Index

A

accessing data from hard drive 39–44

Akaike's information criteria (AIC) 177, 188

analysis of variance (ANOVA)

about 113

N-Way 131–144

performing nonparametric one-way tests 124–128

performing one-way 114–124

analyzing

categorical data 193–210

tables with low expected values 208–210

asterisk (*) 52

B

backward slashes 29

binary logistic regression

about 183

preparing birth weight data set for 183–190

selecting reference levels for models 190–191

blank lines, in SAS statements 48

blanks, in folder names 42

BOOK library 14

BOOKDATA library 148, 150–151, 164, 184, 195–196

box plots, requesting 71–73

built-in tasks 12–13

C

calculating

See also power

See also sample size

chi-square from frequency data 206–208

one-way frequencies 195–197

sample size for a test of proportions 219–223

sample size for one-way ANOVA design 223–225

case sensitivity

in folder names 41

on Microsoft platforms 29

categorical data

about 193

analyzing tables with low expected values 208–210

computing chi-square from frequency data 206–208

computing one-way frequencies 195–197

creating formats 198–200

creating one-way tables with formats 200

creating two-way tables 201–203

Heart_Attack data set 194

reordering table rows and columns using formats 203–206

categorical variables 78–81

CHANGE button 34

character variables, setting length of 61–62

chi-square, computing from frequency data 206–208

CLASS statement 190

classification variables, adding in Summary Statistics tab 76–78

code, editing generated by One-Way Frequencies Statistics task 81–82

CODE area 13, 48

Cody, Ron

An Introduction to SAS University Edition 1, 47, 64, 199

Learning SAS by Example 47, 64, 199

columns

See also variables

importing Excel workbooks with no column headings 38

moving 20

resizing 19

sorting 21–22

COMMENT statement 52, 55, 184

comparing more than two means

See analysis of variance (ANOVA)

