Translation Syntax

import pandas as pd
import numpy as np
myData = pd.read_csv('/path/to/file.csv')

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

use "/path/to/file.dta"

/*To load in a file with extension .sas7bdat*/

LIBNAME myFolder "P:\QAC\QAC201\Studies and Codebooks\StudyName\Data"; 
data new; set myFolder.filename; 

/*To import a file with extension .csv*/

proc import datafile="P:\QAC\qac201\PracticeData\data_name.csv"  out=data_name

 dbms=csv
  replace;
 getnames=yes;
run; 

# If extension is .Rdata

load("/path/to/file.Rdata")


# If extension is csv

myData <- read.csv("/path/to/file.csv")

myData=myData_orig[['VAR1','VAR2','VAR3','VAR4','VAR5','VAR6','VAR7','VAR8']]

* 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 and Codebooks\StudyName\Data\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]

#pd short for pandas

pd.DataFrame.to_csv(myData,‘filename.csv’)

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)

myData=myData.sort_values(by='unique_id')

SORT CASES BY var.

sort var

proc sort; by var; 

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

title_of_subsetted_data=myData[myData.diabetes2==1]

#Or you can use the ['variable'] to access variables 

title_of_subsetted_data = myData[myData['diabetes2']==1]

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

// create a subset from the data
keep if (diabetes2==1)

// if running a procedure on a subset of the data (format: procedure [arguments] if [condition]). for example, if you want to run a frequency table on bio_sex for participants with type II diabetes


tab bio_sex if diabetes2==1

* inside the data step;
if diabetes2=1; 

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

myData['VAR1']= myData['VAR1'].replace(9, numpy.nan)

RECODE VAR1 (9=SYSMIS). 

replace VAR1=. if VAR1==9 

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

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

#method 1. define a function 

def TREE_N(row):
   if row['TREE']=='Maple' :
      return 1 
   if row['TREE']=='Oak' :
      return 2

myData['TREE_N']=myData.apply(TREE_N, axis = 1)  # axis=1 means apply to each row



#method 2. Alternatively, you can use the loc function

myData.loc[myData['TREE'] == 'Maple', 'NewVariable'] = 1 
myData.loc[myData['TREE'] == 'Oak', 'NewVariable'] = 0


#method 3. use apply

myData['NewVariable'] = myData['TREE'].apply(lambda x: 1 if x == 'Maple' else (0 if x == 'Oak' else None))

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;

myData$NewVariable[myData$TREE=="Maple"]<-1
myData$NewVariable[myData$TREE=="Oak"]<-0

# change levels

def new_region(row):
   if row['region']== 1 or row['region']== 2 or row['region']== 3 or  
      row['region']==5 or row['region']==6:
      return 1
   elif row['region']==4 or row['region']==7 or row['region']==8 or
      row['region']==9:
      return 2

myData['new_region']=myData.apply(new_region(row), axis = 1)


#Or you can do it faster

def new_region(row):
   if row['region'] in (1,2,3,5,6):
      return 1
   elif row['region'] in (4,7,8,9):
      return 2

myData['new_region']=myData.apply(new_region(row), axis = 1)

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;

# The below says, make a new variable called "new_region"
# and set it equal to "East" if the original variable region is
# either 1 or 2 or 3 or 5.

myData$new_region[myData$region == 1|myData$region == 2|myData$region == 3|myData$region == 5|myData$region] <- "East"

# Set "new_region" equal to "West" if the original variable region is
# either 7 or 8 or 9.

myData$new_region[myData$region == 4|myData$region == 7|myData$region == 8|myData$region == 9] <- "West"

# import pandas as pd 
myData.loc[myData['year'] >= 2013, 'generation'] = 1
myData.loc[(myData['year'] >= 1997) & (myData['year'] <= 2012), 'generation'] = 2
myData.loc[(myData['year'] >= 1981) & (myData['year'] <= 1996), 'generation'] = 3 
myData.loc[(myData['year'] >= 1965) & (myData['year'] <= 1980), 'generation'] = 4

generate generation =. 
replace generation=1 if year >= 2013
replace generation=2 if year >= 1997 & year <=2012
replace generation=3 if year >=1981 & year <= 1996
replace generation=4 if year >= 1965 & year <= 1980

