Ülo Ennuste Economics

papers and articles in wordpress

NB: 9.ix 2017

NB: Kas riskida e-valimistega või mitte – kitsendusel et Eesistumisel Valitsus ei lagune

Teaduslikult on selle e-valimiste riskiprobleemi* ratsionaalne (mitte-poliitiline või populistlik – kuid loomulikult poliitiliste kitsendustega) lahendamine üsana lihtne eeskätt nn moodsate katastroofi teooriate alusel mis hõlmavad mudelites nt ka Musta Luige (ID kaardi nõrkuse (MLID)) olulist tõenäosust** ja seega ka oota- ja vaata- lahendeid. Ülelihtsustatud kujul nt Bayes’i printsiibi*** alusel arvestades aposteriori tõenäose hindamisel meie peale 2014. ID kaardi nõrkuse parajasti hiljutist ilmsiks tulekut – kuid nt** alusel ilmselt taolisel lihtsustatud käsitlusel MLID probleem ekslikult elimineeritakse .

*) Ajalehed ja MLID

ttps://www.ft.com/content/874359dc-925b-11e7-a9e6-11d2f0ebb7f0 ja

http://www.faz.net/aktuell/feuilleton/debatten/estland-sicherheitsluecke-bei-elektronischen-personalausweisen-15186516.html

http://www.faz.net/aktuell/wirtschaft/parteien-zeigen-im-internet-wahlkampf-wenig-mut-15168510.html

http://pluss.postimees.ee/4238025/vastasele-kasulik-risk-avalikustati-ajaga-voidu-joostes?_ga=2.140402865.308016313.1498803753-219461728.1498803748

**) Uurimused:

Akerlof, Georg; Robert Shiller (2015) Phishing for Phools: The Economics of Manipulation and Deception, ISBN: 9781400873265 Princeton University Press, Princeton, NY and Kindle Edition: 280.

“Akerlof and Shiller extend the standard ‘market failure’ theory–which says that there is a potential role for government intervention when markets fail–by showing that markets fail not only because of the familiar reasons of externalities and unfair income distribution, but also because of the pervasive phenomenon of ‘phishing for phools’ (profit-seeking through manipulation and deception). They point the way to a new paradigm freed from the constraints of market failure theory, able to illuminate ‘control by capital’ (partly through phishing) and to prescribe for ‘control of capital’ (partly by techniques for limiting phishing suggested here).” – Robert H. Wade, London School of Economics.

Chanel, Oliver; Graciela Chichilnisky (2013) „Valuing life: Experimental evidence using sensitivity to rare events“ – Ecological Economics 85: 198–205: doi:10.1016/j.ecolecon.2012.03.004

Chichilnisky, Graciela  (2010) „The foundations of statistics with black swans“ –

https://doi.org/10.1016/j.mathsocsci.2009.09.007Get rights and content

Abstract

We extend the foundation of statistics to integrate rare events that are potentially catastrophic, called black swans.These include natural hazards, regime change in complex systems, market crashes, catastrophic climate change and major episodes of species extinction. Classic statistics and physics treat such events as ‘outliers’ and often disregard them. We propose a new axiomatization of subjective probability requiring equal treatment for rare and frequent events, and characterize the likelihoods or subjective probabilities that the axioms imply. These coincide with countably additive measures and yield normal distributions when the sample has no black swans. When the sample includes black swans, the new likelihoods are represented by a combination of countable and finitely additive measures with both parts present. The axioms were introduced in Chichilnisky (2000, 2002); they extend the axiomatic foundations of Savage (1954)Villegas (1964) and Arrow (1971) and they are valid for bounded and unbounded samples (Chichilnisky, 1996b). The finitely additive measures assign more weight to rare events than do standard distributions and in that sense explain the persistent observation of power laws and ‘heavy tails’ that eludes classic theory.

Chichilnisky, Graciela (2009) „The topology of fear“ – Journal of Mathematical Economics 45:  807–816.

A b s t r a c t

For many years experimental observations have raised questions about the rationality of economic agents—for example, the Allais Paradox or the Equity Premium Puzzle. The probleem is a narrow notion of rationality that disregards fear. This article extends the notion of rationality with new axioms of choice under uncertainty and the decision criteria they imply (Chichilnisky, G., 1996a. An axiomatic approach to sustainable development. Social Choice andWelfare 13, 257–321; Chichilnisky, G., 2000. An axiomatic approach to choice under uncertainty with Catastrophic risks. Resource and Energy Economics; Chichilnisky, G., 2002. Catastrophical Risk. Encyclopedia of Environmetrics, vol. 1. John Wiley & Sons, Ltd., Chicester). In the absence of catastrophes, the old and the newapproach coincide, and both lead to standard expected utility. A sharp difference emerges when facing rare events with important consequences, or catastrophes. Theorem 1 establishes that a classic axiom of choice under uncertainty – Arrow’s Monotone Continuity axiom, or its relatives introduced by DeGroot, Villegas, Hernstein and Milnor – postulate rational behavior that is ‘insensitive’ to rare events as defined in (Chichilnisky, G., 1996a. An axiomatic approach to sustainable development. Social Choice andWelfare 13, 257–321; Chichilnisky, G., 2000. An axiomatic approach to choice under uncertainty with Catastrophic risks. Resource and Energy Economics; Chichilnisky, G., 2002. Catastrophical Risk. Encyclopedia of Environmetrics, vol. 1. John Wiley & Sons, Ltd., Chicester). Theorem 2 replaces this axiom with another that allows extreme responses to extreme events, and characterizes the implied decision criteria as a combination of expected utility with extremal responses. Theorems 1 and 2 offer a new understanding of rationality consistent with previously unexplained observations about decisions involving rare and catastrophic events, decisions involving fear, the Equity Premium Puzzle, ‘jump diffusion’ processes and ‘heavy tails’, and it agrees with (Debreu, G., 1953. Valuation equilibrium and Pareto optimum. Proceedings of the National Academy of Sciences, 40, 588–592) formulation of market behavior and his proof of Adam Smith’s Invisible Hand theorem.

