Royal UniversityPRICE འབྲུག་རྒྱལ་འཛིན་གཙུག་ལག་སློ

of AND DEMAND OF ONION IN INDIA བ་སྡེ།

Bhutan
Gedu College of Business དགེ་འདུ་ཚློང་རིག་མཐློ་རིམ་སློབ་གྲྭ།
Studies
Gedu: Chukha དགེ་འདུ་ ཆུ་ཁ།

Group Assignment

DECLARATION FORM

Module Code: BMS202 Section: D

Module Name: Statistics for Solving Business Problem Type of Course Work: Group
Module Tutor: Mrs. Priya Sharma Date of Submission: 10/12/2020

We hereby declare that this academic work is our own and those derived from other sources have been
appropriately acknowledged. We understand that if found otherwise, our academic work will be cancelled
and no mark will be awarded besides the legal consequences.

Name Student No. Program Section Signature

Ugyen Tshomo 03190440 Finance D

Yenten Jamtsho 03190452 Finance D
Yeshi Wangchuk 03190465 Finance D
Ugyen Tshering 03190436 Finance D
Upendra Dhakal 03190444 Finance D

Module tutor: Mrs. Priya Sharma

Comments: ………………………………………………………..
Signature of Module Tutor
 PRICE AND DEMAND OF ONION IN INDIA

Introduction
Linear regression analysis is the widely used of all statistical techniques. Simple linear regression
is statistical method that allows us to summarize and study relationship between two continuous
variables. We assume that the relationships between variables are linear because:
 Linear regression are simplest non-trivial relationships that can be imagined.
 The ‘true’ relationship between our variables are often at least approximately linear over
the range of values that are interest to us.
 We can often transform the variables in such a way as to linearize the relationships.
Linear regression attempts to model the relationship between two variables by fitting a linear
equation to observed data. It has an equation of the form Y = a + bX, where X is the explanatory
variable and Y is the dependent variable.
If the correlation coefficient indicates a sufficiently strong relationship (direct or inverse)
between variables, we may wish to explore that relationship using regression techniques.
Goal of simple linear regression:
It is to predict the value of a independent variable based on an independent variable.
The greater the linear relationships between the independent variable and the dependent variable,
the more accurate the prediction.
The syntax to calculate each of the terms in the regression is as follows:
• Slope, m: =SLOPE(known_y's, known_x's)
• y-intercept, b: =INTERCEPT(known_y's, known_x's)
• Correlation Coefficient, r: =CORREL(known_y's, known_x's)
• R-squared, r2: =RSQ(known_y's, known_x's)

1
 PRICE AND DEMAND OF ONION IN INDIA

Following is the data of price of Onion and quantity demanded in India in the year 2011.

Month Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
Average Price 9 10 14 11 15 11 16 13 17 17 20 19
(in thousand)
Demand 179 162 137 169 144 158 142 145 121 118 111 105
(in thousand)

3) Conduct a regression analysis and obtain the regression equation and the coefficient of
correlation. Use excel to perform the regression analysis
Regression Analysis using Excel Environment
Regression analysis between the price and quantity supply of Coca-Cola Company.
Let Independent variable (Price) be X, and Dependent variable (supply) be Y.
Obtain regression equation Supply on Price that is Y on X using excel.
We have three methods in excel to obtain a regression equation they are;
1. Using excel functions
2. Using scatter plot chart
3. Using data analysis tool

Method (1) using excel functions

Steps:
 Obtain linear equation ( Y= a+bx),
 a= Y-intercept
 b= Slope
To find Y-intercept (a) use a excel function =INTERCEPT (known_y’s, known_x’s)
 Select supply column (Y) for argument (known_y’s) which is dependent variable and
 Select price column (X) for argument (known_x’s) which is independent variables.
After entering the argument click enter button and Y-intercept will be shown on the spreadsheet
as follows;

2
 PRICE AND DEMAND OF ONION IN INDIA

To find Slope (b) use a function =SLOPE (known_y’s, known_x’s)

 Select supply column (Y) for argument (known_y’s) which is dependent variable and
 Select price column (X) for argument (known_x’s) which is independent variables.
After entering the argument click enter button and slope will be shown on the spreadsheet as
follows;

3
 PRICE AND DEMAND OF ONION IN INDIA

Obtain Karl Pearson’s Correlation coefficient

To obtain Karl Pearson’s Correlation coefficient use a function =CORREL(array1,array2)
 In the case of arguments of the function that is array1 and array2 use either of column (X
and Y) in any order be it in array 2 or array 2.
 If used X column in array1, use Y column array2 and vice versa
After entering the argument click enter button and slope will be shown on the spreadsheet as
follows;

