Translation Syntax – Not Published

GET FILE="/path/to/file.sav".

use "/path/to/file.dta"

LIBNAME myFolder "P:\QAC\QAC201\study name"; 
data new; set myFolder.filename; 

load ("/path/to/file.Rdata")
myData_orig <- objectName

# If calling in from a text file:
myData_orig <- read.table(file = "/path/to/file.txt", sep = "\t", header = TRUE)

* put this as a subordinate of the SAVE OUTFILE command; the outfile will only contain that specified variables.
/KEEP VAR1 VAR2 VAR3 VAR4 VAR5 VAR6 VAR7 VAR8.

use VAR1 VAR2 VAR3 VAR4 VAR5 VAR6 VAR7 VAR8 /// 
   using "P:\QAC\qac201\Studies\study name\filename", clear

* put this code inside a data step;
KEEP VAR1 VAR2 VAR3 VAR4 VAR5 VAR6 VAR7 VAR8; 

var.keep <- c("VAR1", "VAR2", "VAR3", "VAR4", "VAR5", "VAR6", "VAR7", "VAR8")
myData <- myData_orig[ ,var.keep]

SAVE OUTFILE= "/path/to/outfile.sav".

save "/path/to/outfile.dta"

LIBNAME myFolder "/path/to/outFolder";
data myFolder.outfile; set tempfile; by unique_id; 

# write as csv
write.table(myData, file = "/path/to/outfile.csv", sep = ",", row.names = FALSE)

# write as .RData
save(file = "/path/to/outfile.RData", myData)

SORT CASES BY var.

sort var

proc sort; by var; 

myData <- myData[order(myData$var, decreasing = FALSE), ]

*must be added as a command option.
/SELECT=diabetes2 EQ 1 

// create a subset from the data
if diabetes2==1

// if running a procedure on a subset of the data (format: procedure [arguments] if [condition]). for example,
reg height weight if diabetes2==1

* inside the data step;
if diabetes2=1; 

# create a subset of the data 
myDataSubset <- myData[myData$diabetes2 == 1, ]

RECODE VAR1 (9=SYSMIS). 

replace VAR1=. if VAR1==9 

* inside the data step;
if VAR1=9 then VAR1=.;

myData$VAR1[myData$VAR1 == 9 ] <- NA

RECODE TREE ('Maple'=1) ('Oak'=2) INTO TREE_N.

generate TREE_N=.
replace TREE_N=1 if TREE=="Maple"
replace TREE_N=2 if TREE=="Oak"

// OR
encode TREE, gen(TREE_N) 

* inside the data step;
if TREE='Maple' then TREE_N=1;
else if TREE= 'Oak' then TREE_N=2;

# Usually not necessary in R.

COMPUTE new_region=2. 
IF (region=1|region=2|region=3|region=5|region=6) new_region=1.

generate new_region =2
replace new_region=1 if region==1|region==2|region==3|region==5|region==6 

// OR
recode region (1/3 5 6=2), gen(new_region)

* inside the data step;
if region=1 or region=2 or region=3 or region=5 or region=6 then new_region=1;
else if region=4 or region=7 or region=8 or region=9 then new_region=2;

condition1 <- myData$region == 1|myData$region == 2|myData$region == 3|myData$region == 5|myData$region == 6
myData$new_region[condition] <- 1

condition2 <- myData$region == 4|myData$region == 7|myData$region == 8|myData$region == 9
myData$new_region[condition2] <-2 

IF (socphob=1|gad=1|specphob=1|panic=1|agora=1|ocd=1) anxiety=1.
RECODE anxiety (SYSMIS=0). 

gen anxiety=1 if socphob==1|gad==1|specphob==1|panic==1|agora==1|ocd==1
replace anxiety=0 if anxiety==.

