UNICE A.

RODRIGUEZ BSIA-IV

CHAPTER 5 : DEMAND ESTIMATION

Q5. 1 Describe some of the limitations of market experiments.

 Market experiments contain several severe flaws. They are costly, and they are frequently
carried out on too small a scale to provide high levels of trust in the results. Market trials
are rarely conducted for long enough to determine the long-term impacts of various
pricing, advertising, or packaging techniques. Difficulties associated with uncontrolled
market experiments impede their utilization as well. Changing economic conditions
during the experiment can render the results invalid, particularly if the experiment
comprises multiple independent markets. A local strike, layoffs by a large corporation, or
a heavy winter might all derail a market experiment. Similarly, a change in the
promotion, price, or packaging of a competitive product can mislead the results. There is
also a risk that clients lost during the experiment because of price manipulations will not
be reclaimed when the experiment concludes.

Q5. 2 “When I go to the grocery store, I find cents off coupons totally annoying. Why can’t they
just cut the price and do away with the clutter?” Discuss this statement and explain why coupon
promotions are an effective means of promotions for grocery retailers, and popular with many
consumers.

 Cents off promotion is an important successful form of promotion at grocery stores.

Coupons are a manner of discriminating pricing. Not all customers are drawn to coupons
and want to use them.

Q5. 3 Explain how shifting demand and supply curves makes market demand estimation
difficult.

 The identification problem refers to the difficulty in properly isolating independent

variables (X factors) that influence a given dependent variable (Y factor). To accurately
model the demand function for a given product, the effects of all relevant independent
variables must be incorporated. Furthermore, these separate influences must be expressed
 in a suitable linear or log-linear model. The technique of precisely modeling the
relationship between dependent Y variables and independent factors. X the identification
challenge is extremely problematic in demand estimate since many factors that drive
demand also influence supply. When demand and supply are so intertwined that reliable
empirical estimation becomes impossible, identify each distinct function.

Q5. 4 “Rapid innovation in the development, assembly, and delivery of personal computer has
led to a sharply downward – sloping market demand curve for Dell, Inc.” Discuss this statement.

 This assertion is erroneous and indicates a fundamental misunderstanding of the

distinctions between shifts in demand and movements along a demand curve. A market
demand curve depicts the relationship between the price charged and the quantity
demanded while holding all other variables in the demand function constant. To plot a
demand curve, acquire data on the price/quantity relationship while holding all other
elements in the demand function constant. Rapid innovation in personal computer
development, assembly, and delivery has resulted in a surge in market demand for
personal computers. This is shown in a rightward change in the market demand curve,
rather than a downward shift along the market demand curve, while maintaining product
quality and the level of innovation constant.

Q5. 5 “Demand for higher education is highest among the wealthy. This has led to an upward –
sloping demand curve for college education. The higher the tuition charged, the greater is
demand” Discuss this statement.

 This assertion is erroneous and indicates a fundamental misunderstanding of the

distinctions between shifts in demand and movements along a demand curve. A market
demand curve depicts the relationship between the price charged and the amount required
while holding all other factors in the demand function constant. To plot a demand curve,
data on the price/quantity relationship must be obtained while all other parameters in the
demand function are held constant. It is realistic to anticipate an increase in market
demand for higher education as income grows. This is shown in a rightward shift in the
market demand curve, rather than a downward movement along the market demand curve
while maintaining product quality and income level constant. In terms of college
education, a word of caution is in order.
Q5. 6 How the linear and log – linear models differ in terms of their assumptions about the
nature of demand elasticities?

 The demand elasticity is defined as the percentage change in demand caused by a 1%

change in each demand-determining variable. The effect of a one-unit change in any
independent variable on demand is constant in the linear model method. As a result, the
elasticities of demand change at different places along the linear demand curve. The
effect of a one-unit change in any independent variable tends to fluctuate in the log-linear
model method, although demand elasticities are constant. As a result, linear models
assume changing elasticities, whereas log-linear models assume constant elasticities.

Q5. 7 If a regression model estimate of total profit is $50,000 with a standard error of the
estimated of $25.000, what is the chance of an actual loss?

