The Acme Company is trying to decide whether to market a new product.

As in many new-product situations, there is considerable uncertainty

about whether the new product will eventually be popular. Acme believes that it might be wise to introduce the product in a regional test
market before introducing it nationally. Therefore, the company's first decision is whether to conduct the test market.
Acme estimates that the net cost of the test market is $100,000. We assume this is mostly fixed costs, so that the same cost is incurred
regardless of the test market results. If Acme decides to conduct the test market, it must then wait for test market results. Based on the
results of the test market, it can then decide whether to market the product nationally, in which case it will incur a fixed cost of $7 million. On
the other hand, if the original decision is not to run a test market, then the final decision - whether to market the product nationally - can be
made without further delay. Acme's unit margin, the difference between its selling price and its unit variable cost, is $18. We assume this is
relevant only for the national market.
Acme classifies the results in either the test market or the national market as great, fair, or awful. Each of these results in the national market
is accompanied by a forecast of total units sold. These sales volumes (in 1000s of units) are 600 (great), 300 (fair), and 90 (awful). In the absence
of any test market information, Acme estimates that probabilities of the three national market outcomes are 0.45, 0.35, and 0.20, respectively.
In addition, Acme has the following historical data from products that were introduced into both test markets and national markets:
1. Of the products that eventually did great in the national market, 64% did great in the test market, 26% did fair in test market and 10% did
awful in the test market.
2. Of the products that eventually did fair in the national market, 18% did great in the test market, 57% did fair in test market and 25% did
awful in the test market.
3. Of the products that eventually did awful in the national market, 9% did great in the test market, 48% did fair in test market and 43% did
awful in the test market.
The company wants to use the decision tree approach to find the best strategy. It also wants to find the expected value of information provided
by the test market.
Solution:
Company's first decision - Conduct the test market and then launch nationally
Fixed Cost of Test market $100 ('000) dollars
Fixed Cost of National market $7,000 ('000) dollars
Company's second decision - IF No test market - Market the product nationally
Unit Margin $18 dollars
Chances Great Fair
National market units sold (1000s of units)600 300
USING CONDITIONAL PROBABILITIES
TEST MARKET PROBABILITIES
should know how to calculate
Prob. Great Test Market 0.369
Prob. Fair Test Market 0.4125
Prob. Awful Test Market 0.2185
P(TG) = P(TG/NG)* P(NG) + P(TG/NF) * P(NF) + P(TG/NA)* P(NA) = (0.64)(0.45) + (0.18)(0.35) + (0.09)(0.20) = 0.3690
Test market probabilities given the National Mkt prob. Natl Great Natl Fair
Great Test Market 0.64 0.18
Fair Test Market 0.26 0.57
Awful Test Market 0.1 0.25
NATL MKT PROBABILITIES WITHOUT TEST MKT Natl Great Natl Fair
0.45 0.35
USING BAYE'S RULE
National market probabilities given the Test Mkt prob. Natl Great Natl Fair
Great Test Market 0.7805 0.1707
Fair Test Market 0.2836 0.4836
Awful Test Market 0.2059 0.4005
FALSE
0
FALSE Nat'l Market Launch Decision?
0 74
TRUE
-7000
Test Market?
Acme Marketing New Product
No
No
Yes
36.9%
0
TRUE Chance
-100 796.76
41.25%
0
21.85%
0
Expected Value of Sample Information
EVPI = EMV with perfect information (no negative payoffs) - EMV (original launch) with
FALSE
0
Yes
Great Test Market
Fair Test Market
Poor Test Market
No
TRUE Nat'l Market Launch Decision?
0 1710
TRUE
Test Market?
1710
FALSE 0.0%
0 0
EVPI=
EVPI
No
Yes
Yes
The Acme Company is trying to decide whether to market a new product. As in many new-product situations, there is considerable uncertainty
about whether the new product will eventually be popular. Acme believes that it might be wise to introduce the product in a regional test
market before introducing it nationally. Therefore, the company's first decision is whether to conduct the test market.
Acme estimates that the net cost of the test market is $100,000. We assume this is mostly fixed costs, so that the same cost is incurred
regardless of the test market results. If Acme decides to conduct the test market, it must then wait for test market results. Based on the
results of the test market, it can then decide whether to market the product nationally, in which case it will incur a fixed cost of $7 million. On
the other hand, if the original decision is not to run a test market, then the final decision - whether to market the product nationally - can be
made without further delay. Acme's unit margin, the difference between its selling price and its unit variable cost, is $18. We assume this is
Acme classifies the results in either the test market or the national market as great, fair, or awful. Each of these results in the national market
is accompanied by a forecast of total units sold. These sales volumes (in 1000s of units) are 600 (great), 300 (fair), and 90 (awful). In the absence
of any test market information, Acme estimates that probabilities of the three national market outcomes are 0.45, 0.35, and 0.20, respectively.
