You are on page 1of 2

2.#Probability#&#Statistics.

#
Probability:"the"chance"an"uncertain"event"will"occur"(always#between#0&1).#"
Impossible/Event:/an"event"has"no"chance"of"occurring"(probability=0)."
Certain/Event:/an"event"is"sure"to"occur"(probability=1)."
Mutually/exclusive/events://an"event"cannot"occur"at"the"same"time."
5"Events/A/and/B/are/mutually/exclusive/No/joint/probability=/0/
Collectively/exhaustive/events:/One"of"the"events"must"occur.//
Joint/probability:/you"consider"two"events"in"the"same"time"
Marginal/Probability:"a"subset"of"a"collection"of"random"variables""
5"is"the"probability"distribution"of"the"variables/contained"in"the"subset."
5"subsets"represent"both"mutually/exclusive/and"collectively/exhaustive./
Conditional/probability:"the"probability"of"one/event,"given"that"another/event/has"occurred."
EConditional/Probability=Joint/Probability/Marginal/Probability/
Marginal/&/Joint/&/Conditional/Probabilities/In/A/Contingency/Table:/
/ P(A | B) =
P(A and B)
P(B | A) =
P(A and B)
/ P(B) P(A)
/ The"conditional"probability"of"A"given"that"B"has"occurred"
/ The"conditional"probability"of"B"given"that"A"has"occurred"
/ "
P(A"and"B)"="joint"probability"of"A"and"B"
/
P(A)"="marginal"or"simple"probability"of"A"
/ P(B)"="marginal"or"simple"probability"of"B"
/
/
/
/
3.#Decision#Making#Under#Uncertainty."Possible/&/Elements/Decision/Criteria:/#
Payoff/table:"lists"the"payoff"for"each"decision5outcome"pair."Positive"values"correspond"to"rewards"(or"gains),"&"negative"values"correspond"to"costs"(or"losses)."
Maximin/criterion/(pessimist):"the/worst/payoff"in"each"row"of"the"payoff"table"&"chooses"the"decision"corresponding"to/the/best/of/these./
E"Conservative/(pessimistic)/or/risk/averse."Minimizing"the"possible"loss"for"a"worst5case"(maximum"loss)"scenario/(The/lowest/risk)./
"Maximax/criterion/(optimist):"the/best/payoff"in"each"row"of"the"payoff"table"&"chooses"the"decision"corresponding"to/the/best/of/these."Risk/taker/(optimist)"(The/highest/risk)."
The/expected/monetary/value/(realist),/or/EMV:"a"weighted"average"of"the"possible"payoffs"for"this"decision,"weighted"by"the"probabilities"of"the"outcomes."Calculated/through/a/foldingEback/process./
(Probability*Outcome)/
Decision/Tree:/Nodes"(circles,"squares,"and"triangles)"&"branches"(lines)./
Nodes:"points"in"time."Decision/node/(a/square,/):"a"time"when"the"decision"maker"makes"a"decision."No/calculation,/only/choose/the/best/option."
Probability/node/(a/circle,/):/a"time"when"the"result"of"an"uncertain"outcome"becomes"known."Do/not/decide,/only/calculate."
End/node/(triangle,/or/endpoint):"the"problem"is"completed,"all"decisions"have"been"made,"all"uncertainty"has"been"resolved,"&"all"payoffs"&"costs"have"been"incurred."
The/Risk/Profile/for"a"decision"is"a"spike/chart:"the"probability"distribution"of"monetary"outcomes"for"this"decision."By"comparing"risk"profiles"for"different"decisions,"can"gain"more"insight"into"relative"strengths"&"
weaknesses."(Choose"the"highest"EMV)" Ex.6.1/SciTools/
"
"
"
" "
"
"
"
"
" P(A|B)/=/(P(A/and/B))/(P(B))/
Ex.6.4/Acme/
"
" P(B|A)/=/(P(B/and/A))/(P(A))/
"
Bayes/Theorem:"used"to"revise"previously"calculated"probabilities"based"on"new"information."