 Obtain coefficient of determination ( r square)

To obtain coefficient of determination use a function =RSQ (known_y’s, known_x’s)
and for arguments use the X and Y column on known x’s and known y’s respectively and
then click on enter button. The result will be shown as follows;

4
 PRICE AND DEMAND OF ONION IN INDIA

Finally, slope, Y-intercept, Karl Pearson’s correlation and the coefficient of determination shown
the spreadsheet as follows. Substitute the value of Y-intercept and slope in the linear equation
that is Y= a+bx

Method 2: Using Scatter Plot

Step 1; Firstly, Select X and Y column and go to insert and click on insert scatter and
choose simple scatter. Our scattered graph will be shown as below

5
 PRICE AND DEMAND OF ONION IN INDIA

Step 2. Go to chart elements and add required elements as shown below

 Again click on chart element and go to Trendline and click on the arrow which is
shown on the right side of trendline.
 Then select more options where it will show a panel called Format Trandline
 Inside panel select Linear (Trendline options), Automatic (Treandline name),
Display equation of chart and display R-squared value as shown below.

6
 PRICE AND DEMAND OF ONION IN INDIA

Finally our graph and regression equation will be shown on the spreadsheet

Method 3; Using Data Analysis

Steps:
 Select the data
 Go to data and click on Data analysis
 From the dialog box select Regression
 Now, in Input Y range select Y column (dependent) and in Input X range select X
column(Independent)
 Now in output range select where our output is to be shown in the spreadsheet

7
 PRICE AND DEMAND OF ONION IN INDIA

Final the output will be generated automatically as shown in the spreadsheet below;

Regression equation and value of slope, Y-intercept, Karl Pearson correlation and
coefficient of determination when we interchange the value of dependent and Independent
variable are as follows;

8
 PRICE AND DEMAND OF ONION IN INDIA

Manual solution to obtain regression equation and Karl Pearson’s correlation coefficient.
Solution:
Let X be Average Price (in thousand) and let Y be Demand (in thousand)

Month Average Price Demand

(in thousand) (in million) XY X2 Y2
(X) (Y)
Jan 9 179 1,611 81 32,041
Feb 10 162 1,620 100 26,244
Mar 14 137 1,918 196 18,769
Apr 11 169 1,859 121 28,561
May 15 144 2,160 225 20,736
Jun 11 158 1,738 121 24,964
Jul 16 142 2,272 256 20,164
Aug 13 145 1,885 169 21,025
Sep 17 121 2,057 289 14,641
Oct 17 118 2,006 289 13,924
Nov 20 111 2,220 400 12,321
Dec 19 105 1,995 361 11,025
𝟐
∑ 𝑿 = 𝟏𝟕𝟐 ∑ 𝒀 = 𝟏, 𝟔𝟗𝟏 ∑ 𝑿𝒀 = 𝟐𝟑, 𝟑𝟒𝟏 ∑ 𝑿 = 𝟐, 𝟔𝟎𝟖 ∑ 𝒀𝟐 = 𝟐𝟒𝟒, 𝟒𝟏𝟓

∑𝑿 𝟏𝟕𝟐
̅ =
𝑿 = = 𝟏𝟒. 𝟑𝟑
𝑵 𝟏𝟐

∑𝒀 𝟏, 𝟔𝟗𝟏
̅ =
𝒀 = = 𝟏𝟒𝟎. 𝟗𝟐
𝑵 𝟏𝟐

9
 PRICE AND DEMAND OF ONION IN INDIA

Y on X X on Y
𝒏 ∑ 𝑿𝒀 − ∑ 𝑿 . ∑ 𝒀 𝒏 ∑ 𝑿𝒀 − ∑ 𝑿. ∑ 𝒀
𝒃𝒀𝑿 = 𝟐
𝒃𝑿𝒀 =
𝒏 ∑ 𝑿 − (∑ 𝑿)𝟐 𝒏 ∑ 𝒀𝟐 − (∑ 𝒀)𝟐

(𝟏𝟐×𝟐𝟑,𝟑𝟒𝟏)−(𝟏𝟕𝟐×𝟏,𝟔𝟗𝟏) (𝟏𝟐×𝟐𝟑,𝟑𝟒𝟏)−(𝟏𝟕𝟐×𝟏,𝟔𝟗𝟏)
= =
(𝟏𝟐×𝟐,𝟔𝟎𝟖)−(𝟏𝟕𝟐)𝟐 (𝟏𝟐×𝟐𝟒𝟒,𝟒𝟏𝟓)−(𝟏,𝟔𝟗𝟏)𝟐