* inside the data step;
if year GE 2013 then generation=1;
if year GE 1997 and year LE 2012 then generation=2;
if year GE 1981 and year LE 1996 then generation=3;
if year GE 1965 and year LE 1980 then generation=4;

myData$generation[myData$year>=2013]<-1
myData$generation[myData$year>=1997 & myData$year <=2012]<-2
myData$generation[myData$year>=1981 & myData$year <= 1996]<-3
myData$generation[myData$year>=1965 & myData$year <= 1980]<-4

def anxiety(row):
   if row['socphob']==1 or row['gad']== 1 or row['panic']== 1 or row['agora']== 1 or row['ocd']==1:
      return 1
   else:
      return 0

myData['anxiety']=data.apply(lambda row:anxiety(row), axis = 1)

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;

# Make a new variable called "anxiety" and set it equal to 0 if
# the person has none of the anxiety symptoms (that is, if all
# variables (socphob, gad, panic, agora, ocd) are 0)

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


# Set this new variable equal to 1 if the person has a "1" for any of the
# anxiety variables.

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

myData['nd_sum']=myData['nd_symptom1']+myData['nd_symptom2']+
                                   myData['nd_symptom3']+myData['nd_symptom4

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

N/A

VARIABLE LABELS VAR1 'label'.

label variable VAR1 "label"

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

# no built-in label tags for variables

myData=myData.rename({'oldvar':'newvar'}, axis='columns')

* 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"

#Because the function doesn't name the existing levels, make sure you have them all in the right order.

myData['VAR1']=myData['VAR1'].astype('category')
myData['VAR1']=myData['VAR1'].cat.rename_categories(["value0label","value1label",
                                                    value2label","value3label"])

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")

myData['VAR1'].value_counts(normalize = True, sort=False, dropna=False)

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))

import matplotlib.pyplot as plt
import seaborn as sns

sns.countplot(x="CategVar", data=myData)
plt.xlabel("Label for CategVar")
plt.title("Descriptive Title")

myData['QuantVar1'].dropna().describe()

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)

import matplotlib.pyplot as plt
import seaborn as sns

sns.histplot(data=myData, x='QuantVar', bins=30, kde=True) 
plt.title("Descriptive Title Here") 

#Create a contingency table 
tab1 = pd.crosstab(myData['CategResponseVar'], myData['CategExplanatoryVar'])

tab1_colProp = tab1.div(tab1.sum(axis=0), axis=1) # Proportions for each column 

tab1_rowProp = tab1.div(tab1.sum(axis=1), axis=0) # Proportions for each row 

tab1_cellProp = tab1.div(tab1.sum().sum()) # Proportions for the entire table 


#OR can do it this way


#import pandas as pd

print (pd.crosstab(myData['CategResponseVar'],myData['CategExplanatoryVar'],margins=True))

# get column proportions
print(pd.crosstab(myData['CategResponseVar'],myData['CategExplanatoryVar'],margins=True,normalize='columns'))

# get row proportions
print(pd.crosstab(myData['CategResponseVar'],myData['CategExplanatoryVar'],margins=True,normalize='index'))

# get cell proportions
print (pd.crosstab(myData['CategResponseVar'],myData['CategExplanatoryVar'],margins=True,normalize='all'))

* 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; 

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

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

import matplotlib.pyplot as plt
import seaborn as sns

sns.barplot(data=graph_data, x='CategExplanatoryVar', y='BinaryResponseVar', estimator='mean') 
plt.xlabel('Label forCategExplanatoryVar')
plt.ylabel('Label forQuantResponseVar')
plt.title('Descriptive Title Here')

// install and use caplot 

ssc install catplot 

// to show frequencies (conditional) from a  two-way table

catplot, over(CategResponseVar) over(CategExplanatoryVar) blabel(bar)

// to show proportions (conditional; col percent) from a  two-way table

catplot, over(CategResponseVar) over(CategExplanatoryVar)  percent(CategExplanatoryVar) blabel(bar)

// visualization to show percents within group – can only be used
// when response variable has 2 levels.
// Requires data management that has response variable coded as a binary 0/1

graph bar BinaryCategoricalResponseVar, over(CategExplanatoryVar)

