Lecture 2

Please ensure that your
registered name is being

displayed on your zoom
device… Eg. Shanice Smith
Introduction to Business & Economic
Statistic: MTH201
Lecturer: Chrystal Rhone

Refresher…
 Range = (Max. data entry) – (Min. data entry)
 Variance
The average of the squared differences from the mean
2
 ( x   )  ( x  x ) 2
2  s2 
N n 1
 Standard deviation
The square root of the Variance
( x   ) 2
2 ( x  x ) 2
   s 2
s 
N n 1
Measures of Dispersion:
Population Variance and Standard Deviation
Example
You grow 5 carrots in your backyard and
measure the length of each carrot in
centimeters. Here is your data:
9 7 5 4 12
Calculate variance, standard deviation and

range
Solution
2
 ( x   )
2 
N
9 7 5 4 12
Calculate the mean

x = 7.4
N
Solution  
( x   ) 2
2
Mean = 7.4 N
Length of Deviations: Squares:

carrots (cm) x–μ (x – μ)2
9 9 -7.4 = 1.6 (1.6) 2 = 2.56
7 7 -7.4 = -0.4 (-0.4) 2 = 0.16
5 5 -7.4 = -2.4 (-2.4) 2 = 5.76
4 4 -7.4 = -3.4 (-3.4) 2 = 11.56
12 12 -7.4 = 4.60 (4.6) 2 = 21.16
Σ(x – μ) = 0 Σ(x – μ)2 = 41.2
Solution Population Variance
2 ( x   ) 2
 
Squares: N
Length of Deviations:
41.2
carrots (cm) x–μ (x – μ) 2 𝜎 2= =8.24 𝑐𝑚2
5
9 9 -7.4 = 1.6 (1.6)2 = 2.56
7 7 -7.4 = -0.4 (-0.4)2 = 0.16 Population Standard deviation
2
( x   )
  2 
5 5 -7.4 = -2.4 (-2.4)2 = 5.76 N
4 4 -7.4 = -3.4 (-3.4)2 = 11.56 8.24 = 2.87 cm
12 12 -7.4 = 4.60 (4.6)2 = 21.16
Σ(x – μ) = 0 Σ(x – μ)2 = 41.2
Range
Max value – Min value
12-4 = 8
Sample Variance and Standard Deviation
Example
Lets assume we have the following sample
data: 12 18 7 10
Calculate variance, standard deviation and

range
Sample Variance and Standard Deviation
2
Solution  ( x  x )
s2 
n 1
n= ?
? 𝒙
x x – ̅ ሺ࢞࢏ െ࢞ഥሻ૛
12
18
7
10
( x  x ) 2
s2 
n 1
Sample Variance and Standard Deviation 2
 ( x  x )
Solution s2 
n 1
n= 4 𝒙
x x – ̅ ሺ࢞࢏ െ࢞ഥሻ૛
12 0.25 0.0625 n-1 𝒙 3
18 6.25 39.0625 mean 11.7500
7 -4.75 22.5625 Σ(x – ̅) 0
10 -1.75 3.0625 Σ ሺ࢞࢏ െ࢞ഥሻ૛ 64.7500
Σ ሺ࢞࢏ െ࢞ഥሻ૛/n-1 21.583
Variance = 21.583
Std 4.646
Range = 18-7 =11
Unit 2
Correlation
 Correlation is an association or relationship
between two quantitative variables [NOTE:
Correlation is not (does not imply) causation!!!]
 Two variables are said to be correlated if changes

in one variable are associated with changes the
other variable.
 Correlation can be assessed both graphically and

