Elasticity A measure of the responsiveness of one variable to changes in another variable; the % change in 1 variable

that arises due to a given percentage change in another. IE: the elasticity of your grade w/ respect to
studying, denoted is the % change in your grade that will result from a given %change in the time you
spend studying. If the variable G depends on S according to the functional relationship G =∫( ) the
elasticity of G with respect to S may be found using calculus.
Own Price A measure of the responsiveness of the quantity demanded of a good to a change in the price of that good;
Elasticity the % change in quantity demanded divided by the % change in the price of the good.
Positive (+) Sign determines An increase in S leads to an increase in G.
the relationship
Negative (-) between G & S. An increase in S leads to a decrease in G.
< 1 in Absolute <> 1 determines Numerator is > the denominator in the elasticity formula, we know
Value how responsive G a small % change in S leads to a relatively large % change in G.
> 1 in Absolute is to changes in S. Numerator is < the denominator in the elasticity formula. A given
Value % change in S will lead to a relatively small % change in G.
Own Price Elasticity of Demand Measures the responsiveness of quantity demanded to a change in price.
The OPE of Demand for a good w/ a demand function f (Px, Py, M, H) may be found using
calculus:
Elastic Demand | | Demand is elastic if the absolute value of the own price elasticity is greater than 1.
The quantity consumed of a good is relatively responsive to a change in the price of the
good. A rise in price will reduce consumption considerably.
Inelastic Demand | | Demand is inelastic if the absolute value of the own price elasticity is less than 1.
The quantity consumed of a good is relatively unresponsive to a change in the price of the
good when demand is elastic. Price increases will reduce consumption very little.
Unitary Demand | | Demand is unitary elastic if the absolute value of the OPE is equal to 1.
Advertising often provides consumers with information about the existence or quality of a
product, which in turn induces more consumers to buy the product.
Total Revenue Elastic An increase (decrease) in price will lead to a decrease (increase) in total revenue.
Test – When Inelastic An increase (decrease) in price will lead to an increase (decrease) in total revenue.
demand is: Unitary Elasti Total revenue is maximized at the point where demand is unitary elastic.

Example: suppose If the company cuts prices

the research dept. of by 5 %, will computer -1.7 Solving this equation for yields 8.5. The
a computer company sales increase enough to quantity of computers sold will rise by 8.5% if prices are reduced by 5%.
estimates that the increase overall revenues? Since the % increase in quantity demanded is > than the % decline in prices
OPE of demand for a Set: (| | ), the price cut will actually raise the firm’s sales revenues.
laptop is -1.7. -1.7 = EQ , P &
x x
Expressed differently, since demand is elastic, a price cut results in a > than
-5 = % Px proportional increase in sales and thus increases the firm’s total revenues.
Perfectly Elastic Demand is perfectly elastic if the OPE is infinite in absolute value. The demand curve is horizontal. When
Demand demand is perfectly elastic, if prices rise even slightly you will find that none of the good is purchased.
Perfectly Inelastic Demand is perfectly inelastic if the own price elasticity is zero. The demand curve is vertical. When
Demand demand is perfectly inelastic, consumers do not respond at all to changes in price.
Factors Available The more substitutes available for the good, the more elastic the demand for it. A price  leads
affecting Substitutes consumers to substitute toward another product, thus  considerably the quantity demanded of the
the OPE good. When there are few close substitutes for a good, demand tends to be inelastic because
consumers can’t readily switch to a close substitute when the price . Demand for broadly defined
commodities (food) tends to be more inelastic than the demand for specific commodities (beef).
Time Demand tends to be more inelastic in the short term than in the long term. The more time consumers
have to react to a price change, the more elastic the demand for the good. Conceptually, time allows
the consumer to seek out available substitutes.
Expenditur Goods that comprise a relatively small share of consumers’ budgets tend to be more inelastic than
e Share goods for which consumers spend a sizable portion of their incomes. In the extreme case, where a
consumer spends her or his entire budget on a good, the consumer must decrease consumption when
the price rises. In essence, there is nothing to give up but the good itself.
Marginal The change in total revenue due to a change in output. To maximize profits a firm should produce where marginal
Revenue revenue equals marginal cost. Marginal revenue is < than the price for each unit sold, to induce consumers to
purchase more of a good, a firm must lower its price. IE: $5 1st unit, $4 2nd unit. 1st unit has $5 revenue ($5*1),
selling both revenue is $8 ($4*2). $8-$5=$3, < $4 price. (This is elastic by total revenue test)
P = Price of good, E = the own price elasticity of demand for the good.
Demand is elastic, and the formula implies that MR is positive.
[ ] E= Demand is unitary elastic, and marginal revenue is zero, & corresponds to the output at
which total revenue is maximized.
Demand is inelastic, and marginal revenue is negative.
Cross-Price A measure of the responsiveness of the demand for a good to changes in the price of a related good; the %
Elasticity change in the quantity demanded of one good divided by the % change in the price of a related good.

