Title: PPA 220A: Applied Economic Analysis I Meeting 1, Fall 2003 Introduction to Course Munger Chapter 1:
1PPA 220A Applied Economic Analysis I Fall
2003Professor Rob WassmerMeeting
12Probability and Public Policy
2Announcement and HW
- No class next week
- I will assign groups for final on Dec. 2
- Final exam given out Dec. 9
- Describe how article relates to a debate on
government intervention - Primary conflicts implied
- Markets vs. experts
- Politics vs. markets
- Politics vs. experts
3Figure 8.1 Three conflicts
Markets
- Equity Policies
- Income Redistribution
- Resource Distribution
- Control Externalities
- Efficiency Policies
- Market structure
- Control Externalities
- Public Goods
- Information Asymmetry
Politics
Experts
- Institutional Reform Policies
- Information
- Values (Efficiency v. Equity
- Institutional Design
4Munger Chapter 9 Expected Values, Probability,
and Risk
- Dense chapter with many statistical formulas
- Only responsible for what covered here
- Discounting Count at less than face value
- Here based upon uncertainty
- Game Offer
- Flip a fair coin (50 heads, 50 tails)
- Receive 5 for head, 1 for tail
- How much are you willing to pay to play?
- Expected value of event
- Payoff from event x probability of event
5Munger Chapter 9 Expected Values, Probability,
and Risk
- Heads 5 0.5 2.50
- Tails 1 0.5 0.50
- Game 2.50 0.50 3.00
- Ever pay to play more than expected value?
- Do you ever go to Reno?
- What would they need to charge to run game?
- Types of risk tolerances
- Risk accepting Willing to pay more than exp.
value - Risk neutral Willing to pay exp. Value
- Risk averting Willing to pay less than exp.
Value - Also depends on number times played
- Only play once, win 1 or 5
6Munger Chapter 9 Expected Values, Probability,
and Risk
- Policy analysts and probability
- Russian roulette?
- Good policy decision not based upon outcome
- Appropriate decision process
- Two examples Civil rights in South and Kublai
Khan - Strengthen levies on Sacramento and American
Rivers - Probability concepts
- Expectations about an uncertain future
- PEvent X (number of ways X can occur) / total
events - P4 of diamonds 1 / 52 0.0192 or 1.92
- PAce 4 / 52 0.0769 or 7.69
- PRolling 1 or 6 on die 2 / 6 0.333 or 33.3
7Munger Chapter 9 Expected Values, Probability,
and Risk
- Basic rules of probability
- (1) Possible event has a positive probability
- (2) Probability of an event less than or equal to
one - (3) Sum of probabilities of all possible events
is one - Counting rules
- Total number of events of interest
- Calculate with formula
- Depends if combination (order of events not
important) - Depends if permutation (order of events
important)
8Munger Chapter 9 Expected Values, Probability,
and Risk
- Combination examples
- 6 balls in urn, number 1 to 6, draw 2
- No replacement of ball after drawn, order not
important - Outcome of interest 6-1
- Not of interest 1-2, 1-3, 1-4, 1-5, 2-3, 2-4,
2-5, 2-6, 3-4, 3-5, 3-6, 4-5, 4-6, 5-6 - 15 possible outcomes
- Combinations from N take k (order not important)
- CNk N! / (k! (N-k)!)
- N 6, k 2 (654321) / ( (21) (4321) )
720 / 48 15 - Probability drawing 6-1 1 / 15 0.067 or 6.7
9Munger Chapter 9 Expected Values, Probability,
and Risk
- What is SuperLotto Plus?
- Taken from http//www.calottery.com/games
- SuperLottoPlus is your chance to win millions of
dollars! The jackpot ranges from 7 million to
50 million or more. The jackpot rolls over and
grows whenever there is no winner. All you have
to do is pick five numbers from 1 to 47 and one
MEGA number from 1 to 27 and match them to the
numbers drawn by the Lottery every Wednesday and
Saturday.