numerically.
Assessing Correlation Graphically -
Scatterplots
It is used to examine:
 If there is a linear (straight line) relationship
between the quantitative variables
 The direction of the relationship (positive or
negative), if any
 The strength of the relationship (are the plots
closely clustered or dispersed), if any
 If there is any noticeable deviations (outliers) from
the relationship.
How to construct Scatterplots
Example:
The local ice cream shop keeps track of how much ice cream
they sell versus the noon temperature on that day. Here are
their figures for the last 12 days:
Ice Cream Sales vs Temperature
Temperature °C Ice Cream Sales
14.2° $215
16.4° $325
11.9° $185
15.2° $332
18.5° $406
22.1° $522
19.4° $412
25.1° $614
23.4° $544
18.1° $421
22.6° $445
17.2° $408
How to construct Scatterplots
Interpreting scatterplots
Direct Positive
Linear Relationship
Data Correlation Direct Negative Linear

Relationship
No Relationship
Outliers
Assessing Correlation Numerically –
Correlation Coefficient
 An objective numerical measure of correlation.

 It provides a quantitative measure of the strength of
the relationship between two variables.
 The coefficient can take any values from -1 to 1.
The correlation coefficient, denoted by r, can take on
any value from -1 to 1:
𝒓𝒓 = -1 indicates a perfect negative linear relationship
 -1 <𝒓𝒓< 0 indicates a negative linear relationship
𝒓𝒓 = 0 indicates no linear relationship
 0 <𝒓𝒓 < 1 indicates a positive linear relationship
𝒓𝒓 = 1 indicates a perfect positive linear relationship

Pearson Correlation Coefficient:
Alternative formula
Lets talk direction and strength
Example
Use the information in the table below to calculate the
correlation coefficient.
࢞ ࢟
17 150
15 154
19 169
17 172
21 175
89 820
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17 150
15 154
19 169
17 172
21 175
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17 150 N=?
15 154
19 169
17 172
21 175
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17 150 N=5
15 154
19 169
17 172
21 175
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17 150 N=5
∑ 𝑥=?
15 154
19 169
17 172
∑ 𝑦=?
21 175
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17 150
N=5
∑ 𝑥=89
15 154
19 169
17 172
∑ 𝑦=820
21 175
89 820
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17
15
19
150
154
169
∑ 𝑥=89
N=5
∑ 𝑦=82
∑ (𝑥×𝑦)=?
17 172
21 175
89 820
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17
15
150
154
2,550
2,310
∑ 𝑥=89
N=5
∑ 𝑦=82
19
17
21
169
172
175
3,211
2,924
3,675
∑ (𝑥×𝑦)=14,670
89 820 14,670
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17
15
150
154
2,550
2,310
∑ 𝑥=89
N=5
∑ 𝑦=82
19
17
169
172
3,211
2,924 ∑ (𝑥×𝑦)=14,670
21 175 3,675
∑ 𝑥 =? ∑ 𝑦 =?
89 820 14,670
2 2
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17 150 2,550 289 22,500 ∑ 𝑥=89
N=5
∑ 𝑦=82
∑ (𝑥×𝑦)=14,670
15 154 2,310 225 23,716
19 169 3,211 361 28,561
17 172 2,924 289 29,584
21 175 3,675 441 30,625 1,605
89 820 14,670 1,605 134,986
134,986
Solution
࢞ ࢟ ࢞ൈ
࢟ ࢞૛ ࢟૛
17 150 2,550 289 22,500
15 154 2,310 225 23,716
19 169 3,211 361 28,561
17 172 2,924 289 29,584
21 175 3,675 441 30,625
89 820 14,670 1,605 134,986
Solution using alternative formula
࢞ ࢟ ࢞࢏ െ࢞
ഥ ࢟࢏ െ࢟
ഥ ෍ ሺ࢞࢏ െ
࢞ഥሻሺ࢟࢏ െ࢟
ഥሻ ሺ࢞࢏ െഥሻ૛ ሺ࢟࢏ െ
࢞ ഥሻ૛
࢟
17 150 -0.8 -14 11.2 0.64 196

