Marketing Research Approaches to Demand Estimation

Consumer Surveys
data from survey questions

Observational Research
data from observed behavior

Consumer Clinics
data from laboratory experiments

Market Experiments
data from real market tests

Regression Analysis
Year 1 2 3 4 5 6 7 8 9 10 X 10 9 11 12 11 12 13 13 14 15 Y 44 40 42 46 48 52 54 58 56 60

Scatter Diagram

Regression Analysis
Regression Line: Line of Best Fit
Regression Line: Minimizes the sum of the squared vertical deviations (et) of each point from the regression line. Ordinary Least Squares (OLS) Method

Ordinary Least Squares (OLS)

Model:
Yt a bX t et

Yt a bX t et Yt Yt

Ordinary Least Squares (OLS)

Objective: Determine the slope and intercept that minimize the sum of the squared errors.
et2 (Yt Yt ) 2 (Yt a bX t ) 2
t 1 t 1 t 1 n n n

Ordinary Least Squares (OLS)

Estimation Procedure

(X
t 1 n t 1

X )(Yt Y )
t

(X

a Y bX

X)

Ordinary Least Squares (OLS)

Estimation Example
Time
1 2 3 4 5 6 7 8 9 10
n

Xt
10 9 11 12 11 12 13 13 14 15 120

Yt
44 40 42 46 48 52 54 58 56 60 500

Xt X
-2 -3 -1 0 -1 0 1 1 2 3
n

Yt Y
-6 -10 -8 -4 -2 2 4 8 6 10

( X t X )(Yt Y )
12 30 8 0 2 0 4 8 12 30 106

( X t X )2
4 9 1 0 1 0 1 1 4 9 30

n 10
X
t 1 n

X t 120
t 1

Yt 500
t 1

(X
t 1 n

X ) 2 30 X )(Yt Y ) 106

106 3.533 b 30
a 50 (3.533)(12) 7.60

X t 120 12 n 10

Yt 500 50 10 t 1 n

(X
t 1

Ordinary Least Squares (OLS)

Estimation Example
n 10
X
t 1 n n

X t 120 12 n 10

X
t 1

120
2

Y
t 1

500

Yt 500 50 10 t 1 n

(X
t 1 n

X ) 30 X )(Yt Y ) 106

106 3.533 b 30

(X
t 1

a 50 (3.533)(12) 7.60

Tests of Significance
Standard Error of the Slope Estimate
(Yt Y ) 2 et2

sb

(n k ) ( X t X )

(n k ) ( X t X ) 2

Tests of Significance
Example Calculation
Time
1 2 3 4 5 6 7 8 9 10

Xt
10 9 11 12 11 12 13 13 14 15

Yt
44 40 42 46 48 52 54 58 56 60

Yt
42.90 39.37 46.43 49.96 46.43 49.96 53.49 53.49 57.02 60.55

et Yt Yt
1.10 0.63 -4.43 -3.96 1.57 2.04 0.51 4.51 -1.02 -0.55

et2 (Yt Yt )2
1.2100 0.3969 19.6249 15.6816 2.4649 4.1616 0.2601 20.3401 1.0404 0.3025 65.4830

( X t X )2
4 9 1 0 1 0 1 1 4 9 30

e (Yt Yt )2 65.4830
t 1 2 t t 1

(X
t 1

X ) 30
2

sb

(Y Y ) ( n k ) ( X X )
2 t t

65.4830 0.52 (10 2)(30)

Tests of Significance
Example Calculation
et2 (Yt Yt ) 2 65.4830
t 1 t 1 n n

( X t X ) 2 30
t 1

65.4830 sb 0.52 2 ( n k ) ( X t X ) (10 2)(30)

)2 (Yt Y

Tests of Significance
Calculation of the t Statistic
b 3.53 t 6.79 sb 0.52

Degrees of Freedom = (n-k) = (10-2) = 8

Critical Value at 5% level =2.306

Tests of Significance
Decomposition of Sum of Squares
Total Variation = Explained Variation + Unexplained Variation

Y )2 (Y Y )2 (Yt Y ) (Y t t
2

Tests of Significance
Coefficient of Determination
R2 Explained Variation TotalVariation (Yt Y )2 (Y Y )2

373.84 R 0.85 440.00

2

Tests of Significance
Coefficient of Correlation
r R2 withthe signof b

1 r 1
r 0.85 0.92

Multiple Regression Analysis

Model:

Y a b1 X 1 b2 X 2

bk ' X k '

Multiple Regression Analysis

Adjusted Coefficient of Determination
(n 1) (n k )

R 2 1 (1 R 2 )

Multiple Regression Analysis

Analysis of Variance and F Statistic
Explained Variation /(k 1) F Unexplained Variation /(n k )
R 2 /( k 1) F (1 R 2 ) /( n k )

Problems in Regression Analysis

Multicollinearity: Two or more explanatory variables are highly correlated. Heteroskedasticity: Variance of error term is not independent of the Y variable. Autocorrelation: Consecutive error terms are correlated.

Durbin-Watson Statistic
Test for Autocorrelation
(et et 1 ) 2
t 2 n

et2
t 1

If d = 2, autocorrelation is absent.

Steps in Demand Estimation

Model Specification: Identify Variables Collect Data Specify Functional Form Estimate Function Test the Results

Functional Form Specifications

Linear Function:
QX a0 a1 PX a2 I a3 N a4 PY e

Power Function:
b QX a ( PX1 )( PYb2 )

Estimation Format:
ln QX ln a b1 ln PX b2 ln P Y

Regression Output

Multiple Regression Data

Regression Output