Data analyst/ Supply chain analyst

[omarelfarouk90]

Testing the income as a moderator for the effect of alcohol usage on suicide rate

The main aim is to test the significance of the average income as a moderator. If the factor under investigation is a moderator, a different behavior in output will be seen for different moderator levels , we use the data set from Gapminder foundation in Stockholm which was  gathered from 150 countries in the UN to test for this hypothesis statistically.

so for this case , we will apply and test the average income as a moderator for the effect of alcohol usage on the suicide rate. The alcohol usage and the suicide rate are considered as a quantitative input and output. Thus, we will use Pearson correlation between them.

p.s , there is no need to put the posthoc test since there is no categorical variable.

we will divide the income into 3 categories below 1000 USD, greater than 5000USD and greater than 9000USD

the syntax code used is as the following

# -*- Week4 assignment-*- """ Created on Sun Aug 16 12:57:52 2020

@author: omar.elfarouk """

#%%

# Using gap minder data

# CORRELATION import pandas import numpy import scipy.stats import seaborn import matplotlib.pyplot as plt

data = pandas.read_csv('gapminder.csv', low_memory=False)

data['alcconsumption'] = pandas.to_numeric(data['alcconsumption'], errors='coerce') data['incomeperperson'] = pandas.to_numeric(data['incomeperperson'], errors='coerce') data['suicideper100th'] = pandas.to_numeric(data['suicideper100th'], errors='coerce')

data['incomeperperson']=data['incomeperperson'].replace(' ', numpy.nan)

data['alcconsumption']=data['alcconsumption'].replace(' ', numpy.nan)

data['suicideper100th']=data['suicideper100th'].replace(' ', numpy.nan)

data_clean=data.dropna()

print (scipy.stats.pearsonr(data_clean['alcconsumption'], data_clean['suicideper100th']))

def incomegrp (row):   if row['incomeperperson'] <= 1000:      return 1   elif row['incomeperperson'] <= 5000 :      return 2   elif row['incomeperperson'] > 9000:      return 3

data_clean['incomegrp'] = data_clean.apply (lambda row: incomegrp (row),axis=1)

chk1 = data_clean['incomegrp'].value_counts(sort=False, dropna=False) print(chk1)

sub1=data_clean[(data_clean['incomegrp']== 1)] sub2=data_clean[(data_clean['incomegrp']== 2)] sub3=data_clean[(data_clean['incomegrp']== 3)]

print ('association between alcohol consumption and suicide rate for LOW income countries') print (scipy.stats.pearsonr(sub1['alcconsumption'], sub1['suicideper100th'])) print ('       ') print ('association between alcohol usage and suicide rate for MIDDLE income countries') print (scipy.stats.pearsonr(sub2['alcconsumption'], sub2['suicideper100th'])) print ('       ') print ('association between alcohol usage and suicide rate for HIGH income countries') print (scipy.stats.pearsonr(sub3['alcconsumption'], sub3['suicideper100th'])) #%% scat1 = seaborn.regplot(x="alcconsumption", y="suicideper100th", data=sub1) plt.xlabel('Alchol consumption ') plt.ylabel('Suicide rate') plt.title('Scatterplot for the Association Between Alcohol consumption and Suicide rate for LOW income countries') print (scat1) #%% scat2 = seaborn.regplot(x="alcconsumption", y="suicideper100th", fit_reg=False, data=sub2) plt.xlabel('Alcohol consumption') plt.ylabel('Suicide rate') plt.title('Scatterplot for the Association Between Alcohol consumption and Suicide Rate for MIDDLE income countries') print (scat2) #%% scat3 = seaborn.regplot(x="alcconsumption", y="suicideper100th", data=sub3) plt.xlabel('Alcohol consumption') plt.ylabel('Suicide rate') plt.title('Scatterplot for the Association Between Alcohol consumption and Suicide rate for HIGH income countries') print (scat3)

The results on the graph are displayed as following

The alcohol consumption appears to be a significant factor for the suicide rate only for the middle and high income people.However, the alcohol consumption appears to be insignificant factor on the suicide for the countries with the average income is below 1000USD