15 154 -2.8 -10 28 7.84 100
19 169 1.2 5 6 1.44 25
17 172 -0.8 8 -6.4 0.64 64
21 175 3.2 11 35.2 10.24 121
74.0 20.8 506.0
Facts About Correlation
 The order of variables in a correlation is not important.
 Correlations provide evidence of association, not
causation.
 r has no units
 Positive r values indicate positive association between
the variables, and negative r values indicate negative
associations.
 The correlation r is always a number between -1 and 1.
Simple Linear Regression
Analysis
Simple Linear Regression Analysis
 Regression model is a mathematical equation

that describes the relationship between two or
more variables. A simple regression model
includes only two variables: one independent
and one dependent.
 The dependent variable is the one being
explained/predicted; and
 The independent variable is the one used to
explain the variation in the dependent variable.
• Ordinary least squares is the most common type
of linear regression.
Simple Linear Regression Analysis
What factors or variables does a household
consider when deciding how much money it should
spend on food?
 Income
 Size of household
 Preferences and taste
Independent variable =?
Dependent Variable =?
Simple Linear Regression: Equation
 Population : Y   0  1X  
 Sample: regression line
Where
Y = dependent variable (response)
X = independent variable (predictor or explanatory)
0 = intercept (value of Y when X = 0)
1 = slope of the regression line
e = random error (unexplained variation)
= the estimated or predicted value of y based on regression
model
Simple Linear Regression: Estimating
Alpha & Beta
^
𝒚 =𝜶 +𝒃 𝒙 Slope coefficient:
y - intercept:
Or
Or
Example:
A sample of households was taken from a small city and information
on their incomes and food expenditures is displayed in the table
below (in hundreds of dollars: find the values of and for the
regression model
Income Food Expenditure
55 14
83 24
38 13
61 16
33 9
49 15
67 17
Solution:
What is the x variable & Y variable?
What is n?
Income Food Expenditure
^𝒚 =𝜶+𝒃 𝒙 55 14
83 24
38 13
𝛼=𝑦 − 𝑏 𝑥 61 16
33 9
𝒏 ( ∑ 𝑥𝑦 ) − ( ∑ 𝑥 )( ∑ 𝑦 ) 49 15
𝑏= 2 67 17
𝒏 ∑ 𝑥 2 − (∑ 𝑥 )
𝛼=𝑦 − 𝑏 𝑥
Solution:
𝒏 ( ∑ 𝑥𝑦 ) − ( ∑ 𝑥 ) ( ∑ 𝑦 )
𝑏= 2
𝒏 ∑ 𝑥 − (∑ 𝑥 )
2
Food
Income Expenditure
࢞ ࢞ൈ
࢟ ࢞૛ ࢟૛
࢟
1 55 14
2 83 24
3 38 13
4 61 16
5 33 9
6 49 15
7 67 17
Solution:
𝒏 ( ∑ 𝑥𝑦 ) − ( ∑ 𝑥 ) ( ∑ 𝑦 )
𝑏= 2
𝒏 ∑ 𝑥 − (∑ 𝑥 )
2
Food
Income Expenditure ࢞ൈ
࢟ ࢞૛ ࢟૛
࢞ ࢟
55 14 770 3,025 196
83 24
38 13
61 16
33 9
49 15
67 17
386 108
Solution:
𝒏 ( ∑ 𝑥𝑦 ) − ( ∑ 𝑥 ) ( ∑ 𝑦 )
𝑏= 2
𝒏 ∑ 𝑥 − (∑ 𝑥 )
2
Food
Income Expenditure
࢞ ࢞ൈ
࢟ ࢞૛ ࢟૛
࢟
55 14 770 3,025 196
83 24 1,992 6,889 576
38 13 494 1,444 169
61 16 976 3,721 256
33 9 297 1,089 81
49 15 735 2,401 225
67 17 1,139 4,489 289
386 108 6,403 23,058 1,792
Solution:
𝒏 ( ∑ 𝑥𝑦 ) − ( ∑ 𝑥 ) ( ∑ 𝑦 )
𝑏= 2
𝒏 ∑ 𝑥 − (∑ 𝑥 )
2
Food
Income Expenditure 7 ( 6,403 ) −(386 ×108)
࢞
࢞ൈ
࢟ ࢞૛ ࢟૛ 𝑏= =¿
࢟ 7 ( 23,058 ) −386
2
55 14 770 3,025 196

