1

Mathematics: Applications and Interpretations

Internal Assessment

Standard Level

Topic: A comprehensive analysis on the correlation between GDP

growth in India and unemployment rates from 2011-2021.

Total pages: 20
 2

Introduction

An important subject in economics is the connection between Gross Domestic Product (GDP)

and the unemployment rate. The labor force's share that is unemployed yet seeks employment

is represented by the unemployment rate, whereas GDP measures the economic output of a

nation. The correlation between these two measures can offer important clues about the state

of an economy.

As an Indian citizen and an economics enthusiast, I am deeply interested in understanding the

relationship between GDP and unemployment rate in my country. The state of the economy

and the level of employment are important indicators of the well-being of the population, and

I believe that by analyzing this relationship I can gain valuable insights into the health of the

Indian economy.

In this IA, I will be conducting an analysis of GDP and unemployment rate in India from

2011 to 2021, using data from various credible sources, here, the official website of the

World Bank to obtain figures for the GDP. I will also be keeping note of additional factors

such as inflation, demographic data, and trade data to provide a more comprehensive

understanding of the relationship between GDP and unemployment rate in India. My goal is

to provide a personal engagement perspective as an Indian citizen on this matter, with the aim

of understanding the present state of the Indian economy and its future prospects.

Exploration of the mathematical concepts used

The mathematical concepts used in this analysis include mean, deviation from the mean,

correlation coefficient, coefficient of determination and linear regression. The average of a

dataset is it’s mean, deviation from the mean is the difference between each data point and

the mean, correlation coefficient is used to gauge the degree and intensity of a correlation or
 3

link between two variables, linear regression is a method for modeling said link and the

coefficient of determination assesses the accuracy of the model in terms of fitting the data.

Calculations:

1. Correlation coefficient: Also known as Pearson's correlation coefficient, the

correlation coefficient measures the strength or significance of a linear relationship

among two variables and is denoted by the symbol ‘r’. In this case, the correlation

coefficient was calculated on the Casio FX-CG50 graphing calculator:

A general formula to calculate the correlation coefficient (r) is,

Where x represents GDP, y represents unemployment rate, x̄ represents the GDP mean, and ȳ

represents the unemployment rate mean. The correlation coefficient has a range of -1 to 1, a

value of -1 shows a perfect negative correlation, inversely, a 1 value means a perfect positive

correlation, and a value of 0 denotes no correlation.

2. R-squared value: The coefficient of determination, commonly referred to as R-

squared, is a metric used to assess how well a linear regression model fits a set of

data. It is calculated as the correlation coefficient square, and it has a range of 0 to 1,

with 0 denoting no fit and 1 denoting perfect fit.

R² = r²

3. Linear regression is a method for modelling relationships among two variables. The

variables in this scenario are the GDP and the unemployment rate. A general formula for a

linear regression is: y = a + bx, where an is the y-intercept, b is the slope of the line, and y is
 4

the dependent variable (here, GDP) and x is the independent variable (here, unemployment

rate). A slope of the line or the gradient (b) represents GDP change per unit change in the

independent variable (unemployment rate). The dependent variable’s numerical value (GDP)

is represented by the y-intercept when the independent variable (unemployment rate) is equal

to zero (a). The linear regression equation, y = a + bx, can be used to make predictions about

the relationship between GDP and unemployment rate in India.

Methodology:

(Data on GDP and unemployment rate in India from 2011 to 2021 was collected from the

official website of the World Bank.)

Methodology:

The methodology used in this analysis includes the following steps:

1. Firstly, I collected data on GDP and unemployment rate in India from 2011 to 2021

from the official website of the World Bank.

2. Organize the data in a table and calculate the mean of GDP and unemployment rate.

3. For each data point, calculate the deviation from the mean for GDP and

unemployment rate.

4. Multiply the deviation from the mean for GDP and unemployment rate for each data

point.

5. After organising the data in a table, input the values on the Casio FX-CG50 Graphing

Display calculator.

6. To do so, I clicked on the ‘Statistics’ function on the menu and input the values in List

1 and List 2 respectively.

 5

7. Click on ‘CALC’→’REG’ →’X’ →’a+bx’

8. The correlation coefficient is obtained as the final result, which will be denoted as the

‘r’ value on the LinearReg (a+bx) result tab.

9. To calculate the linear regression, repeat steps 2 to 7, and then:

• Using the same values inputted on List 1 and List 2 I found that the ‘a’ and ‘b’

values are also provided by the calculator.

