I have published someth<strong>in</strong>g <strong>in</strong> that direction [i, ii] but now I wouldhave wished to accomplish such work fuller <strong>and</strong> better. F<strong>in</strong>ally, foreach author <strong>the</strong> aim <strong>of</strong> publication consists not only <strong>in</strong> <strong>in</strong>struct<strong>in</strong>go<strong>the</strong>rs, but to learn someth<strong>in</strong>g himself as well. In those booklets, Ihave made some ra<strong>the</strong>r extreme statements on <strong>the</strong> practical uselessness<strong>of</strong> certa<strong>in</strong> specific methods, for example [...]. It is not difficult toquestion such viewpo<strong>in</strong>ts; concern<strong>in</strong>g each def<strong>in</strong>ite problem it issufficient to <strong>in</strong>dicate at least one successful practical application <strong>of</strong> <strong>the</strong>discussed method. Obviously nei<strong>the</strong>r I, nor anyone else is acqua<strong>in</strong>tedwith all <strong>the</strong> pert<strong>in</strong>ent literature but I attempted to accomplish a sample<strong>of</strong> sorts from an <strong>in</strong>f<strong>in</strong>ite amount <strong>of</strong> <strong>in</strong>vestigations so that <strong>the</strong> partisans<strong>of</strong> one or ano<strong>the</strong>r method could have felt <strong>of</strong>fended by my extremepo<strong>in</strong>t <strong>of</strong> view <strong>and</strong> prove <strong>the</strong> opposite.However, concern<strong>in</strong>g <strong>the</strong> application <strong>of</strong> <strong>the</strong> Bernoulli pattern tojudicial verdicts, nowadays no one will probably argue; it is generallyacknowledged rubbish 1 . All <strong>the</strong> o<strong>the</strong>r problems are, however, quitevital. I have thus considered <strong>the</strong> publication <strong>of</strong> those statements not asf<strong>in</strong>al conclusions but as <strong>the</strong> beg<strong>in</strong>n<strong>in</strong>g <strong>of</strong> a big work for betterascerta<strong>in</strong><strong>in</strong>g <strong>the</strong> actual situation.It was thought that we will have to do with a comparatively smallamount <strong>of</strong> concrete material. However, this is not <strong>the</strong> only essentialadvantage <strong>of</strong> <strong>the</strong> described method <strong>of</strong> sampl<strong>in</strong>g as compared with afull study <strong>of</strong> <strong>the</strong> publications. It is known that scientific papers areusually too short so that read<strong>in</strong>g <strong>the</strong>m means decod<strong>in</strong>g 2 whereas <strong>in</strong> thiscase all difficult questions could have been resolved by ask<strong>in</strong>g <strong>the</strong>authors <strong>the</strong>mselves.Of course, along with really scientific objections I have receivedo<strong>the</strong>r, <strong>in</strong>significant letters. Usually such are reports about <strong>the</strong> results <strong>of</strong><strong>in</strong>vestigations <strong>in</strong> which <strong>the</strong> correspondent did not participate but onlyknows about <strong>the</strong>m by hearsay. In such cases, s<strong>in</strong>ce no def<strong>in</strong>ite data areprovided, it always rema<strong>in</strong>s <strong>in</strong>comprehensible whe<strong>the</strong>r <strong>the</strong> success wasachieved ow<strong>in</strong>g to a correct application <strong>of</strong> <strong>the</strong> <strong>the</strong>ory <strong>of</strong> probability or<strong>in</strong> spite <strong>of</strong> its wrong use which is not excluded ei<strong>the</strong>r. For example, if<strong>the</strong> report <strong>in</strong>forms about <strong>the</strong> successful work <strong>of</strong> some technical system,that could have been achieved both because <strong>of</strong> a correct estimation <strong>of</strong><strong>the</strong> essence <strong>of</strong> r<strong>and</strong>om disturbances but also because <strong>the</strong> designerneglected wrong stochastic estimation <strong>and</strong> guided himself by hiseng<strong>in</strong>eer experience which had proved sufficient.On <strong>the</strong> whole, <strong>the</strong> desired result was however achieved: I have<strong>in</strong>deed obta<strong>in</strong>ed objections <strong>of</strong> a scientific k<strong>in</strong>d, although a smallnumber <strong>of</strong> <strong>the</strong>m. They concerned <strong>the</strong> tail areas <strong>of</strong> distributions,forecast<strong>in</strong>g stochastic processes <strong>and</strong> possibilities <strong>of</strong> a periodogramanalysis. Regard<strong>in</strong>g <strong>the</strong> first two items, I was able to become thusacqua<strong>in</strong>ted with <strong>in</strong>terest<strong>in</strong>g <strong>and</strong>, judg<strong>in</strong>g by <strong>the</strong>ir first results,promis<strong>in</strong>g studies, far, however, from be<strong>in</strong>g accomplished. Therefore,I should not yet reject my statement that no reliable practicalapplication <strong>of</strong> <strong>the</strong> pert<strong>in</strong>ent methods is known. In spite <strong>of</strong> all <strong>of</strong> itsnegative essence, it is useful <strong>in</strong> that it stresses <strong>the</strong> need to workpractically <strong>in</strong> those fields.The most remarkable <strong>and</strong> scientifically irrefutable was <strong>the</strong> objectionmade by Pr<strong>of</strong>essor V. A. Tim<strong>of</strong>eev concern<strong>in</strong>g <strong>the</strong> application <strong>of</strong>86
