In the documentation below, each SAS command will be briefly described and then the syntax of the command will be specified. The necessary SAS command will always appear in

CHART PROCEDURE Produces vertical and horizontal bar charts, histograms, block charts, pie charts, and star charts.

CORRELATION PROCEDURE Computes Pearson correlation coefficients and nonparametric measures of association.PROC CHART<option list>;

BYvariable-list;

VBARvariable-list/options;

HBARvariable-list/options;

BLOCKvariable-list/options;

PIEvariable-list/options;

STARvariable-list/options;

DATA COMMAND Begins a data step to create a SAS data set.PROC CORR<option list>;

BYvariable-1 <variable-2> ... <variable-n>;

VARvariable-1 variable 2 <variable-3> ... <variable-n>;

FILENAME COMMAND Associates a SAS file reference with an external file.DATAdata-set-name;

INFILE COMMAND Identifies an external file to read with an INPUT statement.FILENAMEfileref 'external filename';

INPUT COMMAND Describes the arrangement of values in an input record and assigns input values to corresponding SAS variables.INFILEfileref;

GPLOT PROCEDURE Plots the values of two or more variables on a set of coordinate axes (X and Y).INPUTvariable-1<variable-2> ... <variable-n>;

PRINT PROCEDURE Prints the obseravations in a SAS data set.PROC GPLOT<options>;

PLOTplot-requests/options;

RANK PROCEDURE Computes ranks for one or more numerical variables and outputs the ranks to a new SAS data set.PROC PRINT<option list>;

VARvariable-list;

REGRESSION PROCEDURE Provides a general-purpose procedure for regression.PROC RANK<options>; NORMAL=BLOM Computes normal scores for assessing normality.

BYvariable-1 <variable-2> ... <variable-n>;

VARdata-set-variables;

RANKSnew variables;

SORT PROCEDURE Sorts observations in a SAS data set by one or more variables.PROC REG<options>; OUTEST=data-set-nameoutputs a data set that contains parameter estimates and other model fit statistics

MODELdependent variable(s) = explanatory variable(s) </options>;

Model Statement Options

ALPHA=

sets significance value for confidence and prediction intervals and tests

CLB

computes confidence limits for the parameter estimates

CLI

computes confidence limits for an individual predicted value

CLM

computes confidence limits for the expected value of the dependent variable

I

displays inverse of sums of squares and crossproducts

NOINT

fits a model without an intercept

P

computes predicted values

PRESS

outputs the PRESS statistic to the OUTEST= data set.

PCORR1

displays squared partial correlation coefficients using Type I sums of squares

PCORR2

displays squared partial correlation coefficients using Type II sums of squares

R

produces analysis of residuals

SELECTION=

specifies model selection method (FORWARD, BACKWARD, STEPWISE, MAXR, MINR, RSQUARE, ADJRSQ, or CP)

SLE=

sets criterion for entry into model

SLS=

sets criterion for staying in model

SS1

displays the sequential sum of squares

SS2

displays the partial sum of squares

XPX

displays sums-of-squares and crossproducts matrix

BYvariable(s);

IDvariable(s);

OUTPUT<OUT=SAS-data-set> keyword-1=name1 ... <keyword-n=name-n>;

Keywords for Output

COOKD = name

Cook's D influence statistic

DFFITS = name

standard influence of observation on predicted value

H = name

leverage

LCL = name

lower bound of a confidence interval for an individual prediction

LCLM = name

lower bound of a confidence interval for the expected value (mean) of the dependent variable

PREDICTED (or P) = name

predicted values

PRESS = name

ith residual divided by (1-h), where h is the leverage and the model has been refit without the ith observation

RESIDUAL (or R) = name

residuals, caclulated as observed-predicted

RSTUDENT = name

a studentized residual with the current observation deleted

STDI = name

standard error of the individual predicted value

STDP = name

standard error of the mean predicted value

STDR = name

standard error of the residual

STUDENT = name

studentized residuals, residuals divided by their standard errors

UCL = name

upper bound of a confidence interval for an individual prediction

UCLM = name

upper bound of a confidence interval for the expected value (mean) of the dependent variable

PLOT<y-variable*x-variable>;

RESTRICTequation1 <equation2> ... <equationn>;

UNIVARIATE PROCEDURE Produces simple descriptive statistics.PROC SORT<option list>;

BYvariable-list;

PROC UNIVARIATE<option list>;

VARvariable-list;

BYvariable-list;