In addition, Acme has the following historical data from products that were introduced into both test markets and national markets:
1. Of the products that eventually did great in the national market, 64% did great in the test market, 26% did fair in test market and 10% did
2. Of the products that eventually did fair in the national market, 18% did great in the test market, 57% did fair in test market and 25% did
3. Of the products that eventually did awful in the national market, 9% did great in the test market, 48% did fair in test market and 43% did
The company wants to use the decision tree approach to find the best strategy. It also wants to find the expected value of information provided
Chances are great, fair or awful test market
Chances are great, fair or awful national market
Range names:
NatlMktCost: B29
Awful
90
If TG,TF and TA : Test Mkt Outcomes
T = Any of the Test Mkt Outcomes
If TG=Great Test Market, then
P(TG) = P(TG/NG)* P(NG) + P(TG/NF) * P(NF) + P(TG/NA)* P(NA) = (0.64)(0.45) + (0.18)(0.35) + (0.09)(0.20) = 0.3690
Natl Awful
0.09
0.48
0.43
Natl Awful
0.2
Natl Awful
0.0488
0.2327
0.3936
0.0%
0
45.0% 0.0%
10800 3800
Market Outcomes
74
35.0% 0.0%
5400 -1600
20.0% 0.0%
1620 -5380
Range names:
NatlMktCost: B29
TestMktCost: B28
UnitMargin: B33
Great Nat'l Market
Fair Nat'l Market
Poor Nat'l Market
FALSE 0.0%
0 -100
Nat'l Market Launch
2330.243902
78.0488% 28.8%
10800 3700
TRUE Market Outcomes
-7000 2330.243902
17.0732% 6.3%
5400 -1700
4.878% 1.8%
1620 -5480
TRUE 41.25%
0 -100
Nat'l Market Launch
-100
28.3636% 0.0%
10800 3700
FALSE Market Outcomes
-7000 -1048.072727
48.3636% 0.0%
5400 -1700
23.2727% 0.0%
1620 -5480
TRUE 21.85%
0 -100
Nat'l Market Launch
-100
20.595% 0.0%
10800 3700
FALSE Market Outcomes
-7000 -2075.652174
40.0458% 0.0%
5400 -1700
39.3593% 0.0%
1620 -5480
0.0%
0
No
Yes
Great Nat'l Market
Fair Nat'l Market
Poor Nat'l Market
No
Yes
Great Nat'l Market
Fair Nat'l Market
Poor Nat'l Market
No
Yes
Great Nat'l Market
Fair Nat'l Market
Poor Nat'l Market
45.0% 45.0%
3800 3800
Market Outcomes
1710
35.0% 35.0%
0 0
20.0% 20.0%
0 0
Great Nat'l Market
Fair Nat'l Market
Poor Nat'l Market
The Acme Company is trying to decide whether to market a new product. As in many new-product situations, there is considerable uncertainty
about whether the new product will eventually be popular. Acme believes that it might be wise to introduce the product in a regional test
results of the test market, it can then decide whether to market the product nationally, in which case it will incur a fixed cost of $7 million. On
the other hand, if the original decision is not to run a test market, then the final decision - whether to market the product nationally - can be
made without further delay. Acme's unit margin, the difference between its selling price and its unit variable cost, is $18. We assume this is
Acme classifies the results in either the test market or the national market as great, fair, or awful. Each of these results in the national market
is accompanied by a forecast of total units sold. These sales volumes (in 1000s of units) are 600 (great), 300 (fair), and 90 (awful). In the absence
of any test market information, Acme estimates that probabilities of the three national market outcomes are 0.45, 0.35, and 0.20, respectively.
1. Of the products that eventually did great in the national market, 64% did great in the test market, 26% did fair in test market and 10% did
3. Of the products that eventually did awful in the national market, 9% did great in the test market, 48% did fair in test market and 43% did
The company wants to use the decision tree approach to find the best strategy. It also wants to find the expected value of information provided
P(TG) = P(TG/NG)* P(NG) + P(TG/NF) * P(NF) + P(TG/NA)* P(NA) = (0.64)(0.45) + (0.18)(0.35) + (0.09)(0.20) = 0.3690