for errors

For character variable add “$” after variable name in Input statement

SAS Options
Here, PROC
step prints
only the
first 4
observation
s of the data
set third

SAS Options
Here, PROC step
prints the data
set third
beginning with
observation 2
till observation
4

SAS Libraries
Permanent Libraries (Default) –
• SASHELP – contains sample data
sets
• SASUSER – stores personal files
Temporary Library –
WORK – stores files only for current
session

SAS Files
Rules for data set names –
• i. 1 to 32 characters
• ii. must begin with an alphabet A-Z(uppercase or lowercase) or
underscore
• ii. can continue with any combination of alphabets, numbers or
underscores
Referencing SAS Files
• Two-Level Names
• To reference a permanent SAS data set in your SAS programs, we
use a two-level name
• library name and the filename, or data set name:
• libref.filename

PROC Datasets
PROC DATASETS is used
• to list, copy, remove, or delete SAS files.
• to change variable information such as name,
format, informat and label.
PROC Datasets does not require RUN Statement

PROC Datasets
The SAS log gives the name of all SAS datasets in the
library called SASHELP

PROC Datasets – CHANGE Statement
In the following program, we change the name of
dataset first to one using CHANGE Statement.

PROC Datasets – DELETE
Statement
In the following program, we delete dataset one
using DELETE Statement.

Create data set using existing datasetrun
• Use SET Statement and create a temporary data set for use
in current session from an existing data set
• Print the new data set using PROC Print
• Try and see what the following program will do

PROC Print – TITLE
As the name suggests, TITLE Statements adds Title
while printing the output.

PROC Print – SUM
To generate Column totals use SUM Statement
within PROC Step

PROC Sort
Here, PROC Sort is used to create a sorted
dataset in ascending order according to team
variable.

Calculate Subtotals
Here, we calculate and print Subtotals for nhits
sorted by variable team.

PROC Contents
PROC Contents -
• provides information for SAS datasets or libraries
• it gives the name of the dataset or library, the
location, when it was created, the host that
created it, and the time of the last modification.
• For datasets it also provides the number of
observations in the dataset, and attributes for
each variable

PROC Contents
The following program requests information for sashelp.baseball
dataset using PROC Contents.

PROC Freq
PROC FREQ –
• Counts the number (frequency) of occurrences of
each variable(both character and numeric).
• Gives statistics from the data
• Produces one- way to n-way frequency and cross-
tabulation tables.
• Produces printed output by default.
• Lists each variable value along with the
frequencies and percentages.

PROC Freq
The following program demonstrates the
simplest form of PROC FREQ and produces the output
The output of this program is too long for our purpose to include here.
Add TABLES Statement to limit the output for only one
variable and create a one-way frequency table

PROC Freq
Create two-way cross-tabulation tables :
In the TABLES statement, state the variable names
separated by asterisk

PROC Means
PROC MEANS –
• produces statistics for numeric variables.
• produces printed output by default
• computes N, MEAN, STD, MIN and MAX by
default
• similar to PROC SUMMARY however, PROC
SUMMARY does not produce a printed output
by default.

PROC Means
The following shows simplest use of PROC MEANS procedure.

PROC Means – VAR
VAR statement –
• selects specified variable ,
• Identifies the analysis variables and their order in the output.

PROC Means – Statistic
To obtain a specific statistic you must state it in the PROC
MEANS statement.

PROC Means – Class
• The CLASS statement assigns variables used to form subgroups.
• CLASS variables can be either numeric or character.

PROC Means – Output
Output Statement stores result in new data set.
Here, the new data set is baseball_new.

PROC Univariate
PROC UNIVARIATE
• Examines distribution for numeric variables.
• produces printed output by default
The following shows simplest use of PROC Univariate procedure.

PROC Univariate – NORMAL
NORMAL Option requests for tests for normality that include a series of
goodness-of-fit tests based on the empirical distribution function.

PROC Univariate – PLOT
PLOT Option in PROC Univariate produces a stem-
and-leaf plot (or a horizontal bar chart), a box
plot, and a normal quantile plot

Incrementing Loop
Here the i is being incremented by 2 in the loop

Dropping Variable
Here, we create a dataset Sixth. We run a loop
using a new variable i, but drop it so that it
does not include in the dataset.

Decrementing Loop
Here the i is being decremented by 2 in the loop

Dataset using Raw file
1. Create a new folder in myfolders and call it
mine.
2. Use libname statement to create a new SAS
library called mine. How do we get the path
of mine?

3. Upload diamonds.csv dataset into the mine
folder
4. Check the folder

PROC Import
We use Proc IMPORT to import the dataset.
• OUT Option specifies a name for SAS data set
• DATAFILE Statement specifies the location/path of the uploaded
file.
• DBMS Statement indicates the type of uploaded file.
• GETNAMES Statement tells SAS whether the first row of the data
values is to be considered as variable names or not(Yes - if to be
considered as variable names).

Check the MINE Library
Create a temporary data set called diamonds,
using the existing data set.

PROC Corr
Correlation is one of the first steps to
understand the relationship between
variables. To compute correlation in SAS, we
use PROC CORR.
Corr Procedure calculates pairwise correlation
for Numeric variables. This procedure also
provides some summary statistics by default -
Mean, Standard Deviation, Sum, Minimum and
Maximum.

Assignment
Make use of the procedures learnt in the class
to compute statistics for diamonds data set.
https://vincentarelbundock.github.io/Rdatasets/csv/Ecdat/Diamond.csv

SAS DOCUMENTATION = Hallelujah!
http://support.sas.com/documentation/

PROC SQL
http://www2.sas.com/proceedings/sugi27/p191-27.pdf

MACRO LANGUAGE
https://v8doc.sas.com/sashtml/macro/znemacro.htm

ODS
http://support.sas.com/rnd/base/ods/scratch/ods-tips.pdf

Data Visualization using SAS
Use Tasks
see https://welcomedata.wordpress.com/2015/03/23/quick-pie-charts-in-sas-university-edition/

Modeling using SAS
proc reg data=sashelp.cars;
model MPG_City = Cylinders Weight ;
run;

Modeling using SAS
Try this
proc reg data=sashelp.iris;
model SepalLength = SepalWidth PetalLength PetalWidth ;
run;
NOW TRY THIS
proc reg data=sashelp.iris;
model SepalLength = SepalWidth PetalLength PetalWidth /vif collin;
run;

Modeling using SAS : Multicollinearity
http://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.
htm#statug_reg_sect038.htm

Modeling using SAS : PROC LOGISTIC
proc logistic data=sashelp.Bmt;
class Group;
model Status=Group;
run;

Modeling using SAS : PROC LOGISTIC
proc logistic data=sashelp.
Bmt;
class Group;
model Status=Group;
run;

Questions or Feedback
Email us at
info@decisionstats.org

Introduction to sas

More Related Content

What's hot (20)

Viewers also liked (10)

Similar to Introduction to sas (20)

More from Ajay Ohri (20)

Recently uploaded (20)

Introduction to sas