Denoted EQ , P & is mathematically defined as:

x y

When the demand function is Qdx = f (Px, Py, M, H), the cross-price elasticity of demand between goods X and Y may be

found using calculus:

Example If the cross-price elasticity of demand between Corel WordPerfect and Microsoft Word software is 3, a 10% hike in
the price of Word will increase the demand for WordPerfect by 30%, since 30%/10% = 3. This increase in demand
for WordPerfect occurs because consumers substitute away from Word and toward WordPerfect, due to the price
increase.
Whenever goods X and Y are substitutes, an increase in the price of Y leads to an increase in the demand for X.
Whenever goods X and Y are complements, an increase in the price of Y leads to a decrease in the demand for X.
Example Clothing and food have a cross-price elasticity of -0.18. This means that if the price of food increases by 10%, the
demand for clothing will decrease by 1.8%; food and clothing are complements.
Example Every item you carry is generic (generic beer, etc.). You recently read an article in The Wall Street Journal reporting that the
price of recreation is expected to increase by 15 percent. How will this affect your store’s sales of generic food products?
Answer The cross-price elasticity of demand for food and recreation is 0.15. If we insert the given information into the formula for the
cross-price elasticity, we get  (0.15 * 15% = 0.0225) (0.0225 * 100 = 2.25%); food and recreation are
substitutes. If the price of recreation increases by 15%, you can expect the demand for generic food products to increase by
2.25%.
Revenue Firm’s revenues as R = Rx + Ry ;
of X & Y [ Rx = PxQx denotes revenues from the sale of product X ] & [ Ry = PyQy denotes revenues from the sale of product Y ]
The impact of a small % change in the price of product X (%ΔPx = ΔPx/Px) on the total revenues of the firm is
ΔR = [Rx(1 + EQxyPx) + RyEQy, Px] * %ΔPx
Example Restaurant earns $4,000/wk in revenues from OPEoD of burgers, = -1.5 & CPEoD is = -4.0
hamburger sales (product X) and $2,000/wk from (sodas,burgers) What would happen if burger price is cut by
soda sales (product Y). Thus, Rx = $4,000 and Ry = 1%? ΔR = [$4000(1 + (-1.5)) + $2000(-4.0)] * (-1%) = $100
$2,000.
Income A measure of the responsiveness of the demand for a good to changes in consumer income; the % change in quantity
Elasticity
demanded divided by the % change in income.
When good X is a normal good, an increase in income leads to an increase in the consumption of X.
When good X is an inferior good, an increase in income leads to a decrease in the consumption of X.
Example IEoD for nonfed Consumer incomes are expected to As a manager of a meat-processing plant, how will this forecast affect
beef = -1.94 rise by 10 % over the next 3 years. your purchases of non-fed cattle?
Answer Expect to sell 19.4% less non-fed ground beef over the next 3 years. You
should decrease your purchases of non-fed cattle by 19.4%, unless something
 else changes.
Own Advertising Elasticity for good X defines the percentage change in the consumption of X that results from a given
of Demand percentage change in advertising spent on X.
Cross-Advertising Elasticity between goods X and Y would measure the percentage change in the consumption of X that results
from a given percentage change in advertising directed toward Y.
Example How much should you increase advertising to increase the demand for recreation in the United States by 15%.
 EQ , A = 0.25. Solve:
x x
The % change in advertising shows that it must increase by 60% to
increase the demand for recreation by 15%.
Linear If the demand function is linear and given Own Price
Demand by Elasticity
Functions
Cross-Price
Elasticity

Income
Elasticity
The elasticities for a linear demand curve may be found using
calculus. Specifically, and similarly for the cross-price and income
elasticities.
Own If they raise shoe prices, the % decline in the quantity
Price demanded of its shoes will be > in absolute value than the
Elasticity % rise in price. Consequently, demand is elastic: Total
( ) ( ) revenues will fall if it raises shoe prices.
( )
Cross- Since this is positive, good Y is
( )
Price a substitute for them.
Suppose good X sells at $25/pair, good
Elasticity
Y at $35/pair, Zappos utilizes 50 units Income Zappos’ shoes are inferior goods,
of advertising, and average consumer Elasticity since this is a negative number.
income is $20,000. Calculate the own
price, cross-price, and income elasticity
of demand.
Non- If the demand function is not a linear function & is given by Own Price
Linear ; C is a constant Elasticity
Demand Cross-Price
Log-linear Demand: Demand is log-linear if the logarithm of demand is a
Functions Elasticity
linear function of the logarithms of prices, income, and other variables.
Income
Elasticity
( ), & bi’s are arbitrary #’s
Calculus
( ) ( ) & Similarly for the cross-price & income

What would be the impact of a 10% reduction

 in the amount of advertising directed toward
R denotes the daily amount of rainfall good Y?
and Ay represents the level of advertising
on good Y.