Thus , we conclude that with the different significance of alcohol consumption on the suicide rate for different income levels that the Income level is considered as a moderator. as shown form the p values  which was below 0.05 for middle and high income value and r correlation values as shown for output values.

association between alcohol consumption and suicide rate for LOW income countries

r values, p value

(0.26070477719347973, 0.059368958483714575)

association between alcohol usage and suicide rate for MIDDLE income countries

r value, p value

(0.3827653707464948, 0.003022644556108631)

association between alcohol usage and suicide rate for various income among countries

r value , p value

(0.5725515263938896, 7.429925022112332e-05)

Credits for Weasly university team in Coursera for gathering the information and the basic knowledge to do the analysis.

[omarelfarouk90]

The effect of alcohol consumption on suicide rate

For my research , i am planning to investigate the effect of Alcohol consumption on the suicide rate . For my investigation, i will use the data gathered by the gap minder foundation for the average suicide and the average alcohol consumption rate across 170 countries gathered from the UN .

The average suicide rate per 100 person and the average alcohol consumption rate in liter per month are considered as a quantitative values. in order to identify the relationship between two quantitative values, we will use Pearson’s correlation , and thus identifying how significant and strong is the relationship between them . 

The program i am using is the Python for coding, and the syntax for the code is shown below

# -*- coding: utf-8 -*- """ Created on Wed Aug 12 18:24:12 2020

@author: omar.elfarouk """

import pandas import numpy import seaborn import scipy import matplotlib.pyplot as plt

data = pandas.read_csv('gapminder.csv', low_memory=False)

#setting variables you will be working with to numeric

data['internetuserate'] = pandas.to_numeric(data['internetuserate'], errors='coerce') data['urbanrate'] = pandas.to_numeric(data['urbanrate'], errors='coerce') data['incomeperperson'] = pandas.to_numeric(data['incomeperperson'], errors='coerce')

data['alcconsumption'] = pandas.to_numeric(data['alcconsumption'], errors='coerce') data['incomeperperson'] = pandas.to_numeric(data['incomeperperson'], errors='coerce') data['suicideper100th'] = pandas.to_numeric(data['suicideper100th'], errors='coerce')

data['incomeperperson']=data['incomeperperson'].replace(' ', numpy.nan) data['alcconsumption']=data['alcconsumption'].replace(' ', numpy.nan) data['suicideper100th']=data['suicideper100th'].replace(' ', numpy.nan)

#Plotting figure scat1 = seaborn.regplot(x="incomeperperson", y="alcconsumption", fit_reg=True, data=data) plt.xlabel('incomeperperson') plt.ylabel('Alcoholuse') plt.title('Scatterplot for the Association Between income per personand Alcohol usage')

scat2 = seaborn.regplot(x="incomeperperson", y="suicideper100th", fit_reg=True, data=data) plt.xlabel('Income per Person') plt.ylabel('suicideper100th') plt.title('Scatterplot for the Association Between Income per Person and Suicide Rate')

scat3 = seaborn.regplot(x="alcconsumption", y="suicideper100th", fit_reg=True, data=data) plt.xlabel('Alcohol usage') plt.ylabel('suicideper100th') plt.title('Scatterplot for the Association Between Alcohol usage and Suicide Rate')

#Cleaning data data_clean=data.dropna()

#Applying pearson correlation print ('association between Income per person and Alcohole isage') print (scipy.stats.pearsonr(data_clean['incomeperperson'], data_clean['alcconsumption']))

print ('association between incomeperperson and suscide rate ') print (scipy.stats.pearsonr(data_clean['incomeperperson'], data_clean['suicideper100th']))

print ('association between Alcohol usage and suscide rate ') print (scipy.stats.pearsonr(data_clean['alcconsumption'], data_clean['suicideper100th']))

Regarding the average income and the alcohol correlation , there is a strong correlation as shown in the figure below

 The relationship between income and suicide shows a weak correlation and insignificant effect as shown in the figure below

the relationship between the alcohol usage and the suicide rate displays a strong correlation as shown in the figure below.

