Está en la página 1de 16

Simulation Trends:

Probability Management
May 2012

Dennis Sweitzer, Ph.D.!


www.Dennis-Sweitzer.com !

Presented to the

Delaware Chapter of the ASA


American College of Radiology
AstraZeneca Biostatistics Department
Probability Management

Built more elaborate models


Learned to
Display results in column
Copy values to save
Do math with the results

Why not?
Save columns of
simulated
iteraAons
Recombine as
needed
Combining simulaAons results
4 simulaAons:
{ 2 studies} x {2 scenarios}
Why not?
Save columns
Study#1,
of simulated EsAmates of total:
Early Start
iteraAons Resources
Recombine as Study#1, Costs
needed Late Start Pr{success}

Pick opAmal

Study#2,
Early Start M Requires
independence!
Study#2,
Late Start

Eg., porFolio opAmizaAon


Combining simulaAon iteraAons
4 simulaAons:
{ 2 studies} x {2 scenarios}
Why not?
Save columns
Study#1,
of simulated
Early Start
iteraAons
Recombine as Study#1,
needed Late Start EsAmates of

Study#2,
Simulation Early Start
of common
factors Study#2,
Late Start

Preserves relaAonships
Probability Management
Other people already doing it
Further research:


Primary source for rest of presenta1on:
Savage, Scholtes and Zweidler, 2006, "Probability
Management," OR/MS Today, Vol.33, No.1 (February 2006)
h]p://www.orms-today.org/orms-2-06/frprobability.html
(Part 2)
h]p://www.orms-today.org/orms-4-06/frprobability.html
Basic idea

Simulations
Simulations
Simulations
of common
of ofcommon
common
factors
factors
factors
Dependent
Simulations
Dependent
Simulations
Dependent
Simulations Reporting &
Analysis
Dependent Programs
Simulations
EsAmates of
Basic idea
Simulations
Simulations MulAple simulaAons:
Simulations Dierent plaForms
Simulations
Simulations
Dierent s ources

Simulations Dierent uses
ExcelSimulaAon,
Reporting &
Analysis
Programs
Reporting &
Database of SimulaAon Results Analysis
Results at the iteraAon level Programs

Coherent
Basic DeniAons
Simulations

SIP: StochasAc
InformaAon Package
Basic unit of informaAon
Eg, the price of oil, but for
10,000 alternaAve universes

SLURP: StochasAc Library Unit with


RelaAonships Preserved
SIPs are coherent with each other
Eg, in each SIP, iteraAon #4567 is from the same alternaAve universe
Analogous to RepresentaAve Samples (in demographic studies)
COHERENCE
Simulations

Example: variables Requires central control:


X&Y Common standards
Coherent Cer1ca1on authority
Chief Probability Ocer
But not correlated

Basic DeniAons
Simulations

Benets of coherent Requires central control:


modeling Common standards
StaAsAcal dependencies are Cer1ca1on authority
modeled consistently across Chief Probability Ocer
the organizaAon
Models can be rolled up
between levels of the
organizaAon
Auditability: Easier to audit
individual simple models

DIST Standard
Simulations
XML
How to 10,000 numbers
1 XML string
Store SIPs? Metadata + Base 64
Massive encoding of values
amounts of data
Contents:
How to Name
Reduce precision
Share SIPs? and pack it! Mean, Min, Max,
Count of values
Data type (Binary,
1 or 2 Byte)
3 bytes (8 bits each)
into
4 characters (6 bits each)
DIST Standard
A SIP in DIST ts into 1 cell on a spreadsheet

<dist name="User Interface, weeks"


avg="3.3751" min="2.03" max="7.75" count="100"
type="Double" origin="DistShaper3 at smpro.ca"
ver="1.1" >G00Z9SIDCIEmC0nYFtMi6R0XKZ
+KvSzBI85ui5tMZgoDlbGt dF1d/
CqEMwUlmCfVMMg6oUByUXQyIATsaSw1QhgrhOwaaAI9D
6oks9M+IDk0XQyIDlI2mhJZBkQXRnm7IR45ST3D///
IDlgrHD I38VraK2kLownZf41jWw1tROxTsS/
jGRAUJCbwHfwougAAEXR r3A83FQnpnhXukBxM
+kswBykeb0gOQ5RByk83PxtV7mCrH1QQ
jy6LPGstpgFYRrYKvqZ9Ez8AAAAA</dist>!
Each cell contains an array
OperaAons apply funcAons
to each element in array

Source: Marc Thibault, Sam Savage. Probability


Management for Projects: Managing Uncertainty in
plan esAmates and targets.. October 2011
Forecast for the Far Future: Cloudy
Simulations
SLURPS:
Simulations
Simulations
of common
of ofcommon
ComputaAon
factors
common
factors Dependent
factors
Resource Intense Simulations
CoordinaAon Dependent
Tracking interdependencies
Simulations
Storage
Recompute only as needed
Sharing Dependent
Reporting &
Analysis
Accessibility Programs
Simulations
Cloud Based Dependent
Simulations EsAmates of
SupporAng Sotware
MS Excel Spreadsheet Add-ins
Risk Solver from Frontline Systems (www.Solver.com)
XLSim 3 (www.VectorEconomics.com)
<dist name="User Interface, weeks"
avg="3.3751" min="2.03" max="7.75" count="100"
type="Double" origin="DistShaper3 at smpro.ca"
small (single sheet) interacAve simulaAon with DISTs
ver="1.1" >G00Z9SIDCIEmC0nYFtMi6R0XKZ
+KvSzBI85ui5tMZgoDlbGt dF1d/
enables the users of Oracle Crystal Ball and @Risk from
CqEMwUlmCfVMMg6oUByUXQyIATsaSw1QhgrhOwaaAI9D
6oks9M+IDk0XQyIDlI2mhJZBkQXRnm7IR45ST3D///
Palisade Corp. to read and right DISTs.
IDlgrHD I38VraK2kLownZf41jWw1tROxTsS/
jGRAUJCbwHfwougAAEXR r3A83FQnpnhXukBxM
AnalyAca from Lumina Decision Systems, Inc
+kswBykeb0gOQ5RByk83PxtV7mCrH1QQ
jy6LPGstpgFYRrYKvqZ9Ez8AAAAA</dist>!
(www.Lumina.com)
SAS?
R/S+ --Already is vector oriented
RExcel runs R from Excel. ??
R/S+
x1<-rnorm(10000) # an array of 10,000 standard random normal
y1<-rpois(10000, 5) # an array of 10,000 random poissons
(x1+y1)[1:10] # element by element operaAons
Already handles vectors very fast
Needs funcAons to encode & decode DIST

Accessing R from with spreadsheet?
RExcel Access R from within Excel (Addin)
ROOo Access R from within OpenOce spreadsheet
Open Source (like LINIX)
(Perhaps) use spreadsheet for upper level simulaAon
Use R at lower level each cell contains 1000s of simulated values

Probability Management

Savage, Scholtes and Zweidler, 2006, "Probability


Management," OR/MS Today, Vol.33, No.1 (February 2006)
h]p://www.orms-today.org/orms-2-06/frprobability.html
(Part 2)
h]p://www.orms-today.org/orms-4-06/frprobability.html

También podría gustarte