© 2009 Elsevier B.V. All rights reserved.

le Carrè, John (2017 Sept 7) A Legasy of Spies. Kindle

Interweaving past with present so that each may tell its own intense story, John le Carré has spun a single plot as ingenious and thrilling as the two predecessors on which it looks back: The Spy Who Came in from the Cold and Tinker Tailor Soldier Spy. In a story resonating with tension, humor and moral ambivalence, le Carré and his narrator Peter Guillam present the reader with a legacy of unforgettable characters old and new..

Ennuste,Ü. (2014) “Towards Special Methodological Problems of Macro-Optimal Sociocybernetic International Economic Sanctioning Coordination Modelling: Introductory Remarks oPreliminary Postulates and Conjectures.” – Baltic Journal of European Studies Tallinn University of Technology (ISSN 2228-0588), Vol. 4, No. 2 (17), 150-158:

http://www.degruyter.com/view/j/bjes.2014.4.issue-2/bjes-2014-0021/bjes-2014-0021.xml?format=INT

Ennuste, Ü. and Rajasalu, T. (2002) „Critical Probability of the EU Eastern Enlargement Project’s Institutional Failure: Aspects of Calibrated Economic Impacts of the Failure.“  In: Aksel Kirch and Juhan Sillaste (eds.) Monitoring Preparations of Transition Countries for EU-Accession. 4th International Conference 4-6 October, 2002 Pärnu, Estonia, The Institute for European Studies, Tallinn, 212-227: http://www.ies.ee/iesp/ennuste.pdf

Perea, Andrés (2017) „Forward induction reasoning and correct beliefs“- Journal of Economic Theory 169: 489–516:  www.elsevier.com/locate/jet

Abstract

All equilibrium concepts implicitly make a correct beliefs assumption, stating that a player believes that his opponents are correct about his first-order beliefs. In this paper we show that in many dynamic games of interest, this correct beliefs assumption may be incompatible with a very basic form of forward induction reasoning: the first two layers of extensive-form rationalizability (Pearce, 1984;Battigalli, 1997, epistemically characterized by Battigalli and Siniscalchi, 2002). Hence, forward induction reasoning naturally leads us away from equilibrium reasoning. In the second part we classify the games for which equilibrium reasoning is consistent with this type of forward induction reasoning, and find that this class is very small.

©2017 Elsevier Inc. All rights reserved.

 

***) ENE Köide 1 (1985)**** lk488: e.k ilmselt esimest korda üldteaduslikus teatmeteoses on Bayes’i valem avaldatud (lihtsustatud kujul ja märkusega et tegu on „inglise matemaatikuga“ 1702-61 – tegelikult sovjeti okupatsiooni ajal tuli varjata et tegemist oli ikkagi eeskätt anglikaani kirikutegelasega)

****) Mitmesugust:

PM elu24 6.IX 2017 vt fotot kuidas meie theadusmin ENE/EE 10 Köidete rahvuslikku Varumit  prügiurni „salvestas“: vt LISA.