/*Code below assumes your response variable is coded as 1 and 0*/

Proc SGPLOT; vbar ExplVar /response=RespVar stat=mean;



# visualization - Assumes response variable is coded as 0/1

ggplot(data=graph_data) +
    stat_summary(aes(x=CategExplanatoryVar, y=BinaryResponseVar),  fun=”mean”, geom=”bar”) +
   ylab(“Proportion of Subjects at each Response Level within each group”) +
   ggtitle(“Informative Title Here”)

myData['QuantResponseVar'].groupby(myData['CategExplanatoryVar']).describe()

# Finding the average of a quantitative variable by a categorical variable 
average_by_group = myData.groupby('CategExplanatoryVar')['QuantResponseVar'].mean(skipna=True) 

print(average_by_group) 

# Finding the standard deviation of a quantitative variable by a categorical variable 
std_dev_by_group = myData.groupby('CategExplanatoryVar')['QuantResponseVar'].std(skipna=True) 

print(std_dev_by_group) 

# Finding the sample size by group 
sample_size_by_group = myData.groupby('CategExplanatoryVar')['QuantResponseVar'].count() 

print(sample_size_by_group)

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

* visualization: use GUI point-and-click.

// numbers
bys CategExplanatoryVar: sum 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;

# To find the average of a quantitative variable by a categorical variable:
by(myData$QuantResponseVar, myData$CategExplanatoryVar, mean, na.rm = TRUE)

# To find the standard deviation of a quantitative variable by a categorical variable:

by(myData$QuantResponseVar, myData$CategExplanatoryVar, sd, na.rm = TRUE) 

# To find the sample size by group:
by(myData$QuantResponseVar, myData$CategExplanatoryVar, length) 

import matplotlib.pyplot as plt
import seaborn as sns

#Option 1 bar plot

sns.barplot(data=myData, x='CategExplanatoryVar', y='QuantResponseVar', estimator='mean') 
plt.ylabel("Mean of QuantResponseVar") 
plt.title("Mean of QuantResponseVar by CategExplanatoryVar") 

#Option 2 : Box plot

sns.boxplot(data=myData, x='CategExplanatoryVar', y='QuantResponseVar') 
plt.ylabel("Mean of QuantResponseVar") 
plt.title("Descriptive Title Here") 

# Option 1: Bar plot
ggplot(data=myData)+
    stat_summary(aes(x=CategExplanatoryVar, y=QuantResponseVar),
      fun=mean, geom=”bar”)

# Option 2: Boxplot
ggplot(data=myData)+
   geom_boxplot(aes(x=CategExplanatoryVar, y=QuantResponseVar))+
   ggtitle(“Descriptive Title Here”)

import matplotlib.pyplot as plt
import seaborn as sns

sns.scatterplot(data=myData, x='QuantExplanatoryVar', y='QuantResponseVar') 
sns.regplot(data=myData, x='QuantExplanatoryVar', y='QuantResponseVar', ci=None, line_kws={"color": "red"}) 
plt.xlabel('QuantExplanatoryVar') 
plt.ylabel('QuantResponseVar') 
plt.title('Scatter plot with Linear Regression') 

#OR can use 

sns.regplot(x="QuantExplanatoryVar",y="QuantResponseVar",fit_reg=False,data=myData)
plt.xlabel('Label forQuantExplanatoryVar')
plt.ylabel('Label forQuantResponseVar')
plt.title('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")

import matplotlib.pyplot as plt
import seaborn as sns


sns.factorplot(x="CategExplanatoryVar", y="CategResponseVar", hue="CategThirdVar", 
data=myData, kind="bar", ci=None) 
plt.xlabel('Label for CategExplanatoryVar') 
plt.ylabel('Label for CategResponseVar') plt.title('Descriptive Title Here')

* 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;

# visualization
ggplot(data=myData)+    
stat_summary(aes(x=CategExplanatoryVar, y=BinaryResponseVar), fun="mean", geom="bar")+
facet_grid(. ~ CategThirdVar)+
ggtitle("Descriptive Title Here")