"
"P(B | A) = P(A | B i )P(B i )
" i P(A | B 1 )P(B 1 ) + P(A | B 2 )P(B 2 ) + + P(A | B k )P(B k )
"
"
"
"
"
" P(B|A)/=/(P(B/and/A))/(P(A))/
" =P(A/and/B)/P(A)/
" =P(A|B)P(B)/P(A)/
" P(A)=P(A|B)P(B)+P(A|B)P(B)/
"
The/Value/of/information:"
Sample/information/(SI):/the"information"from"the"experiment"itself."
Perfect/information/(PI):/information"from"a"perfect"test,"a"test"that"will"indicate"with"certainty"which"ultimate"outcome"will"occur."
The/expected/value/of/sample/information,/or/EVSI:"the"most"you"would"be"willing"to"pay"for"the"sample"information."
Formula:/EVSI//=/EMV/with/(free)/sample/information//EMV/without/information."
EVSI/=/EMV/from/test/market/exclude/fixed/cost/E/EMV/from/no/test/
The/expected/value/of/perfect/information,/or/EVPI:"the"most"you"would"be"willing"to"pay"for"perfect"information."
EVPI/=/EMV/with/free/PI//EMV/with/no/info//
5The"amount"you"should"be"willing"to"spend"for"information"is"the"expected/increase/in/EMV/you/can/obtain"from"having"the"information.""
5If"the"actual"price"of"the"information"is"less"than"or"equal"to"this"amount,"you"should"purchase"it;"otherwise,"the"information"is"not"worth"its"price."
"
4.#Simulation#Modeling."
Simulation:/A/simulation/model/is/a/computer/model/that/imitates/a/realElife/situation./ Ex.4.3/Market/Return/
Uniform/Distribution:/Continuous,/Symmetric,/Bounded/in/both/direction,/=RAND()/=MIN+(MAX_MIN)*RAND()/
Normal/Distribution:/Continuous,/Symmetric,"Unbounded,bellEshaped/curve."Value"cannot"be"negative(5)"
5"Use"when"they"give"Mean"&"Standard"Divation"=NORMINV(RAND(),Mean,Stdev)"
Discrete/Distribution:/Symmetric,/Skewed/
Use/VLOOKUP"to"find"market"returns"=/VLOOKUP(Random#,/Lookup/Table,/Column/2)/
Cumulative/Frequency:/Count"number"of"random"value(s):"less"than"0,"0.1,"0.2,","0.9."=FREQUENCY/
The"binomial/distribution"is"a"discrete/distribution/that"applies"to"a"very"specific"situation:"
5When"a"number"of"independent"&"identical"trials"occur,"&"each"trial"results"in"a"success/a"failure./
=CRITBINOM(NTrials,PSuccess,RAND())/ Average:"=Average(Market"Return)"
RAND/function:""generate"a"random"number"between"0"&"1"=RAND(),/(1E1,000)/
# EX.15.1/Walton/Bookstore/ 95%/Normsinv:/=normsinv(0.975)/
# Demand:/MIN+(MAX5MIN)*RAND()/ 90%/Normsinv:/=normsinv(0.95)"
# Demand:"=ROUND(NORMINV(RAND(),MEAN,STDEV),0)" "
# Demand:"=VLOOKUP(RAND(),$CUM.PROB.:$DEMAND,2)"
Ex.15.1/Walton/Bookstore/