PS 8.IX: (a) Kõigepealt täpsustada tuleks et kui suure tõenäosusega võib tegemist olla vaenuliku strateegilise kommunikatsiooni manipulatsiooniga (vt nt Akerlof&Shiller, 2015) ja reeturite (le Carrè, 2017) igat masti ja kaliibrit negatiivse aktiivsusega – sest ära ei tohi unustada et oleme parajasti hübriidsõja sanktsioonide sektoris mitmes dimensioonis eesrindel (Ennuste, 2014) – eriti ka ideoloogia ning küberrindel – ja seega eriti sattuda  manipuleeritud tasakaalu (Perea, 2017)  (b) seega on mängus arvukalt kiskjalikke agente/tüüpe kes püüavad meie institutsionaalseid küberneetilisi nõrkuseid ära kasutada külvates meie rahvuslikku teadmusruumi hägusust ning katastroofi hirmu mida traditsioonilised heaoluteooriad ei pruugi adekvaatselt käsitleda (vt Chichlinski, 2009) ja  eriti kompetentse  le Carrè (2017) jne tekstidest) ja seega ka meie tähelpanu kõrvale juhtida meie rahvuslike sotsiaal-küberneetiliste mitmete rahvusliku jätkusuutlikkuse kestlikkuse tõenäosuse seisukohalt eksistentsiaalsete mehhanismide teaduslagedast disunktsionaalsusest ning ka sellest et e-valimistel on veel muid riske peale ID nõrkuste ning meil on seega tegelikult MLID puhul tõenäosuse täiendava suurenemise risk sattuda võltstasakaalu lõksu (Perea, 2017)  (c) nt kuigi meil II kv 2017 majandusaktiivsuse juurdekasvu määr oli pealiskaudselt OK: GDP 5,2% (Eurostat 8.IX 17)  – ja mahuliselt p.c EL/28 keskmisele üsna lähedal – siis samas sügavamalt lähenemiselt näeme et rahvuslike ressursside kõlvatu väljalekkimine meie kodumaisest majandusest oli meil kahetsusväärselt mahukas – eriti haritud põliselanikest tööjõu väljarände (Eurostati järgi põliselanike positiivne efektiivsus on keskmiselt kõrgem kui immigrantidel) ning finantsressursside osas: eriti välismaale netolaenude siirdamisel (vt ESA Kogumajanduse II Kv statistika Tabelit) ja seega ka GDP potentsiaali kahandavalt – järelikult ka eestluse jätkusuutlikkuse kestlikkuse tõenäosust õõnestavalt.

PSPS 9.IX: Momendil on meil MLID kohta teada et mitte eriti usaldusväärsest nukatagusest institutsioonist teatati/õngitseti et eksisteerib teoreetiline katastroofiline e-valimiste risk – ning selle realiseerimine agressorite poolt oleks nendele ääretult kallis (vist Eesti näitel 60 miljardi euro ringis*) – mingeid usaldusväärseid andmeid vist veel ei ole ka MLID riski võimaliku realiseerumise tõenäosuse kohta. Samas on teada* et meil tehakse jõulisi pingutusi selle riski võimalike füüsiliste põhjuste kõrvaldamiseks. Samuti ei ole veel kuulda mingeid usaldusväärseid hinnanguid et kui suurte kahjudega ning milliste tõenäosustega (nii maineliste/moraalsete kui ainelistega/finantslistega  – ja – nii meie kohalike kui ka liidulistega) – tuleks arvestada e-valimiste tühistamisel.

Kokkuvõttes moodsa sotsiaal-küberneetilise stohhastilise optimeerimise rakursist võib suure tõenäosusega väita – et eestluse jätkusuutlikkuse kestlikkuse tõenäosuse seisukohalt ratsionaalne strateegia oleks adaptiivne – ehk ootame ja vaatame veel kuidas tõenäosed edaspidi kujunevad sest pragu need ei näi üldsegi mitte kriitilistena (Ennuste&Rajasalu, 2002) – ehk ootame ja vaatame lõpliku otsustusega niikaua kuni jõuame sillani (autor on täiesti teadlik et see ei ole ratsionaalne ei poliitoponentide ega agressoritele jne natsionaalselt negatiivsete tüüpidele ning euroliidu lõhestajatele jne).

 

LISA: Lihtsustatud Bayes’lik spämmi filtreering

Algoritmi***** alusel tähendagu: A – väidetav e-kiri vihjega – et ID turvaaugu olemasolu on Musta Luige kaliibris oht – on spämm aprioorse tõenäosusega 0,9 (***** alusel); X – e- kirjas on teatavad sõnad –           X( kuuekümne miljardi euro ringis, autoritel pole veel õigust turvaaugu olemasolu väite/hüpoteesi tõestust esitada, jne; nüüd Bayes’i lihtsustatud valemi järgi kus Pr on tõenäosuse operaator – on spämmi aposterioorse tõenäosuse väärtus:
    Pr(A/X)=Pr(X/A)Pr(A):Pr(X) –  ja – ekspertlikult kalibreeritult Pr(A/X)=0,9×0,8:0,75=0,96.
 
*****) https://betterexplained.com/articles/an-intuitive-and-short-explanation-of-bayes-theorem/
„ … Bayesian Spam Filtering

One clever application of Bayes’ Theorem is in spam filtering. We have

  • Event A: The message is spam.
  • Test X: The message contains certain words (X)

Plugged into a more readable formula (from Wikipedia):

Bayesian filtering allows us to predict the chance a message is really spam given the “test results” (the presence of certain words). Clearly, words like “viagra” have a higher chance of appearing in spam messages than in normal ones.

Spam filtering based on a blacklist is flawed — it’s too restrictive and false positives are too great. But Bayesian filtering gives us a middle ground — we use probabilities. As we analyze the words in a message, we can compute the chance it is spam (rather than making a yes/no decision). If a message has a 99.9% chance of being spam, it probably is. As the filter gets trained with more and more messages, it updates the probabilities that certain words lead to spam messages. Advanced Bayesian filters can examine multiple words in a row, as another data point.

Further Reading

There’s a lot being said about Bayes:

Advertisements

September 9, 2017 - Posted by | Uncategorized

No comments yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: