Back To CourseBusiness 116: Quantitative Analysis
11 chapters | 50 lessons
As a member, you'll also get unlimited access to over 70,000 lessons in math, English, science, history, and more. Plus, get practice tests, quizzes, and personalized coaching to help you succeed.Free 5-day trial
Natalie is a teacher and holds an MA in English Education and is in progress on her PhD in psychology.
Laurie has just been hired as the CEO of a tech company and she's now in charge of all of the company's operations. That's a big job! One of the idea's she has to boost the company's profit is to outsource the company's customer service division. That is, she wants to have a different company do all the customer service for their products and pay them a fee rather than paying the salaries, benefits, and office space of having a customer service division. That seems like a good idea, but what if something goes wrong? What if the new plant ends up costing Laurie's company more money? Laurie needs more information. But what is that information worth to her?
The expected value of perfect information (EVPI) measures how much better a decision-maker could do if she or he knows for certain which state of nature would occur. It gives a person like Laurie an idea of how much money it would be worth to continue gathering information until she reaches certainty. To help Laurie figure out the EVPI for her situation though, first we have to understand and calculate the expected value.
Okay, Laurie wants to figure out whether to keep things as they are, or outsource the customer service part of her company to a subcontractor. But there are a lot of things that could happen. For example, the state where the subcontractor is located is considering charging a tax on all companies that do business in that state. If Laurie subcontracts the customer service and then the new tax goes into effect, her business could end up owing a lot of money.
What Laurie is facing a state of nature, which in business is something over which a company has no control but that can impact a company's bottom line. Laurie can't control whether the tax will go into effect or not, but she can consider it when making her decision. As Laurie sees it, she has two decision alternatives or, options to choose from: keep the customer service division as it is or outsource it.
Of course, there are many other options that Laurie could consider, such as changing the structure of the customer service division or outsourcing to another company. But right now she's only considering those two alternatives: leave it unchanged or outsource it to Company A. So Laurie needs to figure out which is the best option- but how? One way to do that is to calculate the expected value of each decision alternative, which is the weighted sum of a decision alternative across different states of nature. If that sounds complicated, don't worry! We'll help Laurie calculate the expected value of each option and that should make it more clear.
The first thing Laurie does is construct a table so that she can see all her options and all possible states of nature. Along the left side, she's labeled each row to represent a decision alternative, keep the division or outsource to Company A. Along the top, she's labeled each column according to different states of nature: the tax does, or does not, go through. Now, in each cell, Laurie fills in what will happen with her company for that decision alternative in that state of nature. In Laurie's case, she wants to know the cost of each decision alternative in each state of nature.
For example, if she keeps the customer service department as it is, her company will spend $750,000 on it in the next year. This is the same number whether or not the tax goes through because the tax won't affect the company's costs if the department stays in the company. But what if she chooses to outsource? In that case, she has two different numbers. If the tax does not pass, she calculates that her company's costs will only be $450,000. That's good! But if the tax does pass, then she has to factor in the cost of the tax, which means it will end up costing her $950,000. Not so good!
As we've said, Laurie needs to calculate the expected value for each decision alternative. To do that, she has to figure out the probability that each state of nature will happen. For example, let's say there is a 30% chance that the tax will pass and a 70% chance that it won't. Laurie has to multiply $750,000 and $450,000 by .7 and put those values into the table. Then, she's multiply $750,000 and $950,000 by .3 and put those values in. Now, she adds each row and gets the expected value of that row, or decision alternative. If she keeps the customer service department in house, she can expect to spend $750,000 in the next year. But if she outsources it, her expected value is $600,000. Sounds like the better choice!
But wait! What Laurie has now is the expected value of each possible choice; that's pretty good information but she still doesn't know exactly what will happen. It's a risk either way. What if Laurie could know for sure whether that tax will go through? That would make her decision much easier. What is that information worth to her? This is where EVPI comes in. Remember EVPI gives a person like Laurie an idea of how much money it would be worth to continue gathering information until she reaches certainty. Let's calculate Laurie's EVPI.
First, let's go back to her expected value table. She now needs to figure out the maximum payoff or best financial situation for each state of nature. Remember that in Laurie's case, the numbers are negative because they are the cost to her company, so the maximum payoff is the lowest negative number. She'll want to find the weighted maximum payoff for each state of nature and add them up. When she does this, she get's -$540,000. Now, Laurie needs to subtract the maximum expected value from -$540,000. In this case, the maximum expected value is -$600,000. When she subtracts that from -$540,000, she gets $60,000. $60,000 is her EVPI.
That means, given the option, Laurie should spend $60,000 to get information that would lead her to know with certainty whether the tax would go through or not. Of course, there is probably not a way for Laurie to get 100% certain information but she could spend less than $60,000 to get more information that gets her nearer to absolute certainty. The point is that EVPI shows her how much she can spend to increase her knowledge about a decision.
When making business decisions, a person should take into consideration certain states of nature, or something over which a company has no control but that can impact a company's bottom line as they weigh decision alternatives, or options to choose from. To do that, many businesses calculate the expected value of each decision alternative, which is the weighted sum of a decision alternative across different states of nature. The expected value of perfect information (EVPI) measures how much better a decision-maker could do if he or she knew for certain which state of nature would occur. EVPI is calculated by taking the maximum payoff or best financial situation for each state of nature and adding them up. That sum is then subtracted from the best possible expected value.
To unlock this lesson you must be a Study.com Member.
Create your account
Did you know… We have over 160 college courses that prepare you to earn credit by exam that is accepted by over 2,000 colleges and universities. You can test out of the first two years of college and save thousands off your degree. Anyone can earn credit-by-exam regardless of age or education level.
To learn more, visit our Earning Credit Page
Not sure what college you want to attend yet? Study.com has thousands of articles about every imaginable degree, area of study and career path that can help you find the school that's right for you.
Back To CourseBusiness 116: Quantitative Analysis
11 chapters | 50 lessons