• The intercept of y (a) and the gradient/the slope of line (b) and are obtained as

the result.

• The linear regression equation is obtained by substituting the obtained values

in the equation y = a + bx

10. To calculate R-squared value, square the correlation coefficient obtained in step 8, the

result is the R-squared value. (Also provided in the results tab along with ‘a’, ‘b’ and

‘r’ values.)

By following these steps, I was able to obtain the correlation coefficient, linear regression

equation and R-squared value between GDP and unemployment rate in India from 2011 to

2021. These findings shed light on how these two economic indicators relate to one another.
 6

Calculations and Results:

GDP (in Unemployment GDP Unemployment GDP Deviation *

Year $B) Rate (%) Deviation Deviation Unemployment Deviation

2011 1,823.05 5.43 -542.59 -0.25 135.64

2012 1,827.64 5.41 -538.00 -0.27 145.26

2013 1,856.72 5.42 -508.92 -0.26 132.31

2014 2,039.13 5.44 -326.51 -0.24 78.36

2015 2,103.59 5.44 -262.05 -0.24 62.89

2016 2,294.80 5.42 -70.84 -0.26 18.41

2017 2,651.47 5.36 285.83 -0.32 -91.46

2018 2,702.93 5.33 337.29 -0.35 -118.05

2019 2,831.55 5.27 465.91 -0.41 -191.02

2020 2667.69 8.00 302.05 2.32 700.75

2021 3173.40 5.98 807.76 0.30 242.32

Fig. 1 Table: GDP and unemployment rate in India from 2011 to 2021
 7

1. Firstly, I found the correlation coefficient,

Calculating the mean of GDP and unemployment rate using a Casio FX CG-50
graphing display calculator.
• Mean of GDP:

(3,173.40 + 2, 667.69 + 2,831.55

+2, 702.93 + 2, 651.47 + 2, 294.80
+ 2,103.59 + 2, 039.13 + 1,856.72 + 1,827.64 + 1,823.05)
= 2,365.64
11

• Mean of unemployment rate:

 5.98 + 8 + 5.27 + 5.33 + 5.36 

 
 + 5.42 + 5.44 + 5.44 + 5.42 + 5.41 + 5.43  = 5.68
11

2. Subtract the mean from each data point in the GDP and unemployment rate columns

to obtain the deviation from the mean.

• Deviation GDP = GDP - Mean GDP

• Deviation UR = Unemployment rate - Mean unemployment rate

4. Multiply the deviation from the mean for GDP and unemployment rate for each data

point

• DeviationGDP  DeviationUR

5. After creating a table with these values, I inputted my values corresponding to the

respective year for which the GDP and unemployment rate was measured.

6. Following the steps measured above, I conducted a test on the statistics mode by

entering my data sets, next I clicked on ‘CALC’→’REG’ →’X’ → ’a+bx’

Obtained ‘r’ value = 0.302

The correlation coefficient (r) = 0.302

 8

This indicates a weak positive correlation between GDP and unemployment rate.

Secondly, linear regression, here I found the linear regression by using the values previously

obtained by the calculator

1. ‘a’ value=1347.154, ‘b’ value=178.452

• The intercept of y (a) and the gradient/the slope of line (b) and are obtained as the

result in the first step.

2. The linear regression equation is obtained by substituting the values in the equation

y = a + bx

a=1347.154, b=178.452

Linear regression equation:

y = 1347.154 - 178.452x (where y is GDP and x is unemployment rate)

Lastly, I calculated the R-squared value,

1. Correlation coefficient (r) = 0.302 (calculated previously)

2. R-squared value = Correlationcoefficient 2 = (0.302)2 = 0.09

The R-squared value measures the appropriateness of the linear regression equation in terms

of fitting the given data. It has a value between 0 and 1, with a value of 0 signifying that the

linear regression equation does not fit the data at all and a value of 1 signifying that it does so

flawlessly. The R-squared value in this instance is 0.09, indicating that the linear model only

explains 9% of the variance in the data. The gradient (b) represents the GDP change for unit
 9

change in the independent variable (unemployment rate). The value of the dependent variable

(GDP) is represented by the y-intercept (a) when the independent variable (unemployment

rate) is equal to zero.

Findings

Correlation coefficient (r):

I utilised correlation coefficient as the metric to quantify the degree of correlation between

GDP and unemployment rates in India spanning from 2011 to 2021.

A correlation coefficient of 0.302 in this case indicates a slightly positive connection between

the two variables, which means that as GDP rises, the unemployment rate likewise tends to

rise.

It's worth noting that a correlation coefficient is sensitive to outliers and does not take into

account the distribution of the data. In this case, a moderate positive correlation coefficient of

0.302 suggests that there is a general trend of increasing unemployment rate as GDP

increases, but the data points that deviate from this trend, disprove this.

Linear Regression:

The findings of the linear regression analysis reveal these insights. Firstly, the slope of line

(b) is 178.452, suggesting that a 1% increase in the unemployment rate corresponds to a

178.452 billion increase in GDP. This suggests that there is a positive relationship between

unemployment rate and GDP.

Secondly, the y-intercept (a) of 1347.154 suggests that when the unemployment rate is 0%,

the GDP is 1347.154 billion.

 10

R-squared value:

A measure of the appropriateness of the linear regression equation in fitting the data is the R-

squared value. Its value ranges from 0 to 1, with 0 indicating that the linear regression

equation does not fit the data at all and 1 indicating that it does so perfectly.

Only 9% of the variation in the unemployment rate can be accounted for by the variance in

GDP, according to the R-squared value of 0.09. This means that there are other factors that

play a more significant role in determining the unemployment rate in India, rather than just

GDP.

The R-squared test indicates that, from 2011 to 2021, there's a moderate correlation between

India's GDP and unemployment rate, but that the linear regression model does not perfectly

fit the data. This suggests that other factors such as government policies, demographics, and

trade may also be influencing this relationship. Not to mention the impact COVID-19 had on

the world in 2020 and 2021. Additionally, this low R-squared value implies that there may be

other models that could better explain the relationship between GDP and unemployment rate

in India from 2011 to 2021.

 11

An anomaly in the mathematical data: Measuring COVID-19’s impact

Providing clarity to this to investigation without keeping in account COVID-19’s influence

on the economy is impossible. COVID-19’s impact on India's economy has been significant.

The country went into a nationwide lockdown in March 2020, which led to a sharp decline in

economic activity and a spike in unemployment. This is reflected in the data from 2020 and

2021, which shows a significant decrease in GDP and an increase in unemployment rate.

The impact of COVID-19 on the economy has likely distorted this relationship in the short

term, as the sudden and severe shock of the pandemic led to an unprecedented decline in

economic activity and a sharp increase in unemployment.

It is widely acknowledged that the COVID-19 pandemic had a major effect on global

economies, including India, resulting in widespread job loss and economic downturn. Many

industries, such as hospitality and travel, were hit particularly hard, leading to a spike in

unemployment rates. In addition, efforts like lockdowns and social distancing to halt the

virus's transmission had a detrimental effect on businesses and subsequently employment.

The relationship between COVID-19 and unemployment in 2020 and 2021 is complex and

multifaceted, but it is clear that the pandemic had a significant negative impact on

employment.

However, as the economy begins to recover and the country continues to fight the pandemic,

it's possible that this relationship will become stronger once again.

Thus, I conducted an additional investigation to analyse a correlation, however, the years

2020 and 2021 were subtracted from the subsequent investigation due to COVID-19’s effect

on the economy of the world.

To begin with, I conducted an outlier test to determine outliers which had a significant effect

on our variables.
 12

For calculating the outlier(s) in the data set provided, I used the method of Interquartile

Range (IQR). The steps to calculate the outlier using IQR are as follows:

1. Arrange the data set in ascending order: 5.27, 5.33, 5.36, 5.41, 5.42, 5.42, 5.43, 5.44,

5.44, 5.98, 8.00

2. Determine the data set's median value. It is the middle number when the data set is

sorted in ascending order, for this data set, median value is 5.42.

3. Determine the data set's first quartile (Q1) and third quartile (Q3). In this case, Q1 =

5.36 and Q3 = 5.44.

4. Calculate the Interquartile Range (IQR) by subtracting Q1 from Q3.

In this case, IQR = Q3 - Q1 = 5.44 - 5.36 = 0.08

5. I then utilized the following formulas to determine the data set's lower and upper

boundaries.:

• Lower bound = Q1 − 1.5  IQR = 5.36 - 1.5  0.08 = 5.24

• Upper bound = Q3 + 1.5  IQR = 5.44 + 1.5  0.08 = 5.56

6. A value is deemed an outlier if it is either lower or higher than the lower or upper

bound. In this case, the values that are greater than the upper bound are 8.00 and 5.98,

the rates for 2020 and 2021 respectively, and therefore are considered outliers.
 13

In order to visually represent this distribution, I utilised a Box and Whisker Plot Diagram,

which is a mathematical tool aiding me in visually representing the distribution of the data of

the unemployment rates of India from 2011-2021. It is used to show a data set's median,

quartiles, and range. A box and whisker plot makes it simple to spot any patterns or

abnormalities in the data by giving a clear visual depiction of the distribution and outliers of

the data set.

Here, it helps me visualise the data and the outliers, 8.00 and 5.98 which, as noted before, are

the unemployment rates of 2020 and 2021 respectively. Thus, are indicated by the red dots in

the Box and Whisker diagram above.

COVID-19 has had a significant impact on the world economy, including on the employment

rate. In India, the outbreak of the pandemic led to a lockdown, which resulted in many

businesses shutting down or reducing their operations, leading to job losses. The

unemployment rate in India increased significantly during the months of the lockdown, and it

is highly likely that the outliers of 8% and 5.98% in the unemployment rate data in 2020 and

2021 are a result of the effect of COVID on India’s economy.

 14

Calculations without outliers

Correlation Coefficient

Following the steps measured earlier, I re-conducted a test on the statistics mode by entering

my data sets, discounting the data for 2020 and 2021, next I clicked on ‘CALC’→’REG’

→’X’ → ’a+bx’

Obtained ‘r’ value = -0.862

The correlation coefficient (r) = -0.862

Indicating a strong negative correlation among GDP and unemployment rates

Linear Regression

I will use the values previously obtained by the calculator to again determine the Linear

Regression equation.

1. ‘a’ value = 33918.288, ‘b’ value = -5876.622

Performing step 1 again, which was used to calculate linear regression before, yields the

line's slope (b) and y-intercept (a), as the final result.

2. In the equation y = a + bx, the values of a and b are again substituted to produce the linear

regression equation.

a=33918.288, b=-5876.622

Linear regression equation: y = 33918.288 + (−5876.622) x

(where y is GDP and x is unemployment rate)

.
 15

Mathematical Analysis of Findings and Results

An in-depth analysis of the correlation coefficient of -0.862 between GDP and

unemployment rate in India from 2011 to 2021 reveals several key insights. Firstly, the strong

inverse relationship between India's economic growth and unemployment rate is indicated by

the strong negative correlation coefficient. This is in line with the general economic theory

that economic growth generates jobs and reduces unemployment. The negative correlation

coefficient indicates that as GDP increases, unemployment rate decreases, and as GDP

decreases, unemployment rate increases. Moreover, compared to the initial investigation, the

removal of outliers, with GDP values of 8.00 and 5.98, further strengthens the correlation

coefficient and r-squared values, indicating the robustness of the relationship. This suggests

that as the Indian economy grows, more jobs are created and unemployment rate falls, which

is a positive sign for the Indian economy.

The second linear regression equation y = 33918.288 + (−5876.622) x , where y represents

GDP and x represents the unemployment rate in India from 2011 to 2021, can provide further

insight into the relationship between these two variables.

The y-intercept of the equation, 33918.288, represents the GDP when the unemployment rate

is 0%. The coefficient of the x variable, -5876.622, represents the change in GDP for every

1% change in unemployment rate. This negative coefficient indicates that as the

unemployment rate increases by 1%, the GDP decreases by 5876.622. This corresponds to

the negative correlation coefficient found earlier between GDP and unemployment rate,

which shows that economic growth is associated with a decrease in the unemployment rate.

Secondly, the y-intercept (a) of 33918.288 indicates that when the unemployment rate is 0%,

the GDP is 33918.288 billion. This value represents the GDP when there is full employment,

and can be used as a benchmark for economic growth.

 16

Thirdly, the linear regression equation y = 33918.288 - 5876.622x can be used to make future

predictions about the relationship between GDP and unemployment rate.

Additionally, the R-squared value of 0.74 indicates that the fluctuation in the unemployment

rate explains 74% of the variation in GDP. This suggests a significant correlation between

India's GDP and unemployment rate from 2011 to 2021. Although, there can be other factors

slightly influencing the relationship between GDP and unemployment rate in India, and this

relationship may be more complex than a simple linear relationship. Factors such as

government policies, demographics, and technology could be affecting both GDP and

unemployment rate, should also be considered when interpreting these results.

Note of other factors

In addition to GDP and unemployment rate, inflation, demographic data and trade data

should also be noted to provide a more comprehensive understanding of the relationship.

Economic growth and employment are negatively impacted by inflation as assessed by the

Consumer Price Index (CPI). Demographic data such as population growth, urbanization, and

education levels also play a role in the relationship between GDP and unemployment rate.