𝟐𝟖𝟎,𝟎𝟗𝟐−𝟐𝟗𝟎,𝟖𝟓𝟐 𝟐𝟖𝟎,𝟎𝟗𝟐−𝟐𝟗𝟎,𝟖𝟓𝟐
= =
𝟑𝟏,𝟐𝟗𝟔−𝟐𝟗,𝟓𝟖𝟒 𝟐,𝟗𝟑𝟐,𝟗𝟖𝟎−𝟐,𝟖𝟓𝟗,𝟒𝟖𝟏

−𝟏𝟎,𝟕𝟔𝟎 −𝟏𝟎,𝟕𝟔𝟎
= =
𝟏,𝟕𝟏𝟐 𝟕𝟑,𝟒𝟗𝟗

= −𝟔. 𝟐𝟖𝟓𝟎 = −𝟎. 𝟏𝟒𝟔𝟒

Regression Equation on Y on X Regression Equation on X on Y

̅ = 𝒃𝒀𝑿 (𝑿 − 𝑿
𝒀−𝒀 ̅) ̅ = 𝒃𝑿𝒀 (𝒀 − 𝒀
𝑿−𝑿 ̅)

𝒀 − 𝟏𝟒𝟎. 𝟗𝟐 = −𝟔. 𝟐𝟖𝟓𝟎(𝑿 − 𝟏𝟒. 𝟑𝟑) 𝑿 − 𝟏𝟒. 𝟑𝟑 = −𝟎. 𝟏𝟒𝟔𝟒(𝒀 − 𝟏𝟒𝟎. 𝟗𝟐)

𝒀 − 𝟏𝟒𝟎. 𝟗𝟐 = −𝟔. 𝟐𝟖𝟓𝟎𝑿 + 𝟗𝟎. 𝟎𝟔𝟒𝟏 𝑿 − 𝟏𝟒. 𝟑𝟑 = −𝟎. 𝟏𝟒𝟔𝟒𝒀 + 𝟐𝟎. 𝟔𝟑𝟎𝟕

𝒀 = −𝟔. 𝟐𝟖𝟓𝟎𝑿 + 𝟗𝟎. 𝟎𝟔𝟒𝟏 + 𝟏𝟒𝟎. 𝟗𝟐 𝑿 = −𝟎. 𝟏𝟒𝟔𝟒𝒀 + 𝟐𝟎. 𝟔𝟑𝟎𝟕 + 𝟏𝟒. 𝟑𝟑

𝒀 = −𝟔. 𝟐𝟖𝟓𝟎𝑿 + 𝟐𝟑𝟎. 𝟗𝟖𝟒𝟏 𝑿 = −𝟎. 𝟏𝟒𝟔𝟒𝒀 + 𝟑𝟒. 𝟗𝟔𝟎𝟕

Karl Pearsons Correlation coefficient;

𝒓 = √𝒃𝑿𝒀 − 𝒃𝒀𝑿
= ±√𝟔. 𝟐𝟖𝟓𝟎 × 𝟎. 𝟏𝟒𝟔𝟒

= ±√𝟎. 𝟗𝟐𝟎𝟏

= −𝟎. 𝟗𝟓

10
 PRICE AND DEMAND OF ONION IN INDIA

Question 4: Make conclusion

Regression line of Y on X
Keeping Y (demand for onion) as dependent variable and X (average price of onion per tonne) as
the independent variables we obtain the following result;
 Equation as; Y = 231 - 6.285X
 Y-intercept as; 231
 Slope as; -6.285
 Coefficient of determination as; 0.920
 Coefficient of correlation as; -0.959

From the above equation we came to know that (interpretation)

 Y-intercept is 231; it means that when the average price is equal to 0, supply will be
231million units of quantity. From this information we can conclude that 231 units of
quantity worth product are supplied at free of cost may be to their relatives, charity, free
distribution to the workers and etc.

 Slope of regression line Y on X is -6.285; it means that when average price increased by
1 unit on average, it will result in 6.285 million quantity decrease in supply of onion in
India in 2011.
 From the sign of a regression coefficient tells us whether there is positive or negative
correlation between each dependent and the independent variables. A negative coefficient
of 0.959 indicates that as the value of the independent variable (average price) increases,
the mean of the dependent variable (quantity demand of onion) will decrease as shown on
the regression line in previous page with the help of excel function.

 We can calculate coefficient of determination to compare the model relationships. So to

calculate coefficient of determination use =RSQ(dependent variable, independent
variables) function, so when we compute the value we found 0.920 which lies in very
high degree of correlation. Therefore we can conclude that this relation can give us better
prediction of the unknown variables.