* inside the data step;
if socphob=1 or gad=1 or specphob=1 or panic=1 or agora=1 or ocd=1 then anxiety=1; 
else anxiety=0;

myData$anxiety <- NA
myData$anxiety[myData$socphob == 0&myData$gad==0&myData$panic == 0&myData$agora==0&myData$ocd == 0] <- 0
myData$anxiety[myData$socphob == 1|myData$gad==1|myData$panic == 1|myData$agora==1|myData$ocd == 1] <- 1

COMPUTE nd_sum=sum(nd_symptom1 nd_symptom2 nd_symptom3 nd_symptom4).

egen nd_sum=rsum(nd_symptom1 nd_symptom2 nd_symptom3 nd_symptom4) 

* inside the data step;
nd_sum=sum(of nd_symptom1 nd_symptom2 nd_symptom3 nd_symptom4);

myData$nd_sum <- myData$nd_symptom1+myData$nd_symptom2+myData$nd_symptom3+myData$nd_symptom4

VARIABLE LABELS VAR1 'label'.

label variable VAR1 "label"

* inside the data step;
LABEL VAR1='label'; 

# no built-in label tags for variables

* no actual rename function, this will create a copy of the variable with the desired name.
COMPUTE newvarname=VAR1.

rename VAR1 newvarname

* inside the data step;
RENAME VAR1=newvarname;

names(myData)[names(myData)== "VAR1"] <- "newvarname"

VALUE LABELS VAR1 0 'value0label' 1 'value1label' 2 'value2label' 3 'value3label'.

label define labelName 0 "value0label" 1 "value1label" 2 "value2label" 3 "value3label"
label values VAR1 labelName

* Set up format before the data step;
proc format; VALUE FORMATNAME 0="value0label" 1="value1label" 2="value2label" 3="value3label";

data myData; set myData;
   * other data management procedures;
	format VAR1 FORMATNAME.
   run;

# get order of the values
levels(myData$VAR1) 

# input the labels in the same order as how the values were printed above
levels(myData$VAR1) <- c("value0label", "value1label", "value2label", "value3label")

FREQUENCIES VARIABLES=CategVar1 CategVar2 CategVar3
   /ORDER=ANALYSIS. 

tab1 CategVar1 CategVar2 CategVar3

proc freq; tables CategVar1 CategVar2 CategVar3; 

library(descr) # install library if needed
freq(as.ordered(myData$CategVar1))
freq(as.ordered(myData$CategVar2))
freq(as.ordered(myData$CategVar3))

DESCRIPTIVES VARIABLES=QuantVar1 QuantVar2 QuantVar3
   /STATISTICS=MEAN STDDEV. 

summarize QuantVar1 QuantVar2 QuantVar3

proc means; var QuantVar1 QuantVar2 QuantVar3; 

# Repeat for each variable 
summary(myData$QuantVar1) 
mean(myData$QuantVar1, na.rm = TRUE) 
sd(myData$QuantVar1, na.rm = TRUE)

* numbers.
CROSSTABS
   /TABLES=CategResponseVar by CategExplanatoryVar 
   /CELLS COUNT ROW COLUMN TOTAL. 

* visualization: use GUI point-and-click. 

// numbers
tab CategResponseVar CategExplanatoryVar, row column cell

// visualization
graph bar (mean) CategResponseVar, over(CategExplanatoryVar)

* numbers;
proc freq; tables CategResponseVar*CategExplanatoryVar; 

* visualzation;
proc GCHART; vbar CategExplanatoryVar /discrete type=mean sumvar=CategResponseVar; 

# numbers
tab1 <- table(myData$CategResponseVar, myData$CategExplanatoryVar)
tab1_colProp <- prop.table(tab1, 2) # column proportions 
tab1_rowProp <- prop.table(tab1, 1) # row proportions 
tab1_cellProp <- prop.table(tab1) # cell proportions 

# visualization
ggplot(data=myData)+
geom_bar(aes(x=CategExplanatoryVar, y=CategResponseVar), fun.y="count")+
ggtitle(“Descriptive Title Here”)

* numbers.
MEANS TABLES= CategExplanatoryVar by QuantResponseVar 
   /CELLS MEAN COUNT STDDEV. 

* visualization: use GUI point-and-click.