For instance, a population that is fast expanding can strain the labour market and raise

unemployment, whereas a population that is well educated can result in a more productive

workforce and a reduction in unemployment. Trade data can also provide valuable insights on

the relationship between GDP and unemployment rate. The balance of trade (exports vs

imports) and the types of goods traded can have an impact on economic growth and

employment. For example, a country that specializes in exporting high-tech goods may have

a different relationship between GDP and unemployment rate compared to a country that

specializes in exporting raw materials.

 17

Limitations and Scope for Further Research

It is important to note that this analysis has limitations, unfortunately. Firstly, the data used in

this analysis only covers the period from 2011 to 2021, so it does not provide a long-term

perspective on the relationship between GDP and unemployment rate in India. Besides,

correlation does not imply causation, and other factors such as government policies,

demographic and trade data may be influencing both GDP and unemployment rate. COVID-

19 too played a big role in my investigation and its effect on economic growth was apparent

and widespread. Therefore, it is important to conduct further research to understand the

causal relationship between GDP and unemployment rate in India, moreover, investigating

how our economy recovers from the effects of COVID-19 can also help in conducting a

deeper analysis of this relationship.

 18

Conclusion

I derived numerous important conclusions on my investigation of the relationship between

India's GDP and unemployment rates between 2011 and 2021. The strong negative

correlation coefficient of -0.862 suggests that economic growth in India is associated with a

decrease in the unemployment rate. This finding aligns with the accepted understanding in

economics that a growing economy leads to job creation and a decrease in unemployment.

Furthermore, the linear regression model addresses 74% of the variation in the data,

indicating a strong correlation, according to the high R-squared value of 0.74. This supports

the findings showing a significant inverse relationship between India's GDP and

unemployment rate.

I will also state that the values I obtained earlier without removing the outliers, which were

the rates for the COVID years of 2020 and 2021, provided me a correlation coefficient of

0.302. The inclusion of these years clearly skewed the results, and further analysis with the

exclusion of these years yielded me a completely different result. As a result, also showing

the extent of damage of an extenuating circumstance like COVID-19. Also, analyzing other

factors such as inflation, demographic and trade data would provide a more comprehensive

understanding of this relationship. It is important to continue to study and understand the

relationship between these two key economic indicators to make informed policy decisions

and promote sustainable economic growth in India, therefore, enabling the betterment of the

country, leading to holistic development.

 19

Bibliography
Belcher, Paul. Mathematics : Applications and Interpretation. Standard Level. Course Companion. Oxford,

United Kingdom, Oxford University Press, 2019.

“GDP (Current US$) - India | Data.” [Link],

[Link]/indicator/[Link]?end=2021&locations=IN&start=2011. Accessed 28 Jan.

2023.

“Unemployment, Total (% of Total Labor Force) (Modeled ILO Estimate) | Data.” [Link],

[Link]/indicator/[Link]?end=2021&start=2011.

“Correlation: Pearson’s & Spearman’s [IB Math AI SL/HL].” [Link],

[Link]/watch?v=EyMHz5k4SU0&t=345s. Accessed 28 Jan. 2023.

“Line of Regression Equation (& Reliability) [IB Math AI SL/HL].” [Link],

[Link]/watch?v=biyosVy8it4&t=1s. Accessed 28 Jan. 2023

“Coefficient of Determination (R-Squared) - Definition, Formula & Properties.” BYJUS,

[Link]/maths/coefficient-of-determination/#:~:text=The%20coefficient%20of%20determination%20or.

“Quartiles, Interquartile Range, Box & Whisker Diagrams [IB Math AI SL/HL].” [Link],

[Link]/watch?v=PwnVr3uQKCs. Accessed 28 Jan. 2023.

Upadhyay, Alex. “Impact of Covid-19 on Indian Economy.” Times of India Blog, [Link],

24 July 2021, [Link]/readersblog/mymusiclife/impact-of-covid-19-on-indian-economy-4-

35585/.

Agarwal, Prateek. “Unemployment in India.” Intelligent Economist, 19 Nov. 2018,

[Link]/unemployment-in-india/.
 20

Appendices

Appendix 1: Graph for the values for the GDP of India from 2011-2021.

Appendix 2: Table for the values for the GDP of India from 2011-2021.

Appendix 3: Graphed values for the unemployment rates of India from 2011-2021, obtained

from the World Bank website.

Appendix 4: Table for the values for the unemployment rates of India from 2011-2021.

(All raw data is obtained from the official World Bank website)