  The Pearson correlation  ,and the p-values are displayed as shown in the text below

association between Income per person and Alcohol usage (0.29177119807858265, 0.00010297020763990634)

Thus ,there is a weak positive correlation beween income per person and alcohol usage, However. it is considered as a significant as the p value is below 0.05, thus we can safely reject the null hypothesis and claim that there is a significant relation between the Alcohol usage and the income

association between income per person and suicide rate (0.0060833598985392135, 0.9368723631391026)

Thus ,there is a weak positive correlation between the income and the suicide rate, and also it is considered insignificant as the  p value is equal to 0.93, thus we can safely accept the null hypothesis and claim that there no significant relation between the average income and the suicide rate. association between Alcohol usage and suicide rate (0.3874255193053243, 1.5168064802517918e-07)

Thus ,there is a weak positive correlation between suicide rate  and alcohol usage, However. it is considered as a significant as the p value is below 0.05, thus we can safely reject the null hypothesis and claim that there is a significant relation between the Alcohol usage and the suicide rate.

[omarelfarouk90]

The effect of average income on the alcohol consumption rate per person

A study have been conducted using the data set gathered by Gapminder organization for data of more than 150 countries obtained from the UN. To study the effect of average income on the alcohol consumption rate.

In order to perform the analysis where the input is categorical (income below or above $2000 USD, denoted by 0 and 1) and the output is also categorical regarding the alcohol consumption rate (below 3 liters, 3 liters to 9 liters, and above 9 liters) denoted in 0,1 and 2

so far, it seems graphically that the countries with average income below $2000 are having a higher alcohol consumption rate.

to prove this theory , a chi- squared test need to be provided for the categorical input and output data.

the results of chi square was as following.

the p value was equal to 1.24*10^-9, indicating the significant difference and thus rejecting the null hypothesis that says there is no significant relationship between average income and alcohol consumption.

later on , w need to identify which category of alcohol usage is significantly affected by the average income, thus we need to used a post hoc test of bonferoni , so we will compare the p value with 0.016which is divided the number of categories which is 3 .

and thus we will perform chi square comparison between the 3 alcohol levels

the result will be as shown  

there was a significant difference between the first and third and the second and third category , which is shown by the low p-value with was far smaller than the Bonferonni  probability calculated, And thus, rejecting the null hypothesis that says there is no significant difference between alcohol levels of the first and third category and the second and Third category. indicating that we can divide into two categories , below 9 liters and more that 9 liters of alcohol consumption

In conclusion , the lower average income in a country below 2000 USD is more likely to have an increase in the alcohol consumption rate for drinking by more than 9 liter per person.

Source code for python

""" Created on Wed Aug 26 18:17:30 2015

@author: Omar Elfarouk """

import pandas import numpy import scipy.stats import seaborn import matplotlib.pyplot as plt

data = pandas.read_csv('gapminder.csv', low_memory=False)

# new code setting variables you will be working with to numeric data['Alcoholuse'] = pandas.to_numeric(data['Alcoholuse'], errors='coerce') data['Income'] = pandas.to_numeric(data['Income'], errors='coerce') data['suicideper100th'] = pandas.to_numeric(data['suicideper100th'], errors='coerce')

#subset data the excel sheet available , and data wrangling sub1=data sub1 = sub1.replace(r'\s+', 0, regex=True) #Replace empty strings with zero #sub1=data[(data['AGE']>=18) & (data['AGE']<=25) & (data['CHECK321']==1)]

#make a copy of my new subsetted data sub2 = sub1.copy()

# recode missing values to python missing (NaN) #sub2['Alcoholuse']=sub2['Alcoholuse'].replace(0, numpy.nan) #sub2['Income']=sub2['Income'].replace(0, numpy.nan) #sub2['suicideper100th']=sub2['suicideper100th'].replace(0, numpy.nan) #recoding values for S3AQ3B1 into a new variable, USFREQMO #recode1 = {1: 30, 2: 22, 3: 14, 4: 6, 5: 2.5, 6: 1} #sub2['USFREQMO']= sub2['S3AQ3B1'].map(recode1)