PYTHON

import pandas as pd

import seaborn as sns

import matplotlib.pyplot as plt

# Plot setup

plt.figure(figsize=(10, 6))

sns.barplot(

data=myData,

x='CategExplanatoryVar',

y='BinaryResponseVar',

hue='CategThirdVar', # Creates separate bars for each level of CategThirdVar within the same plot

estimator='mean', # Uses mean of BinaryResponseVar for each category

ci=None # Remove if you want confidence intervals

)

# Customize plot plt.title("Descriptive Title Here")

plt.xlabel("Explanatory Variable")

plt.ylabel("Mean of Binary Response Variable") plt.legend(title="Third Variable")


// visualization to show percents within group – best to use when
// response variable is more than 2 levels
graph hbar (percent), over(CategResponseVar) over(CategExplanatoryVar) percent stack asyvars

// visualization to show percents within group – can only be used
// when response variable has 2 levels.
// Requires data management that has response variable coded as a binary 0/1
graph bar BinaryCategoricalResponseVar, over(CategExplanatoryVar)

# visualization - Assumes response variable is coded as 0/1
# visualization


ggplot(data=myData)+                           stat_summary(aes(x=CategExplanatoryVar, y=BinaryResponseVar), fun="mean", geom="bar)+                                                           facet_grid(. ~ CategThirdVar)+
ggtitle("Descriptive Title Here")


import pandas as pd 

table = myData.groupby(['CategExplanatoryVar', 'CategThirdVar'])['QuantResponseVar'].mean().reset_index() 

print(table)

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))

import matplotlib.pyplot as plt
import seaborn as sns

sns.barplot(x="CategExplanatoryVar", y="QuantResponseVar", hue="CategThirdVar", data=myData, ci=None) 
plt.xlabel('Label for CategExplanatoryVar') 
plt.ylabel('Label for QuantResponseVar') 
plt.title('Descriptive Title Here')

import matplotlib.pyplot as plt
import seaborn as sns

# Create a FacetGrid to facet by the 'CategThirdVar' column 
g = sns.FacetGrid(myData, col="CategThirdVar", height=4, aspect=1.2) 

# Map scatterplot with regression line to each facet 
g.map_dataframe(sns.scatterplot, x="QuantExplanatoryVar", y="QuantResponseVar", color="blue") g.map_dataframe(sns.lineplot, x="QuantExplanatoryVar", y="QuantResponseVar", ci=None, color="orange", linestyle="--") 

* 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
twoway (scatter QuantResponseVar QuantExplanatoryVar) (lfit QuantResponseVar QuantExplanatoryVar), by(CategThirdVar)

* 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)

import pandas as pd
import scipy.stats as stats

ct1=pd.crosstab(myData['CategResponseVar'],myData['CategExplanatoryVar'])
print ('chi-square value, p value,degrees of freedom,expected counts')
cs1=stats.chi2_contingency(ct1)
print(cs1)

# column percentages
colsum=ct1.sum(axis=0)
colpct=ct1/colsum
print(colpct)

# Post-hoc
# for each Chi Sq pair data subset 
# (code below compares group 1 to group 2)

recode1= {1: 1, 2:2}
myData['COMP1v2']=myData['CategExplanatoryVar'].map(recode1)
ct1=pd.crosstab(myData['CategResponseVar'],myData['COMP1v2'])
cs1=stats.chi2_contingency(ct1)
print(cs1)

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

tab CategResponseVar CategExplanatoryVar, chi2 row col 

*If post-hoc necessary look at two levels of explanatory variable at a time*

tab CategResponseVar CategExplanatoryVar if (CategExplanatoryVar=="GroupA" | CategExplanatoryVar=="GroupB") , chi2 row col

tab CategResponseVar CategExplanatoryVar if (CategExplanatoryVar=="GroupA" | CategExplanatoryVar=="GroupC") , 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

## Post-hoc test of which explanatory levels vary.
source(“https://raw.githubusercontent.com/PassionDrivenStatistics/R/master/ChiSquarePostHoc.R”)
myChi<-chisq.test(myData$CategResponseVar, myData$CategExplantoryVar)
Observed_table<-myChi$observed
chisq.post.hoc(Observed_table, popsInRows=FALSE, control=”bonferroni”)