 Based on the regression coefficients and X variable values, the standard error of the
estimate can be used to generate a range within which the dependent Y variable can be
predicted with varied degrees of statistical confidence. Because the regression equation
predicts that the best estimate of the value for the dependent variable is Y t, the standard
error of the estimate can be used to measure how accurate a forecast Y t is likely to be. If
the us error components are normally distributed about the regression equation, as they
would be in large samples of more than 120 observations. Because the 5% rejection
region is evenly distributed across the distribution's tails, there is a 2.5% chance of
encountering an observation that is two standard deviations below the fitted value. In this
case, there is a 2.5% probability that real profits will be less than $0, or more than two
standard deviations less than the predicted value of $50,000.

Q5. 8 A simple regression TR = a + bQ is not able to explain 19 percent of the variation in total
revenue. What is the coefficient of correlation between TR and Q?

 The correlation coefficient, r, indicates the goodness of fit in a basic regression model
with only one independent variable. The correlation coefficient is in the range of 1 to -1.
If r = 1, the dependent Y variable and the independent X variable have a perfect direct
linear relationship. If r = -1, Y and X have a perfect inverse linear relationship. Actual Y
tall values in both cases fall perfectly on the regression line. All the underlying variance
 in the dependent Y variable is explained by the regression equation in terms of variation
in the independent X variable. If r = 0, there is no correlation between the dependent and
independent variables; they are independent. When r = 0, there is no relationship between
actual and predicted values.

Q5. 9 In regression – based estimate of demand function, the beta coefficient for advertising
equals 3.75 with a standard deviation of 1.25 units. What is the range within which there can be
99 percent confidence that the actual parameter of advertising can be found?

 The standard deviation reveals the precision with which the dependent variable's value
may be predicted by the regression equation. We are aware that at the 0.01 level of
significance or with 99% confidence, a t-statistic greater than 3 enables us to reject the
idea that the dependent and independent variables are unrelated to one another.
Therefore, the t-statistic must fall between -3 and +3 for the hypothesis to be accepted
with 99% confidence.

Q5. 10 Managers often study the profit margin – sales relation over the life cycle of individual
products, rather than the more direct profit – sales relation. In addition to the economic reasons
for doing so, are there statistical advantages as well? (Note: Profit margin equals profit divided
by sales.)

 It's important to note that managers frequently focus on the profit margin-sales
relationship over the course of a single product's life cycle as opposed to the more direct
profit-sales relationship. This is since profit margins are a reliable predictor of the relative
earnings a company may generate from a particular product. While low profit margins
imply the opposite, high profit margins indicate that customers value the product and still
want to purchase it, which is beneficial for a business.
 PROBLEMS

P5.1 Multiplication Demand Functions. Gateway tours, Inc. has estimated the following
multiplication demand functions for packaged holiday tours in the East Lansing, Michigan,
market using quarterly data covering the past 4 years (16 observations)

Qy= 10PY-1.10 Px0.5 Ay3.8 Ax2.5 l1.85

R2= 80%, Standard Error of the Estimate = 20

Here, Qy is the quantity of tours sold, Py is the average tour price, Px is the average for some
other good. Ay is tour advertising, Ax is advertising of some other good, and l is per capita
disposable income. The standard errors of the exponents in the proceedings multiplication
demand functions are

BPy = 0.04, bPx = 0.35, bAx = 0.5 b a x = 0.9 and bl= 0.45

A. Is tour demand elastic with respect to price?

 Since |-1:10| > 1, the exponent on Py indicates that demand appears elastic. Now, we
must determine if it significantly exceeds 1. First, since we want to determine whether
price elasticity is significant and greater than 1, rather than just different from 1, this test
should be one-tailed. Next, the null hypothesis now involves one rather than zero is.
1.1 - 1 = 2.5
0.04

B. Are tours a normal good?

 A normal good requires "I > 0. Our estimate for "I is 1.85, and its standard error is 0.45.
All we want to know now is if "I > 0, so again this is a one-tailed test, though our null
hypothesis now involves zero rather than one (so this differs from part a). Our test
statistic is:
 1.85 – 0 = 4.11
0,45