# contingency table of observed counts ct1=pandas.crosstab(sub2['Alcoholuse'], sub2['Income']) print (ct1)

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

# chi-square print ('chi-square value, p value, expected counts') cs1= scipy.stats.chi2_contingency(ct1) print (cs1)

# set variable types sub2["Income"] = sub2["Income"].astype('category') # new code for setting variables to numeric: sub2['Alcoholuse'] = pandas.to_numeric(sub2['Alcoholuse'], errors='coerce')

# old code for setting variables to numeric: #sub2['TAB12MDX'] = sub2['TAB12MDX'].convert_objects(convert_numeric=True)

# graph percent with nicotine dependence within each smoking frequency group seaborn.factorplot(x="Income", y="Alcoholuse", data=sub2, kind="bar", ci=None) plt.xlabel('Income below or greater than 2000USD') plt.ylabel('Alcohol consumption rate')

recode2 = {0: 0, 1: 1} sub2['COMP1v1']= sub2['Alcoholuse'].map(recode2)

# contingency table of observed counts ct2=pandas.crosstab(sub2['Income'], sub2['COMP1v1']) print (ct2)

# column percentages for creating the column sum colsum=ct2.sum(axis=0) colpct=ct2/colsum print(colpct)

print ('chi-square value, p value, expected counts') cs2= scipy.stats.chi2_contingency(ct2) print (cs2)

recode3 = {1: 1, 2: 2} sub2['COMP1v2']= sub2['Alcoholuse'].map(recode3)

# contingency table of observed counts ct3=pandas.crosstab(sub2['Income'], sub2['COMP1v2']) print (ct3)

# column percentages for creating the column sum colsum=ct3.sum(axis=0) colpct=ct3/colsum print(colpct)

print ('chi-square value, p value, expected counts') cs3= scipy.stats.chi2_contingency(ct3) print (cs3)

recode4 = {0: 0, 2: 2} sub2['COMP1v14']= sub2['Alcoholuse'].map(recode4)

# contingency table of observed counts ct4=pandas.crosstab(sub2['Income'], sub2['COMP1v14']) print (ct4)

# column percentages for creating the column sum colsum=ct4.sum(axis=0) colpct=ct4/colsum print(colpct)

print ('chi-square value, p value, expected counts') cs4= scipy.stats.chi2_contingency(ct4) print (cs4)

[omarelfarouk90]

The significance of alcohol consumption and average income on suicide rate

I have performed some data analysis on the data gathered by the gap minder foundation in Stockholm to help in the UN development . i have used the same gathered data to analyze the effect of alcohol consumption and average income on the suicide rate per 100 people, the analysis was conducted using the OLS regression technique from the python stats model.

the input of average income was divided into two categories, greater than or equal $2000 per month and less than $2000 USD per month

the input of the alcohol consumption was divided into two categories according to their consumption per liter

category 0  below 3L per month

category 1 from 3L to 9L consumption per month

the code was as following

Created on Sat Aug  8 10:27:52 2020

@author: omar.elfarouk """

import numpy import pandas as pd import statsmodels.formula.api as smf import statsmodels.stats.multicomp as multi from pandas import DataFrame as df

data = pd.read_csv('gapminder.csv', low_memory=False) df = pd.DataFrame(data) #setting variables you will be working with to numeric df = df.replace(r'\s+', 0, regex=True) #Replace empty strings with zero

#subset data to income per person , alcohol consumption ,suiside rate , and employment sub1=data sub1 = sub1.replace(r'\s+', 0, regex=True) #Replace empty strings with zero #SETTING MISSING DATA

# Creating a secondary variable multiplying income by alcohol consumption by employment rate

#sub1['suicideper100th']=sub1['suicideper100th'].replace(0, numpy.nan)

sub1['suicideper100th']= pd.to_numeric(sub1['suicideper100th'])

#sub1['Income']= pd.to_numeric(sub1['Income']) ct1 = sub1.groupby('suicideper100th').size() print (ct1)