 We computed the coefficient of correlation between quantity demand and the average
price of onion as shown on the previous solution. With the help of the coefficient of
correlation we can know about statistical relationship between two variablesInvalid
source specified.. In other word it shows how two variables move in relation to one
another. We obtain the result as -0.959 which lies in negatively very high degree of
correlation category. Therefore the relation is strong and the predicted value will be valid.

11
 PRICE AND DEMAND OF ONION IN INDIA

Regression line of X on Y
Keeping Y (quantity demand) as independent variable and X (average price) as the dependent
variables we obtain the following result;
 equation as; X = 34.963 - 0.1464Y
 X-intercept as; 34.963
 Slope as; - 0.1464
 Coefficient of determination as; 0.920
 Coefficient of correlation as; -0.959

From the above equation we came to know that (interpretation)

 X-intercept is 34.963; it means that when the quantity demand of onion in 2011 is equal
to 0, average price will be 34.963. From this information we can conclude that 34.963 of
fixed costs is required to produced 1 million units of onion. Fixed costs are required to
pay for tax, rent, power even if the firm are not producing any quantity of goods.

 Slope of regression line Y on X is - 0.1464; it means that when average quantity demand
of onion increased by 1 unit it will result in 0.1464 decreases in average price of onion in
India.

 From the sign of a regression coefficient tells us whether there is positive or negative
correlation between each dependent and the independent variablesInvalid source
specified.. A negative coefficient of -0.959 indicates that as the value of the independent
variable (average price) increases, the mean of the dependent variable (quantity demand
of onion in million) will decrease.

 We can calculate coefficient of determination to compare the model relationships. So to

calculate coefficient of determination use =RSQ(dependent variable, independent
variables) function, so when we compute the value we found 0.920 which lies in very
high degree of correlation. Therefore we can conclude that this relation can give us better
prediction of the unknown variables.

 We computed the coefficient of correlation between quantity demand and the average
price of onion as shown on the previous solution. With the help of the coefficient of
correlation we can know about statistical relationship between two variables. In other
word it shows how two variables move in relation to one another. We obtain the result as
-0.959 which lies in negatively very high degree of correlation category. Therefore the
relation is strong and the predicted value will be valid.

12
 PRICE AND DEMAND OF ONION IN INDIA

Significance of the result

In statistics, the purpose of the regression equations are to come up with an equation like model
that represents the flow of pattern or patterns present in the collected data. So let’s discuss what
the regression equation is all about.
The Variables
Essentially in statistic, we use the regression equation to predict the values of a dependent
variable. This dependent variable is also called the outcome variable. It is the effect that we are
interested in predicting, such as the amount of quantity demand with regard to assumed average
price and vice versa as we have shown the detail calculation in the upcoming page.

The independent variable for this gross data which we have collected from the average price of
onion is predictor variable. In our group project work, we are going to consider the price per
units. This means that we can be in position to think/find the quantity demand of onion.
Let’s see the simple scatter plot of the data which we have obtained with the help of excel
function.

25

20

Price 15
per
unit 10

0
0 50 100 150 200

Quantity supplied in million units

Just by looking at the graphic, we could notice a slight downward trend in the data. This suggests
that the average price and the quantity demanded of onion have a negative relationship with
these two variables.
Unfortunately, the graph itself is not a statistical model that we can use to predict and describe
the data. We can’t offer a clear and reliable prediction of the price per tone and quantity demand
of onion.

13
 PRICE AND DEMAND OF ONION IN INDIA

The Regression Equation

A regression equation is a statistical model that is used to determine the specific relationship
between the predictor variable and the outcome variable. A model regression equation allows
you to predict the outcome with a relatively small amount of errorInvalid source specified..
Y = 231 - 6.285X (Y = b + aX)
In this model, Y (demand for onion in million) represents an outcome variable and X (average
price) represents its corresponding predictor variable. The equation also contains numerical
relationships between the predictor and the outcome.
The 231 in the equation represents an intercept for the model if the predictor be a zero value.
You could consider it something like a baseline or control point. This term represents the
numerical relationship between the predictor variable and the outcome for the unknown term.
These are called regression coefficients.
Using the method of least squares, we can determine the line of best fit for a series of data. We
have taken the liberty of finding the line of best fit for our price and quantity supply in millions
units.

25

20 y = -0.1464x + 34.963
R² = 0.9201

15
Price
Series1
Per
10 Linear (Series1)
unit
5

0
0 50 100 150 200

Quantity supplied in million

Now we have a mathematicalunits
model. Since there is a line, we can create an equation to describe
and predict data points.