confidence interval 70–71, 99

continuous variables, generating descriptive statistics for 68–73

Cook's D 171

correlation

about 147

creating permanent SAS data sets 147–152

creating Correlation and scatter plot matrices 155–160

creating Spearman non-parametric correlations 160–161

interpreting correlation coefficients 160

reading Exercise.xls workbook 151–152

using Statistics Correlation task 152–154

correlation coefficients, interpreting 160

Correlation matrix 155–160

CSV files

about 29

importing data from 38–39

reading 59–60

CUMFREQPLOT 82

D

data

accessing from hard drive 39–44

importing 27–45

importing Excel workbooks with invalid SAS variable names 37

importing from CSV files 38–39

listing SAS Data set 35–36

reading from shared folders 44–45

reading from text files 47–64

Utilities tab 28–29

values, separated by delimiters 49–58

data sets 35–36

See also tables

DATA statement 55, 199

DATA tab 68, 74, 76, 79

DATASETS procedure 38

delimiters

data values separated by 49–58

reading text files with other 60–61

descriptive statistics

about 67

adding classification variables in Summary Statistics tab 76–78

categorical variables 78–81

distribution for systolic blood pressure 74–76

editing SAS code generated by One-Way Frequencies Statistics task 81–82

generating for continuous variables 68–73

diagnostic plots 169–171

distribution, for systolic blood pressure 74–76

DLM= option 60–61

dollar sign ($) 55

downloading SAS University Edition 2–6

DSD option 60

E

EDIT button 82

errors, viewing 58–59

Excel workbooks

about 29

importing data from 29–35

importing with invalid SAS variable names 37

importing with no column headings 38

Exercise.xls workbook, reading 151–152

F

F test 99

File Save icon 58

files

case sensitivity and names of 29

CSV 29

selecting to import 31

XLS 29

filtering

rows 23

tables 22–24

filters, removing 23

Fisher's Exact test 208–210

fixed columns, reading text data in 62–64

folders, shared 39–44

FORMAT procedure 198–200

FORMAT statement 199

formats

creating 198–200

creating one-way tables with 200

reordering table rows/columns using 203–206

FREQ procedure 81, 203–204

FREQPLOT 82

frequency data, computing chi-square from 206–208

F-value 139

H

hard drive, accessing data from 39–44

HEART library 15

Heart_Attack data set 194

histograms 71–73, 98, 120

horizontal scroll bars 18

I

Import Utility 60, 86–87, 108

importing

data 27–45, 38–39

data from CSV files 38–39

Excel workbooks with invalid SAS variable names 37

Excel workbooks with no column headings 38

INFILE statement 55, 60–61, 64

Information Center screen 12

informats 63

INPUT statement 55, 61–62, 63

interpreting

correlation coefficients 160

models with significant interactions 143–144

results of N-Way ANOVA 141–143

An Introduction to SAS University Edition (Cody) 1, 47, 64, 199

K

Kruskal-Wallis test 127

kurtosis 75

L

Learning SAS by Example (Cody) 47, 64, 199

length, setting of character variables 61–62

LENGTH statement 61–62

Levin's test of homogeneity of variance 121

LIBNAME statement 148, 150

LIBRARIES tab 14–19, 35

linear regression 164–169

lines, in SAS statements 48

listing SAS Data set 35–36

LOG area 13, 48

logistic regression 183–191

LSMEANS 142–143

M

Menu icon 53

models, selecting reference levels for 190–191

moving columns 20

multiple regression

about 163

demonstrating 171–175

stepwise 176–181

MYFMTS library 14

N

names, in SAS 49

Navigation pane 13

NOCUM option 81–82

nonparametric one-sample tests 93

nonparametric one-way tests 124–128

nonparametric two-sample tests 101–107

N-Way ANOVA

about 131

interpreting models with significant interactions 143–144

interpreting results of 141–143

performing two-way ANOVA 131–141

using 134–141

O

one-sample tests

about 85

nonparametric 93

performing one-sample t tests 85–93

one-way ANOVA

computing sample size for 223–225

performing 114–124

one-way frequencies 79, 81–82, 195–197

one-way tables 200

OPTIONS tab 33, 69–70, 74, 79

Oracle VM VirtualBox 1–2

ORDER= option 203–204

P

PAD option 64

paired t test 107–111

Pearson correlation coefficient 153–154

permanent SAS data sets, creating 147–152

PLOT statement 224

PLOTS= option 81

plus (+) sign 23, 41

power 213

POWER procedure 223–225

Preferences menu 53

PRINT procedure 185, 199

Programmer Mode 13

programs rules 48–49

p-value 98–99, 121–122, 139

Q

Q-Q plot 74–75, 91–92, 98, 118–119, 170

QUIT statement 48

R

random samples, selecting 131–134

reading

CSV files 59–60

data from shared folders 44–45

data from text files 47–64

Exercise.xls workbook 151–152

text data in fixed columns 62–64

text files 49–58

text files with other delimiters 60–61

reference levels, selecting for models 190–191

regression, multiple 171–175, 176–181

removing filters 23

reordering table rows/columns using formats 203–206

resizing columns 19

Resources link 12

restarting virtual machines 43

RESULTS area 13, 48, 56

rows

See observations

filtering 23

subsetting 22–24

R-square 173–174, 177

RUN icon 36, 56, 71, 103, 105

RUN statement 48, 55, 185, 199

S

sample size

about 213

calculating for a test of proportions 219–223

computing for one-way ANOVA designs 223–225

computing for t tests 214–218

SAS Studio

See also specific topics

about 9–12

opening 12

using built-in tasks 12–13

SAS University Edition

about 1–2

downloading 2–6

SASHELP library 15, 68, 148

SBC (Schwarz Bayesian Information Criterion) 176–181

SC (Schwarz Criterion) 188–189

scatter plot matrices 155–160

Schwarz Bayesian Information Criterion (SBC) 176–181

Schwarz Criterion (SC) 188–189

scroll bars 18

semicolon (;) 48

SET statement 184, 199

shared folders 39–45

simple regression

about 163

diagnostic plots 169–171

linear 164–169

skewness 75

sorting columns 21–22

Spearman non-parametric correlations 160–161

Start SAS Studio button 12

Statistics Correlation task 153–154

Statistics tab 79

Statistics Task menu 68

stepwise multiple regression 176–181

Student-Newman-Keuls test 123

subsetting rows 22–24

Summary Statistics tab, adding classification variables in 76–78

systolic blood pressure, distribution for 74–76

T

t tests

computing sample size for 214–218

for independent groups 95–101

one-sample 85–93

tables

analyzing with low expected values 208–210

filtering 22–24

reordering rows/columns using formats 203–206

TABLES statement 81

test of proportions, calculating sample size for a 219–223

text data, reading in fixed columns 62–64

text files

reading 49–58

reading data from 47–64

reading with other delimiters 60–61

TITLE statement 82

two-sample tests

about 95

nonparametric 101–107

paired t test 107–111

unpaired t test 95–101

two-way ANOVA 131–141

two-way tables 201–203

U

underscore (_) 49

univariate analysis

See descriptive statistics

unpaired t test 95–101

Update icon 12

Utilities tab 28–29

V

VALUE statement 198–200

values

analyzing tables with low expected 208–210

selecting 24

variable names, importing Excel workbooks with invalid 37

variance inflation factor (VIF) 173–175

vertical scroll bars 18

virtual computer

defined 1–2

restarting 43

starting 9

VirtualBox 9–11

VMware Fusion 2

VMware Player 2

VMware Workstation Player 2

W

warnings, viewing 58–59

WHERE statement 102, 125, 184

Wilcoxon Rank Sum Test 105

Wilcoxon Signed Rank test 93

work area 13, 48

WORK library 14, 34, 36, 147–148, 176, 202

workbooks, Excel 29

X

XLS files 29

Y

Yesno format 199