83 24 1,992 6,889 576
38 13 494 1,444 169
44,821− 41,688
𝑏= =¿
61 16 976 3,721 256 161,406 − 148,996
33 9 297 1,089 81
49 15 735 2,401 225
3,133
67 17 1,139 4,489 289 𝑏= =0.2525
386 108
12,410
6,403 23,058 1,792
Solution: ALTERNATIVE FORMULA 𝑏=∑
(𝒙 ¿¿ 𝒊 − 𝒙)(𝒚 𝒊 − 𝒚 ¿)
¿¿
∑ (𝒙 𝒊 − 𝒙)𝟐
࢞ ࢟ ࢞࢏ െ࢞
ഥ ࢟࢏ െ࢟
ഥ ෍ ሺ࢞࢏ െ
࢞ഥሻሺ࢟࢏ െ࢟
ഥሻ ሺ࢞࢏ െഥሻ૛ ሺ࢟࢏ െ
࢞ ഥሻ૛
࢟
55 14 -0.143 -1.429 0.204 0.020 2.041 Mean(x) 55.1429

83 24 27.857 8.571 238.776 776.020 73.469 mean(y) 15.4286
38 13 -17.143 -2.429 41.633 293.878 5.898
61 16 5.857 0.571 3.347 34.306 0.327
33 9 -22.143 -6.429 142.347 490.306 41.327
49 15 -6.143 -0.429 2.633 37.735 0.184
67 17 11.857 1.571 18.633 140.592 2.469
447.5714 1,772.9 125.7 coefficent (b) 0.2525
447.6
𝑏= =0.2525
1,772.9
Solution: 𝑏=0.2525
𝜶=𝒚 −𝒃 𝒙
Food
Income Expenditure
࢞ ࢞ൈ
࢟ ࢞૛ ࢟૛
࢟
55 14 770 3,025 196
83 24 1,992 6,889 576 What is the mean of the
38 13 494 1,444 169 X and Y variables?
61 16 976 3,721 256
33 9 297 1,089 81
49 15 735 2,401 225
67 17 1,139 4,489 289
386 108 6,403 23,058 1,792
𝜶=𝒚 −𝒃 𝒙
Food
Income Expenditure
࢞ ࢞ൈ
࢟ ࢞૛ ࢟૛
࢟
55 14 770 3,025 196 𝒚=𝟏𝟓.𝟒𝟐𝟖𝟔
83 24 1,992 6,889 576
38 13 494 1,444 169 𝒙=𝟓𝟓. 𝟏𝟒𝟐𝟗
61 16 976 3,721 256
33 9 297 1,089 81
49 15 735 2,401 225
67 17 1,139 4,489 289
386 108 6,403 23,058 1,792
Food
Income Expenditure ࢞ൈ
࢟ ࢞૛ ࢟૛ 𝒚=𝟏𝟓.𝟒𝟐𝟖𝟔
࢞ ࢟
55 14 770 3,025 196 𝒙=𝟓𝟓. 𝟏𝟒𝟐𝟗
83 24 1,992 6,889 576
38 13 494 1,444 169 15.4286 - 0.2525(55.1429)
61 16 976 3,721 256
33 9 297 1,089 81 𝛼=15.4286 −13.9212
49 15 735 2,401 225
67 17 1,139 4,489 289 𝛼=1.5073
386 108 6,403 23,058 1,792
Solution: ^
𝒚 = 𝜶 +𝒃 𝒙
Food
Income Expenditure
𝛼=1.5073
࢞ ࢞ൈ
࢟ ࢞૛ ࢟૛
࢟
55 14 770 3,025 196 𝑏=0.2525
83 24 1,992 6,889 576
38 13 494 1,444 169
61 16 976 3,721 256
33 9 297 1,089 81 ^
𝑦 =1.5073+0.2525 𝑥
49 15 735 2,401 225
67 17 1,139 4,489 289
386 108 6,403 23,058 1,792
Income
Simple Linear Regression: Prediction
• We can find the predicted value of y for any specific value of x.