C. Is X a complement good or substitute good?

 Since the anticipated coefficient is positive, it is likely that the products will be
connected. Alternative products. This is a one-tailed test once more since we want to
determine whether the coincident is positive, not if it differs significantly from zero.
Creating our t-statistic, we had to:

0,5 – 0 = 1.43
0.35
D. Given your answer to part C, can you explain why the demand effects of A y and Ax, are
both positive?
 This finding demonstrates that, despite X being a replacement good, X's promotion
raises. Demands for tour volume. It's conceivable that promotion by a rival raises
knowledge of advertising for Disney World could boost sales of products unrelated
to Disney, for example, theme parks merely because people see the advertisements
and consider vacationing there.

P5. 2 Revenue Versus Profit Maximization. On weekends during summer months, Eric
Cartman rents jet skis at beach on hourly basis. Last week, Cartman rented jet skis for 20 hours
per day at a rate of $50 per hour. This weeks, rentals 15 hours per day when Cartman raised the
price to $55 per hour.
Using these two price – outputs combinations, the relevant linear demand marginal
revenue curves can be estimated as

P = $70 - $1Q and MR = $70 - $2Q

A. Calculate the revenue – maximizing price – output combination. How much these
maximum revenues? If marginal cost is $30 per hour, calculate the profits at this activity
level, assuming TC = MC X Q.
 B. Calculate the profit – maximizing price – outputs combination along with revenues and
profits at this activity level.

P5. 3 Multiple Regression. Colorful Tile, Inc., rapidly growing chain of ceramic title outlets
that caters to the do – it – yourself home modeling market. In 2007, 33 stores ware operated in a
small to medium – size metropolitan markets. An in – house study sales by these outlets revealed
the following (standard errors parentheses)

Q = 4 – 5P + 2A + 0.21 + 0.25HF
(3) (1.8) (0.7) (0.1) (0.1)
R2 = 93% Standard Error of the Estimate = 6

Here, Q is tile sales (in thousands of cases), P is the tile price (per case). A is advertising
expenditures (in thousands of dollars), I is the disposable income per household (in thousands of
dollars, and HF is household formation (in hundreds)

A. Fully evaluate and interpret these empirical results on an overall basis using R2,
R1, F statistic and SEE information.

B. Is quantity demanded sensitive to “own” price?

C. Austin, Texas, was a typical covered by this analysis. During 2007 in the Austin
market, price was $5, advertising was, income was an average $55,000 per
household, and the number of household formation was 4,000. Calculate and
interpret the relevant advertising point elasticity.

D. Assume that the preceding model and data are relevant for the coming period.
Estimate the probability that the Austin store will make a profit during 2008 if
total costs are projected to be $300,000.
P5.4 Linear Demand Curve Estimation. Xerox Corporation develops, manufactures,
and services document equipment and software solutions worldwide. Assume the
company offered $75 off the $1,475 regular price on the Phaser 6360, a durable high-
speed color copier, and Internet sales, jumped from 700 units to 800 units per week (see
http://www.office.xerox.com).

A. Estimate the color copier demand curve, assuming that it is linear.

B. If marginal costs per unit are $650, calculate the profit-maximizing price-output
combination. [Remember: The marginal revenue curve has the same intercept as the
demand curve, but has twice its negative slope (falls twice as fast).]

P5.5 Market Demand. Gregory House, a Philadelphia-based management consultant,

has been asked to calculate and analyze market demand for a new video game that is to
be marketed tore tail (R) and wholesale (W) customers over the Internet.
The client estimates fixed costs of $750,000 per year for the product, and that
licensing fees and other marginal costs will be $20 per unit. The client has also provided
the following annual demand information:

P R= $62.50-$0.00005QR
Pw = $50-$0.002Qw

A. Express quantity as a function of price for both retail and wholesale customers. Add
these quantities together to calculate the market demand curve. Graph the retail,
wholesale, and market demand curves for prices ranging from $65 to $35 per unit.