// numbers
bys CategExplanatoryVar: summary QuantResponseVar

// visualization
graph box QuantResponseVar, over(CategExplanatoryVar)

* numbers;
proc sort; by CategExplanatoryVar; 
proc means; var QuantResponseVar; 
   by CategExplanatoryVar;

* visualization;
proc gchart; vbar CategExplanatoryVar /discrete type=mean sumvar=QuantResponseVar;

# numbers
by(myData$QuantResponseVar, myData$CategExplanatoryVar, mean, na.rm = TRUE) 
by(myData$QuantResponseVar, myData$CategExplanatoryVar, sd, na.rm = TRUE) 
by(myData$QuantResponseVar, myData$CategExplanatoryVar, length) 

# visualization

# bar
ggplot(data=myData)+    
stat_summary(aes(x=CategExplanatoryVar, y=QuantResponseVar), fun.y=mean, geom=”bar”) 

# boxplot
ggplot(data=myData)+  
geom_boxplot(aes(x=CategExplanatoryVar, y=QuantResponseVar))+    
ggtitle(“Descriptive Title Here”) 

* visualization.
GRAPH 
   /scatterplot(bivar)=QuantExplanatoryVar with QuantResponseVar. 

// visualization
twoway (scatter QuantResponseVar QuantExplanatoryVar) (lfit QuantResponseVar QuantExplanatoryVar) 

* visualization;
proc gplot; plot QuantResponseVar*QuantExplanatoryVar; 

ggplot(data=myData)+
geom_point(aes(x=QuantExplanatoryVar, y=QuantResponseVar))+
geom_smooth(aes(x=QuantExplanatoryVar, y=QuantResponseVar), method=”lm”)

* numbers.
CROSSTABS
   /TABLES=CategResponseVar BY CategExplanatoryVar BY CategThirdVar. 

* visualization: use GUI point-and-click. 

// numbers
bys CategThirdVar: tab CategResponseVar CategExplanatoryVar, row column cell 

// visualization
bys CategThirdVar: graph bar (mean) CategResponseVar, over(CategExplanatoryVar)

* numbers;
proc sort; by CategThirdVar; 
proc freq; tables CategResponseVar*CategExplanatoryVar; 
   by CategThirdVar;

* visualzation;
proc gchart; vbar CategExplanatoryVar /discrete type=mean sumvar=CategResponseVar; 
   by CategThirdVar;

# numbers
tab1 <- ftable(myData$CategResponseVar, myData$CategExplanatoryVar, myData$CategThirdVar)
tab1_rowProp <- prop.table(tab1, 1) 
tab1_colProp <- prop.table(tab1, 2) 
tab1_cellProp <- prop.table(tab1)

# visualization
ggplot(data=myData)+    
geom_bar(aes(x=CategExplanatoryVar, y=CategResponseVar), fun.y="count")+
facet_grid(. ~ CategThirdVar)+
ggtitle("Descriptive Title Here")

MEANS TABLES= QuantResponseVar BY CategExplanatoryVar BY CategThirdVar
   /CELLS MEAN COUNT STDDEV. 

bys CategExplanatoryVar CategThirdVar: su QuantResponseVar 

proc sort; by CategExplanatoryVar CategThirdVar; 
proc means; var QuantResponseVar; 
   by CategExplanatoryVar CategThirdVar; 

ftable(by(myData$QuantResponseVar, list(myData$CategExplanatoryVar, myData$CategThirdVar), mean, na.rm = TRUE))

* numbers.
SORT CASES  BY region. 
SPLIT FILE LAYERED BY region. 
CORRELATIONS 
  /VARIABLES=id age 
  /PRINT=TWOTAIL NOSIG 
  /MISSING=PAIRWISE.
SPLIT FILE OFF.

* visualization.
SORT CASES  BY region. 
SPLIT FILE LAYERED BY region. 
GRAPH
  /SCATTERPLOT(BIVAR)=id WITH exp
  /MISSING=LISTWISE.
 SPLIT FILE OFF.