What would be the impact on demand of
a 10% increase in the daily amount of
rainfall?
We know that for log-linear demand 10% increase in rainfall
functions, the coefficient of the logarithm will lead to a 30%
of a variable gives the elasticity of increase in the demand for
demand with respect to that variable. raincoats.
Thus, the elasticity of demand for 10% reduction in advertising directed toward
raincoats with respect to rainfall is  good Y leads to a 20% increase in the demand
for raincoats.
Can you think of a good that might be good Y in this example?
Perhaps good Y is umbrellas, for one would expect the demand for raincoats to increase whenever fewer umbrella
advertisements are made.
Econometrics The statistical analysis of economic phenomena.
Regression Line The line that minimizes the squared deviations btwn. the line (the expected relation) and the actual data pts.
Least Squares Regression The line that minimizes the sum of squared deviations between the line and the actual data points.
Standard Of each estimated coefficient is a measure of how much each estimated coefficient would vary in regressions based on
Error the same underlying true demand relation, but with different observations. The smaller the SE of an estimated
coefficient the smaller the variation in the estimate given data from different outlets (samples of data)
The least squares regression The parameter estimates, â & bˆ, represent the values of a & b
line for the equation that result in the smallest sum of squared errors btwn a line &
Y = a + bX + e the actual data.
is given by
Y = aˆ + bˆ X
Rule of Thumb for a 95 Percent If the parameter estimates of a regression equation are â and bˆ, the 95 percent confidence intervals for the
Confidence Interval true values of a and b can be approximated by
aˆ ± 2σ aˆ & bˆ ± 2σ bˆ where σ aˆ and σ bˆare the standard errors of â, and bˆ, respectively.
t-statistic The ratio of the value of a parameter estimate to the standard error of the parameter estimate.
IE: If the parameter estimates are aˆ & bˆ and the corresponding standard errors are σ aˆ & σ bˆ , the t-
statistic for aˆ is and the t-statistic for bˆ is
Rule of Thumb for Using t- When the absolute value of the t-statistic is greater than 2, the manager can be 95% confident that the true
Statistics value of the underlying parameter in the regression is not zero.
R-square (aka Tells the fraction of the total variation in the dependent variable that is explained by the regression. It is computed
coefficient of as the ratio of the sum of squared errors from the regression (SSRegression) to the total sum of squared errors
determination) (SSTotal):
Value of an R-square from 0 to 1
This means that the estimated demand equation (the regression line) explains 75 percent of the total variation in TV sales
across the sample of 10 outlets.

Closer the R-square is to 1, the “better” the overall fit of the estimated regression equation to the actual data. Unfortunately, there is no simple
cutoff that can be used to determine whether an R-square is close enough to 1 to indicate a “good” fit. With time series data, R-squares are often
in excess of .9; with cross-sectional data, .5 might be a reasonably good fit. A major drawback of the R- square is that it is a subjective measure
of goodness of fit. Sometimes, the R-square is very close to 1 merely because the number of observations is small relative to the # of estimated
parameters. This situation is undesirable because it can provide a very misleading indicator of the goodness of fit of the regression line.
For this reason, many researchers use the adjusted R-square as a measure of goodness of fit.
̅̅̅̅ ( )
( ) , where n is the total # of observations & k is the # of estimated coefficients
( )
In performing a regression, the # of parameters to be estimated can’t exceed the # of observations. n – k represents the residual
degrees of freedom (that is, estimating numerous coefficients from relatively few observations) after conducting the regression.
IE: n=10,k=2 1 - (1 - .75) (9/8) = .72 =̅̅̅̅ ; There is little difference between the R-square and the adjusted R-square, so it
does not appear that the “high” R- square is a result of an excessive # of estimated coefficients relative to the sample size.
F-statistic An alternative measure of goodness of fit. Provides a measure of the total variation explained by the regression
relative to the total unexplained variation. The greater the F-statistic, the better the overall fit of the regression line
through the actual data. IE: F-statistic = .0012, there is only a .12 % chance that the estimated regression model fit the
data purely by accident. As with P-values, the lower the significance value of the F-statistic, the more confident you
can be of the overall fit of the regression equation. Regressions that have F-statistics with significance values of 5% or
less are generally considered significant. Based on the significance value reported in cell 26-F of Table 3–8, our
regression is significant at the .12 percent level. The regression is therefore highly significant.
Sometimes, a plot of the data will reveal To estimate a log-linear demand function, the
nonlinearities in the data. It appears that price econometrician takes the natural logarithm of prices
and quantity are not linearly related: The and quantities before executing the regression routine
demand function is a curve. The log-linear that minimizes the sum of squared errors (e):
demand curve we examined earlier has such a Q’ = β0 + βPP’ + e ; where Q’ = Q ln and P’ = P ln
curved shape.