B. Fill in the following table:

Market Demand is Retail Plus Wholesale Demand

Price ($) Retail Wholesale Market Total Total Total

 Demand Demand Demand Revenue Cost Profit
65
60
55
50
45
40
35

C. Calculate the profit-maximizing price-output combination and total profit?

P5.6 Revenue Versus Profit Maximization. The Best Buy Company, Inc., is a leading specialty
retailer of consumer electronics, personal computers, entertainment software, and appliances.
The company operates retail stores and commercial Web sites, the best known of which is
bestbuy.com. Recently, this site offered a home theater unit with a 5-disc DVD player,
MP3playback, and digital AM/FM. At a price of $1,100, weekly sales totalled 2,500 units. After
a $100online rebate was offered, weekly sales jumped to 5,000 units.
Using these two price-output combinations, the relevant linear demand and marginal
revenue curves can be estimated as

P=$1,200-$0.04Q and MR=$1,200-$0.08Q

A. Calculate the revenue-maximizing price-output combination and revenue level. If Best Buy's
marginal cost per unit is $800, calculate profits at this activity level assuming TC=MCxQ.

B. Calculate the profit-maximizing price-output combination. Also calculate revenues and profits
at the profit-maximizing activity level.

P5.7 Identification Problem. Business is booming for Consulting Services, Inc. (CSI),a local
supplier of computer set-up consulting services. The company can profitably employ technicians
as quickly as they can be trained. The average hourly rate billed by CSI for trained technician
services and the number of billable hours (output) per quarter over the past six quarters are as
follows:

Q–1 Q–2 Q–3 Q–4 Q–5 Q–6

Hourly rate 20 25 30 35 40 45
($)
Billable 2,000 3,000 4,000 5,000 6,000 7,000
Hours

Quarterly demand and supply curves for CSI service are

QD = 4,000 – 200P + 2,000T (Demand)

QS = - 2,000 + 200P (Supply)

Where Q is the output, P is price, T is trend factor, and T = 1 during Q – 1 and increased by 1
unit per quarter.

A. Express each demand and supply curve in terms of price as a function of output.

B. Plot the quarterly demand curves for the last six quarterly periods. (Hint: Let T=1 to find
the Y intercept for Q-1,T=2 for Q-2,and so on.)

C. Plot the CSI supply curve on the same graph. D. What is this problem's relation to the
identification problem?

P5.8 Regression Analysis. Identify each of the following statements as true or false and explain
why;

A. A parameter is a population characteristic that is estimated by a coefficient derived from

a sample of data.
 B. A one-tail t - test is used to indicate whether the independent variables as a group explain
a significant share of demand variation.

C. Given values for independent variables, the estimated demand relation can be used to
derive a predicted value for demand.

D. D. A two-tail t test is an appropriate means for testing direction (positive or negative) of

the influences of independent variables.

E. E. The coefficient of determination shows the share of total variation in demand that
cannot be explained by the regression model.

P5.9 Linear Demand Curve Estimation. Kenny McCormick manages a 100-unitapartment

building and knows from experience that all units will be occupied if rent is $900 per month.
McCormick also knows that, on average, one additional unit will go unoccupied for each$10
increase in the monthly rental rate.

A. Estimate the apartment rental demand curve assuming that it is linear and that price is
expressed as a function of output.
B. Calculate the revenue – maximizing apartment rental rate. How much are these maximum
revenues?
C. If all of costs are fixed, what is the profit – maximizing number of vacant apartments?
Explain your answer.

P5. 10 Demand Estimation Concepts. Identify each of the following statements as true or false
and explain why.

A. The effect of a $1 change in price is constant, but the elasticity of demand will vary along
a linear demand curve.
B. In practice, price and quantity tend to be individuality rather than simultaneously
determined.
C. A demand curve is revealed if prices fall while supply conditions are held constant.
D. The effect of a $1 change in price will vary, but the elasticity of demand is constant along
a log – linear demand curve.
E. Consumer interviews are a useful means for incorporating subjective information into
demand estimation.