Income
Lets assume we selected a household whose monthly income is

$6100. Forecasted food expenditure = ?
^
𝐹𝑜𝑜𝑑 𝐸𝑥𝑝𝑒𝑛𝑑𝑖𝑡𝑢𝑟𝑒=1.5073+ 0.2525 ( 61 )
¿𝟏𝟔.𝟗𝟎𝟕𝟑 𝒉𝒖𝒏𝒅𝒓𝒆𝒅=$𝟏,𝟔𝟗𝟎.𝟕𝟐𝟓𝟐
On average, all households with a monthly income of $6100 spend approximately
$1,690.7252 per month on food.
Simple Linear Regression: Prediction
Income
Calculate the forecasted value for food expenditure when income

is $3200 and $9800
^
𝐹𝑜𝑜𝑑 𝐸𝑥𝑝𝑒𝑛𝑑𝑖𝑡𝑢𝑟𝑒=1.5073+ 0.2525 ( 32 )=𝟗 . 𝟓𝟖𝟔𝟎=$ 𝟗𝟓𝟖 .𝟓𝟗𝟕𝟗
^
𝐹𝑜𝑜𝑑 𝐸𝑥𝑝𝑒𝑛𝑑𝑖𝑡𝑢𝑟𝑒=1.5073+ 0.2525 ( 98 ) =𝟐𝟔 . 𝟐𝟒𝟖𝟖=$ 𝟐 , 𝟔𝟐𝟒 . 𝟖𝟏𝟖𝟕
Coefficient of Determination ()
 Determines the percent of the variation in the y variable

explained by the x-variables
 how well the regression model fits the observed data.
 The square of r – simple linear model
 a high R2 value indicates that the model is a good fit for
the data, vice versa
 The range is 0 to 1
Simple Linear Regression: Assumptions
 The regression model is linear in parameters
 The residuals are independent – primarily affects time series data
 (No autocorrelation)
 Constant variance of residuals

 (Homoscedasticity)
 Normality: The residuals of the model are normally distributed.

The End!

Lecture 2

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Lecture 2

Uploaded by

Copyright:

Available Formats

Please ensure that your

registered name is being

Lecturer: Chrystal Rhone

Calculate variance, standard deviation and

Calculate the mean

Length of Deviations: Squares:

Calculate variance, standard deviation and

 Two variables are said to be correlated if changes

 Correlation can be assessed both graphically and

Data Correlation Direct Negative Linear

 An objective numerical measure of correlation.

𝒓𝒓 = -1 indicates a perfect negative linear relationship

 -1 <𝒓𝒓< 0 indicates a negative linear relationship

𝒓𝒓 = 0 indicates no linear relationship

 0 <𝒓𝒓 < 1 indicates a positive linear relationship

𝒓𝒓 = 1 indicates a perfect positive linear relationship

Pearson Correlation Coefficient:

17 150 -0.8 -14 11.2 0.64 196

 Regression model is a mathematical equation

 Sample: regression line

55 14 770 3,025 196

55 14 -0.143 -1.429 0.204 0.020 2.041 Mean(x) 55.1429

• We can find the predicted value of y for any specific value of x.

Lets assume we selected a household whose monthly income is

Calculate the forecasted value for food expenditure when income

 Determines the percent of the variation in the y variable

 Constant variance of residuals

 Normality: The residuals of the model are normally distributed.

You might also like