14
 PRICE AND DEMAND OF ONION IN INDIA

Question 5; apply the model to the real world.

When it comes to the application of this model in the real world, we can use this regression
equation to study the functional relationship between the variable and thereby prediction or
forecasting can be possible.
We have obtained the two regression equation in the previous part of our assignment therefore
we can use this equation in predicting future dependent variable as; the quantity demand in
million when price is Rs 25 and average price when quantity demand in million is 200.
Regression line of Y on X (when X = 25)
Y = 231 - 6.285X
Y = 231 - 6.285 * 25
Y = 73.875 million units of onion

Regression line of X on Y (when Y = 200 units of quantity)

X = 34.963 - 0.1464Y
X = 34.963 - 0.1464 * 200
X = Rs 5.683

15
 PRICE AND DEMAND OF ONION IN INDIA

How your conclusions might impact the real world?

We can use regression equation to study the functional relationship between the variable and
thereby prediction or forecasting can be possible but in practical life, sometime it may not
happened as per the prediction done with the help of regression equation. Therefore our
conclusion which we have drawn recently might be impacted in the real world as follows;
I. We have found that due to negative relation of data, at lower price there is greater
quantity demand of onion but in real satiation there will be not much production by
farmer due to limited resources and they are reluctant to produce more at lower price.

II. Since onion is perishable goods they cannot really apply the result obtained from
regression equation since they cannot store the onion for longer duration if there is fall in
demand.
III. Since onion is necessities goods, therefore when the price is lower there is greater
demand as per the finding. But in real life quantity demand will increase slightly and
remain constant even if piece continuously fall since quantity use of onion during curry
will be almost constant.

In conclusion the correlation is another method to forecast the sales, demand and supply.
Correlation looks at the strength of relationship between two variables. Likewise, through our
conclusion the business may be able to interpret and predict the relationship between price and
quantity demanded whereby business will be aware of increasing price and its impact on supply
and demand of the product. Eventually, business shall alter the price of goods and services to
increase the volume of sales quantitatively and qualitatively. Business shall learn that increasing
the price will decrease quantity demand from the customers which ultimately impacts the sales
and income of the business and on other hand decreasing the price shall increase the demand but
have to think and decide more while decreasing the price drastically which may affect the profit
margin though sales may increase.
However, the negative expected impacts shall be unreliable data to some extent. Though there is
negative relationship between price and quantity demanded in our extracted data and conclusion
where it was depicted as with decrease in price it may increase the quantity demanded however,
with advancement in technology and innovation even with increasing price the demand shall
remain same or increase thus, we shall conclude that our conclusion shall not be always a
reliable data in real application.

16
 PRICE AND DEMAND OF ONION IN INDIA

How can you take advantage of your data or why your data is not useful?
Advantages of Linear Regression that we can take as we apply in reality are as follows;
 Simple implementation
Linear Regression is a very simple algorithm that can be implemented very easily to give
satisfactory results. Furthermore, these models can be trained easily and efficiently even on
systems with relatively low computational power when compared to other complex algorithms.
Linear regression has a considerably lower time complexity when compared to some of the other
machine learning algorithms. The mathematical equations of linear regression are also fairly easy
to understand and interpret. Hence linear regression is very easy to master.

 Performance on linearly separable datasets

Linear regression fits linearly separable datasets almost perfectly and is often used to find the
nature of the relationship between variables.
 Over fitting can be reduced by regularization
Over fitting is a situation that arises when a machine learning model fits a dataset very closely
and hence captures the noisy data as well. This negatively impacts the performance of model and
reduces its accuracy on the test set. Regularization is a technique that can be easily implemented
and is capable of effectively reducing the complexity of a function so as to reduce the risk of
over fitting.

17
 PRICE AND DEMAND OF ONION IN INDIA

Conclusion
This project has enabled us to examine historical data and analyzed past records which helps us
to understand data to make better decisions, including prediction of sales. With the help of this
project, we are able to forecast about the future price and demand of the Onion in India and it
also helped us in finding ways to improve the efficiency of the business process. It is very
important for getting better results in future. All in one, the completion of this project furnished
us distinguished opportunity to expand our knowledge on the topic ‘regression analyses.
Nevertheless, we enjoyed doing this project and we are pretty sure that this project will definitely
help us in our future endeavor.

18
 PRICE AND DEMAND OF ONION IN INDIA

Reference
(2016, March 21). Retrieved from https://macrotrends.net/stocks/charts/KO/cocacola/stock-
price-history
The Superior University, Lahore. (2015, January 1). Retrieved from
https://www.slideshare.net/mobile/Faazi321/market-demand-and-supply-of-coke

19