// visualization
bys CategThirdVar: twoway (scatter QuantResponseVar QuantExplanatoryVar) (lfit QuantResponseVar QuantExplanatoryVar) 

* visualization;
proc sort; by CategThirdVar
proc gplot; plot QuantResponseVar*QuantExplanatoryVar;
   by CategThirdVar; 

ggplot(data=myData)+
geom_point(aes(x=QuantExplanatoryVar, y=QuantResponseVar))+
geom_smooth(aes(x=QuantExplanatoryVar, y=QuantResponseVar), method=”lm”)+
facet_grid(. ~ CategThirdVar)

CROSSTABS
   /TABLES= CategResponseVar by CategExplanatoryVar
   /STATISTICS=CHISQ. 

tab CategResponseVar CategExplanatoryVar, chi2 row col 

proc freq; tables CategResponseVar*CategExplanatoryVar/ chisq; 

myChi <- chisq.test(myData$CategResponseVar, myData$CategExplanatoryVar) 
myChi 
myChi$observed # for actual, observed cell counts 
prop.table(myChi$observed, 2) # for column percentages 
prop.table(myChi$observed, 1) # for row percentages

UNIANOVA QuantResponseVar BY CategExplanatoryVar.

* for post-hoc test add the following options to the UNIANOVA command.
UNIANOVA QuantResponseVar BY CategExplanatoryVar.
   /POSTHOC=CategExplanatoryVar (TUKEY)
   /PRINT=ETASQ DESCRIPTIVE.

oneway QuantResponseVar CategExplanatoryVar, tabulate 

// for post-hoc test add the `sidak` option to oneway command
oneway QuantResponseVar CategExplanatoryVar, tabulate sidak

proc anova; class CategExplanatoryVar; 
model QuantResponseVar = CategExplanatoryVar; means CategExplanatoryVar; 

* for post-hoc test add the `duncan` option to proc anova command;
proc anova; class CategExplanatoryVar; 
model QuantResponseVar = CategExplanatoryVar; means CategExplanatoryVar /duncan; 

myAnovaResults <- aov(QuantResponseVar ~ CategExplanatoryVar, data = myData) 
summary(myAnovaResults)

# for post-hoc test
myAnovaResults <- aov(QuantResponseVar ~ CategExplanatoryVar, data = myData) 
TukeyHSD(myAnovaResults)

CORRELATIONS
   /VARIABLES= QuantResponseVar QuantExplanatoryVar
   /STATISTICS DESCRIPTIVES. 

corr QuantResponseVar QuantExplanatoryVar

//OR
pwcorr QuantResponseVar QuantExplanatoryVar, sig

proc corr; var QuantResponseVar QuantExplanatoryVar;

cor.test(myData$QuantResponseVar, myData$QuantExplanatoryVar)

CROSSTABS
   /TABLES = CategResponseVar by CategExplanatoryVar by CategThirdVar
   /CELLS = COUNT ROW
   /STATISTICS = CHISQ. 

bys CategThirdVar: tab CategResponseVar CategExplanatoryVar, chi2 row 

proc sort; by CategThirdVar; 
proc freq; tables CategResponseVar*CategExplanatoryVar/chisq; 
   by CategThirdVar; 

by(myData, 
myData$CategThirdVar, 
function(x) list( chisq.test(x$CategResponseVar, x$CategExplanatoryVar), chisq.test(x$CategResponseVar, x$CategExplanatoryVar)$observed, prop.table(chisq.test(x$CategResponseVar, x$CategExplanatoryVar)$observed, 2))) 

SORT CASES BY CategThirdVar.
SPLIT FILE LAYERED BY CategThirdVar.

ONEWAY QuantResponseVar BY CategExplanatoryVar
/STATISTICS DESCRIPTIVES
/POSTHOC = BONFERRONI ALPHA (0.05).