## Or check Pearson Residuals
myChi$residuals


import statsmodels.formula.api as smf
import statsmodels.stats.multicomp as multi

model1= smf.ols(formula='QuantResponseVar~ C(CategExplanatoryVar)', data=myData)
results1=model1.fit()
print (results1.summary())
# Post-hoc test
sub1=myData[['QuantResponseVar','CategExplanatoryVar']].dropna()
mc1=multi.MultiComparison(sub1['QuantResponseVar'],sub1['CategExplanatoryVar'])
res1= mc1.tukeyhsd()print(res1.summary())

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)

import scipy

sub1=myData[['QuantResponseVar', 'QuantExplanatoryVar']].dropna()
print (‘Plot Title’)
print(scipy.stats.pearsonr(sub1['QuantResponseVar'],sub1['QuantExplanatoryVar']))

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)

PYTHON

SPSS

import pandas as pd 
import scipy.stats as stats 

# Function to apply to each group 
def chi_sq_test(group):
contingency_table = pd.crosstab(group['CategResponseVar'], group['CategExplanatoryVar']) chi2_result = stats.chi2_contingency(contingency_table) 

observed = chi2_result[3]  
proportions = observed / observed.sum(axis=0)  

return { 'chi2_result': chi2_result, 'observed': observed, 'proportions': proportions }  

print(myData.groupby('CategThirdVar').apply(chi_sq_test))



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))) 

import pandas as pd 
import statsmodels.api as sm 
from statsmodels.formula.api import ols
# Group data by 'CategThirdVar' and apply ANOVA within each group 
results = myData.groupby('CategThirdVar').apply( 
lambda x: { 
'anova_model': ols('QuantResponseVar ~ CategExplanatoryVar', data=x).fit(), 
'summary': sm.stats.anova_lm(ols('QuantResponseVar ~ CategExplanatoryVar', data=x).fit(), typ=2) } ) 

# To access each group's result, you can loop through or use the results variable directly. 
# Example: print results for each group 
for group, result in results.items(): 
print(f"\nGroup: {group}") 
print("ANOVA Summary:\n", result['summary'])

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))))

from scipy.stats import pearsonr

correlation, p_value = pearsonr(x, y) 
print(f"Pearson Correlation Coefficient: {correlation}") 
print(f"P-value: {p_value}")

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))

import statsmodels.formula.api as smf 
import pandas as pd
import numpy as np

#If the Explanatory Variable is Quantitative
my_lm_quant = smf.ols('QuantResponseVar ~ QuantExplanatoryVar', data=myData).fit() 

print(my_lm_quant.summary())

#If the explanatory variable is Categorical
# Convert categorical variable to 'category' type if necessary 
myData['CategExplanatoryVar'] = myData['CategExplanatoryVar'].astype('category') 

my_lm_categ = smf.ols('QuantResponseVar ~ CategExplanatoryVar', data=myData).fit() 

print(my_lm_categ.summary())

* 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)

import statsmodels.formula.api as smf 
import pandas as pd
import numpy as np

my_logreg = smf.logit('BinaryResponseVar ~ ExplanatoryVar + ExplanatoryVar2', data=myData).fit() 

print(my_logreg.summary()) 

odds_ratios = np.exp(my_logreg.params) 
print(odds_ratios) 

#confidence intervals
conf = my_logreg.conf_int() 

#Confidence intervals for the odds ratios
conf_odds_ratios = np.exp(conf) 
print(conf_odds_ratios)

# Predicted probabilities for each observation predicted_probabilities = my_logreg.predict(myData) print("Predicted Probabilities:\n", predicted_probabilities)

* 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(ExplanatoryVar) )

my.logreg <- glm(BinaryResponseVar ~ ExplanatoryVar, 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

# If you have many explanatory variables, you can just continue to add them in

my.logreg <- glm(BinaryResponseVar ~ ExplanatoryVar + ExplanatoryVar2, 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

import statsmodels.formula.api as smf

my_lm = smf.ols('QuantResponseVar ~ QuantExplanatoryVar + CategExtraVar', data = myData).fit()

print(my_lm.summary())

* 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)