# using ols function for calculating the F-statistic and associated p value model1 = smf.ols(formula='suicideper100th ~ C(Income)', data=sub1).fit() results1 = model1 print (results1.summary())

sub2 = sub1[['suicideper100th', 'Income']].dropna()

print ('means for income by suicide status') m1= sub2.groupby('Income').mean() print (m1)

print ('standard deviations for income suiside status') sd1 = sub2.groupby('Income').std() print (sd1) #i will call it sub3 sub3 = sub1[['suicideper100th', 'Alcoholuse']].dropna()

model2 = smf.ols(formula='suicideper100th ~ C(Alcoholuse)', data=sub3).fit() print (model2.summary())

print ('means for alcohol use by suicide status') m2= sub3.groupby('Alcoholuse').mean() print (m2)

print ('standard deviations for alcohol use by suicide') sd2 = sub3.groupby('Alcoholuse').std() print (sd2) #tuckey honesty test comparision for post hoc test mc1 = multi.MultiComparison(sub3['suicideper100th'], sub3['Alcoholuse']) res1 = mc1.tukeyhsd() print(res1.summary())

the null hypothesis indicates that there is no difference in the level of consumption of alcohol on the suicide rate and also there is no difference in the income level on the suicide rate.

the alternative hypothesis is that there is a significance difference on the alcohol consumption and the average income on the suicide rate.

the results are displayed as following

OLS Regression Results                             ============================================================================== Dep. Variable:        suicideper100th   R-squared:                       0.013 Model:                            OLS   Adj. R-squared:                  0.009 Method:                 Least Squares   F-statistic:                     2.875 Date:                Sun, 09 Aug 2020   Prob (F-statistic):             0.0914 Time:                        02:48:14   Log-Likelihood:                -703.84 No. Observations:                 213   AIC:                             1412. Df Residuals:                     211   BIC:                             1418. Df Model:                           1                                         Covariance Type:            nonrobust      

the low value of F- statistics and P value being greater that 0.025 indicates that we have failed to reject the null hypothesis and we accept the fact that there is no significant difference on the effect of annual income value on the suicide rate

 OLS Regression Results                             ============================================================================== Dep. Variable:        suicideper100th   R-squared:                       0.006 Model:                            OLS   Adj. R-squared:                 -0.004 Method:                 Least Squares   F-statistic:                    0.5930 Date:                Sun, 09 Aug 2020   Prob (F-statistic):              0.554 Time:                        02:48:14   Log-Likelihood:                -704.69 No. Observations:                 213   AIC:                             1415. Df Residuals:                     210   BIC:                             1425. Df Model:                           2                                         Covariance Type:            nonrobust                                         ======================================================================================                         coef    std err          t      P>|t|      [0.025      0.975] -------------------------------------------------------------------------------------- Intercept              7.7779      0.942      8.254      0.000       5.920       9.635 C(Alcoholuse)[T.1]     0.9818      1.204      0.815      0.416      -1.392       3.355 C(Alcoholuse)[T.2]     1.2756      1.190      1.072      0.285      -1.071       3.622

the low value of F- statistics and P value being greater that 0.025 indicates that we have failed to reject the null hypothesis and we accept the fact that there is no significant difference on the effect of alcohol consumption level on the suicide rate.

another analysis have been conducted,which is called the post hoc test, it is used to analyze the difference between the groups of categorical level without increasing the type 1 error in an accumulative manner. we use  the Tuckey honesty test for post hoc comparison. and it agrees with the fact that there is no difference between the alcohol usage levels on the suicide rate .

means for alcohol use by suicide status            suicideper100th Alcoholuse                 0                  7.777891 1                  8.759692 2                  9.053453 standard deviations for alcohol use by suicide            suicideper100th Alcoholuse                 0                  6.086994 1                  5.809631 2                  7.663338 Multiple Comparison of Means - Tukey HSD, FWER=0.05 =================================================== group1 group2 meandiff p-adj   lower  upper  reject ---------------------------------------------------     0      1   0.9818  0.678 -1.8605 3.8241  False     0      2   1.2756 0.5313 -1.5338 4.0849  False     1      2   0.2938    0.9 -2.1713 2.7588  False ---------------------------------------------------