SPLIT FILE OFF.

bys CategThirdVar: oneway QuantResponseVar CategExplanatoryVar, tab sidak

proc sort; by CategThirdVar;
proc anova; class CategExplanatoryVar; 
   model QuantResponseVar=CategExplanatoryVar; 
   means CategExplanatoryVar; 
   by CategThirdVar /duncan; 

by(myData, 
	myData$CategThirdVar, 
	function(x) list(aov(QuantResponseVar ~ CategExplanatoryVar, data = x), summary(aov( QuantResponseVar ~ CategExplanatoryVar, data = x))))

SORT CASES BY CategThirdVar.
SPLIT FILE LAYERED BY CategThirdVar.

CORRELATIONS
   /VARIABLES= QuantResponseVar QuantExplanatoryVar
   /STATISTICS DESCRIPTIVES.

SPLIT FILE OFF. 

bys CategThirdVar: corr QuantResponseVar QuantExplanatoryVar

//OR
bys CategThirdVar: pwcorr QuantResponseVar QuantExplanatoryVar, sig

proc sort; by CategThirdVar; 
proc corr; var QuantResponseVar QuantExplanatoryVar; 
   by CategThirdVar; 

by(myData,
	myData$CategThirdVar, 
	function(x) cor.test(x$QuantResponseVar, x$QuantExplanatoryVar))

* note if explanatory var is categorical, make sure that the variable is type `nominal`.
REGRESSION
	/DEPENDENT QuantResponseVar
	/METHOD ENTER ExplanatoryVar.

//if explanatory var is quantitative
reg QuantResponseVar c.QuantExplanatoryVar

//if explanatory var is categorical
reg QuantResponseVar i.CategExplanatoryVar

* if explanatory var is quantitative;
proc glm; 
	model QuantResponseVar=QuantExplanatoryVar  /solution;

* if explanatory var is categorical;
proc glm; class CategExplanatoryVar; 
	model QuantResponseVar=CategExplanatoryVar /solution;

# if explanatory var is quantitative
my.lm <- lm(QuantResponseVar ~ QuantExplanatoryVar, data = myData) 
summary(my.lm)

# if explanatory var is categorical
my.lm <- lm(QuantResponseVar ~ factor(CategExplanatoryVar), data = myData) 
summary(my.lm)

* note if explanatory var is categorical, make sure that the variable is type `nominal`.
LOGISTIC REGRESSION BinaryResponseVar with ExplanatoryVar ThirdVar1 ThirdVar2. 

// for all quantitative predictors, add `c.` before the variable name (e.g. c.height)
// for all categorical predictors, add `i.` before the variabe name (e.g. i.race)

logistic BinaryResponseVar ExplanatoryVar ThirdVar1 ThirdVar2

* list all categorical variables in the model under the class subcommand (e.g. CategThirdVar);

proc logistic; 
	class BinaryResponseVar(ref="referenceGroup") CategThirdVar; 
	model BinaryResponseVar = ExplanatoryVar CategThirdVar QuantThirdVar;

# if categorical variable is encoded as numeric, wrap it around with the factor() function (e.g. factor(CategThirdVar1) )

my.logreg <- glm(BinaryResponseVar ~ ExplanatoryVar + factor(CategThirdVar1) + ThirdVar2, data = myData, family = "binomial") 
summary(my.logreg)  # for p-values 
exp(my.logreg$coefficients)  # for odds ratios 
exp(confint(my.logreg))  # for confidence intervals on the odds ratios

* note if explanatory var is categorical, make sure that the variable is type `nominal`.
REGRESSION
   /DEPENDENT QuantResponseVar
   /METHOD ENTER ExplanatoryVar ExtraVar1 ExtraVar2.

//if a predictor var is quantitative, add `c.`. if a predictor var is categorical, add `i.`.

reg QuantResponseVar i.CategExplanatoryVar i.CategExtraVar1 c.QuantExtraVar2

* if a predictor var is categorical, add to `class`;
proc glm; 
	class CategExplanatoryVar; 
	model QuantResponseVar=CategExplanatoryVar ExtraVar1 /solution;

# if a predictor var is categorical, wrap the var with factor() (e.g. factor(CategExtraVar) )

my.lm <- lm(QuantResponseVar ~ QuantExplanatoryVar + factor(CategExtraVar, data = myData) 
summary(my.lm)