# Revenue:"="$Unit"Price*MIN($Order"Quantity,"Demand1)"
# Cost:"=$Unit"Cost*$Order"Quantity"
# Refund:"$Unit"Refund*MAX($Order"Quantity5Demand1,0)"
# Profit:"=Revenue5Cost+Refund"
# Average:"=Average(Profit)"
# Min:"=Min(Profit)/"Max:"=Max(Profit)"
# Stdev:"=STDEV(Profit)/SQRT(#1000)"
# 95%"Confident;"Lower/Upper:"Average5+1.96*Stdev"
" IF(B12>B16,(B12*B16)*B6,0)"
90%"Confident;"Lower/Upper:"Average5+1.64*Stdev"
" Cum.Freq.:"=frequency($Profit,Bin1)"
" Freq./Distribution:"251,"Under5Upper"
" New/Scenario:"What5If"Analysis,"Data"Table,"Colum"
" input:Order"Quantity"
"
"
"
"
"
"
"
"
"
""
Ex.6.1/SciTools/
"
"
#
#
#
#
#
#
#
#
#
#
#
#
"
"
"
"
"

Bayes/Rule:/ Bayes/Rule:/
P(MS|TS)=P(TS|MS)"P(MS)" P(E|PE)=P(PE|E)"P(E)"
""""""""""""""""""""(P(TS|MS)"P(MS))+(P(TS|MF)P(MF))" """"""""""""""""""""(P(PE|E)"P(E))+(P(PE|NOE)P(NOE))"
P(MF|TS)=P(TS|MF)"P(MF)" P(NOE|PE)=P(PE|NOE)"P(NOE)"
""""""""""""""""""""(P(TS|MF)"P(MF))+(P(TS|MS)P(MS))" """"""""""""""""""""(P(PE|NOE)"P(NOE))+(P(PE|E)P(E))"
P(MS|TF)=P(TF|MS)"P(MS)" P(E|P"NOE)=P(P"NOE|E)"P(E)"
""""""""""""""""""""(P(TF|MS)"P(MS))+(P(TF|MF)"P(MF))" """"""""""""""""""""(P(P"NOE|E)"P(E))+(P(P"NOE|NOE)"P(NOE))" Bayes/Rule:/
P(MF|TF)=P(TF|MF)"P(MF)" P(NOE|P"NOE)=P(P"NOE|NOE)"P(NOE)" P(NG|TG)=P(TG|NG)P(NG)=P(TG|NG)P(NG)"
""""""""""""""""""""(P(TF|MF)"P(MF))+(P(TF|MS)"P(MS))" """"""""""""""""""""(P(P"NOE|NOE)"P(NOE))+(P(P"NOE|E)"P(E))" " P(TG)" P(TG|NG)P(NG)+P(TG|NF)P(NF)+P(TG|NA)P(NA)"
P(TS)=(P(TS|MS)"P(MS))+(P(TS|MF)"P(MF)" P(PE)=(P(PE|E)"P(E))+(P(PE|NOE)"P(NOE)" P(NF|TG)=P(TG|NF)P(NF)=P(TG|NF)P(NF)"
" P(TG)" P(TG|NF)P(NF)+P(TG|NA)P(NA)+P(TG|NG)P(NG)"
P(TF)=(P(TF|MS)"P(MS))+(P(TF|MF)"P(MF)" P(P"NOE)=(P(P"NOE|E)"P(E))+(P(P"NOE|NOE)"P(NOE)" P(NA|TG)=P(TG|NA)P(NA)=P(TG|NA)P(NA)"
" " " P(TG)" P(TG|NA)P(NA)+P(TG|NG)P(NG)+P(TG|NF)P(NF)"
P(NG|TF)=P(TF|NG)P(NG)=P(TF|NG)P(NG)"
" P(TF)" P(TF|NG)P(NG)+P(TF|NF)P(NF)+P(TF|NA)P(NA)"
P(NF|TF)=P(TF|NF)P(NF)=P(TF|NF)P(NF)"
" P(TF)" P(TF|NF)P(NF)+P(TF|NA)P(NA)+P(TF|NG)P(NG)"
P(NA|TF)=P(TF|NA)P(NA)=P(TF|NA)P(NA)"
" P(TF)" P(TF|NA)P(NA)+P(TF|NG)P(NG)+P(TF|NF)P(NF)"
P(NG|TA)=P(TA|NG)P(NG)=P(TA|NG)P(NG)"
" P(TA)" P(TA|NG)P(NG)+P(TA|NF)P(NF)+P(TA|NA)P(NA)"
P(NF|TA)=P(TA|NF)P(NF)=P(TA|NF)P(NF)"
" P(TA)" P(TA|NF)P(NF)+P(TA|NA)P(NA)+P(TA|NG)P(NG)"
P(NA|TA)=P(TA|NA)P(NA)=P(TA|NA)P(NA)"
" P(TA)" P(TA|NA)P(NA)+P(TA|NG)P(NG)+P(TA|NF)P(NF)"
"

You might also like