10Munger Chapter 9 Expected Values, Probability,
and Risk
- First event (N 47, k 5)
- (47!) / ( 5! (42!) ) 2.5959 ( 120 1.4151)
1,532,544 - Where 2.5959 equals 259 with 57 zeros after it
- Chance of event 1 / 1,532,544
- Second event (N 27, k 1)
- (27!) / ( 1! (26!) ) 27
- Chance of event 1 / 27
- Discuss probability of both events occurring
later
11Munger Chapter 9 Expected Values, Probability,
and Risk
- Permutation example
- Same as urn example above but order of draw
counts - 6-1 not same as 1-6
- Outcome of interest 6-1
- Not of interest 1-2, 1-3, 1-4, 1-5, 2-3, 2-4,
2-5, 2-6, 3-4, 3-5, 3-6, 4-5, 4-6, 5-6, 2-1, 3-1,
4-1, 5-1, 3-2, 4-2, 5-2, 6-2, 4-3, 5-3, 6-3, 5-4,
6-4, 6-5 - 30 possible outcomes
- Combinations from N take k (order important)
- CNk N! / ((N-k)!)
- N 6, k 2 (654321) / (4321) 720 /
24 30 - Probability drawing 6-1 1 / 30 0.033 or 3.3
12Munger Chapter 9 Expected Values, Probability,
and Risk
- Language of probability
- Independent
- Event A and B are if occurrence of one unrelated
to other - Probability of rain today (1 / 10) independent of
you being elected to CA Assembly (1 / 300) - Union
- Given A and B are independent the probability of
A occurs, or B, or both A and B found by adding
independent probabilities ( 30 / 300 1 / 300 )
31 / 300 - Intersection
- Given A and B are independent, the probability of
both occurring - CA Super Lotto example
- (1 / 1,532, 544) ( 1 / 27) 1 / 41,378,688
13Munger Chapter 9 Expected Values, Probability,
and Risk
- Conditional
- Event A and B are not independent
- Probability of A occurring given that B has
already - Formulas in Munger
- Your level of risk aversion
- Two choices (1) sure payoff of 1 and a 20
chance of winning 5 - Can only play once
- Risk neutral person indifferent
- Risk accepting person takes 5
- Risk averse person takes 1
- What are you? Does it depend upon circumstances?
- What would you like public decision maker to be?
14Munger Chapter 9 Expected Values, Probability,
and Risk
- Policy example
- Sacramento City Manager Stockpile sandbags?
- Chance of flooding in any given year 10
- Is each years flood best considered an
independent event? - 100 year flood protection
- Cost of stockpiling in each year 2.5 million
- What outcome variable is needed to make good
decision? - Does evaluation of decision quality depend on
flood occuring?
15Munger Chapter 9 Expected Values, Probability,
and Risk
- Decision analysis
- Map or tree to illustrate consequences of choices
- Method
- Identify mutually exclusive outcomes
- Estimate the value of outcomes if they come to
pass - Assign probabilities to outcomes
- Multiply estimated value of each outcome by
probabilities to obtain expected outcome - Figure 9.6
- Expected remediation cost for three waste burial
styles - Lesson Cheapest up-front alternative is most
expensive in terms of long-term expected cost
16Fig. 9.6 Simplified Decision Analysis for
Disposal Technology
Human decision
Revealed by nature in future with probability
conditional on prior human decision
Yes 0.6
Remediation Required? Cost if yes40m
Augured Holes (Construction cost 5m)
No 0.4
Yes 0.4
Shallow Land Burial (Construction cost 15m)
Remediation Required? Cost if yes27.5m
No 0.6
Above Ground Vaults ( Construction cost 25m)
Yes 0.1
Remediation Required? Cost if yes10m
No 0.9
17Munger Chapter 9 Expected Values, Probability,
and Risk
- Add construction plus expected remediation costs
- Are constituents risk neutral?
- How far off in the future are remediation costs
- Time value of (covered next time)
18Birthday Problem
- Found at http//www.mste.uiuc.edu/reese/birthday/i
ntro.html - How likely is that two people in class have same
B-day? - Drawing from an urn of 365 days, N times, with
replacement - Formula
19HomeworkDue the Start of Meeting Thirteen
- (1) Do assigned reading and compose a typed and
well-developed question from the reading assigned
for thirteenth week that relates to something
that you do not understand from it. - (2) Provide a typed and double-spaced explanation
for the answer given in Munger for question 1 on
pp. 318-319. - (3) Write a one to two page, double-spaced
response to the discussion and advanced questions
for Chapter 9 at Mungers web site
http//www.wwnorton.com/college/polisci/analyzingp
olicy .