periodograms. It occurred that work with <strong>the</strong>m can be successful forexample when adjust<strong>in</strong>g systems <strong>of</strong> automatic regulation for isolat<strong>in</strong>gspecific periods <strong>of</strong> disturbances so as to suppress <strong>the</strong>m. The appliedtechnique is not stochastic but I considered it necessary to describebriefly <strong>the</strong> example provided by Tim<strong>of</strong>eev (§ 2.3 below).Then, when becom<strong>in</strong>g acqua<strong>in</strong>ted with some statistical medicalproblems, I encountered an apparently promis<strong>in</strong>g example <strong>of</strong>application <strong>of</strong> multivariate analysis (§ 2.2 below). It is almostdoubtless that such methods can also be widely applied <strong>in</strong> technologyfor solv<strong>in</strong>g various problems <strong>of</strong> reliability <strong>of</strong> mach<strong>in</strong>ery. However,much efforts should be made for exclud<strong>in</strong>g <strong>the</strong> almost.I thought it useful to discuss also a problem <strong>of</strong> a more generalnature: what k<strong>in</strong>d <strong>of</strong> aims is it reasonable to formulate for a stochasticstudy? Naturally, <strong>the</strong>y should not be ei<strong>the</strong>r too particular (that wouldbe un<strong>in</strong>terest<strong>in</strong>g), or too general (unatta<strong>in</strong>able), see <strong>the</strong> historicalmaterial <strong>in</strong> Chapter 1.I am s<strong>in</strong>cerely grateful to <strong>the</strong> Editor, V. I. Kovalev 3 , who <strong>in</strong>itiatedthis booklet <strong>and</strong> <strong>in</strong>variably helped me.1. Extreme Op<strong>in</strong>ions about <strong>the</strong> Theory <strong>of</strong> <strong>Probability</strong>1.1. Laplace’s s<strong>in</strong>gular <strong>and</strong> very facile metaphysics. Both <strong>in</strong>teach<strong>in</strong>g <strong>and</strong> dur<strong>in</strong>g practical work I have to encounter (although evermore rarely) delusions about <strong>the</strong> actual possibilities <strong>of</strong> stochasticmethods. In an <strong>in</strong>tentionally rough way <strong>the</strong>y can be expressed thus.Consider some event. We are obviously unable to say whe<strong>the</strong>r itoccurs or not. It is <strong>the</strong>refore r<strong>and</strong>om, so let us study it by stochasticmethods.If you beg<strong>in</strong> to argue, a few textbooks can be cited where <strong>in</strong>deed anapproximately same statement (although less roughly) is written. Itfollows that <strong>the</strong> <strong>the</strong>ory <strong>of</strong> probability is a special science <strong>in</strong> whichsome essential conclusions can be made out <strong>of</strong> complete ignorance.From many viewpo<strong>in</strong>ts (historical, psychological, etc) it seems<strong>in</strong>terest<strong>in</strong>g to f<strong>in</strong>d out <strong>the</strong> historical roots <strong>of</strong> that delusion. In general,<strong>the</strong> study <strong>of</strong> <strong>the</strong> emergence <strong>of</strong> some approach (scientific approach <strong>in</strong>particular) is extremely difficult s<strong>in</strong>ce it usually dem<strong>and</strong>s an analysis<strong>of</strong> great many sources. The <strong>the</strong>ory <strong>of</strong> probability was, however, lucky<strong>in</strong> some sense.At <strong>the</strong> turn <strong>of</strong> <strong>the</strong> 18 th century a greatest scholar, Laplace, summed<strong>and</strong> essentially advanced both its general ideology <strong>and</strong> concreteresults. Be<strong>in</strong>g extremely diligent, he left a very detailed description <strong>of</strong>his views <strong>and</strong> results <strong>in</strong> his Théorie analytique des probabilités (TAP).We consider it permissible to restrict our attention by analyz<strong>in</strong>g thiss<strong>in</strong>gle source although a strict historian <strong>of</strong> science certa<strong>in</strong>ly will notapprove <strong>of</strong> such a view. For his part, he will be <strong>in</strong> <strong>the</strong> right; forexample, it is extremely important for <strong>the</strong> history <strong>of</strong> science to study<strong>the</strong> evolution <strong>of</strong> Laplace’s own ideas <strong>and</strong> his relations with o<strong>the</strong>rscientists, but we are actually pursu<strong>in</strong>g a narrow applied aim.In our century <strong>of</strong> rapid development <strong>of</strong> <strong>the</strong> science <strong>of</strong> science weought to describe our source [see Bibliography]. It is a great volumeconta<strong>in</strong><strong>in</strong>g about 58 lists 4 <strong>and</strong> it is pleasant to note that also <strong>in</strong> our time87
- Page 1 and 2:
Studies in the History of Statistic
- Page 3 and 4:
Introduction by CompilerI am presen
- Page 5 and 6:
(Lect. Notes Math., No. 1021, 1983,
- Page 7 and 8:
sufficiently securely that a carefu
- Page 9 and 10:
is energy?) from chapter 4 of Feynm
- Page 11 and 12:
demand to apply transfinite numbers
- Page 13 and 14:
for stating that Ω consists of ele
- Page 15 and 16:
chances to draw a more suitable apa
- Page 17 and 18:
Let the space of elementary events
- Page 19 and 20:
2.3. Independence. When desiring to
- Page 21 and 22:
Eξ = ∑ aipi.Our form of definiti
- Page 23 and 24:
absolutely precisely if the pertine
- Page 25 and 26:
where x is any real number. If dens
- Page 27 and 28:
probability can be coupled with an
- Page 29 and 30:
Nowadays we are sure that no indepe
- Page 31 and 32:
λ = λ(T)with λ(T) being actually
- Page 33 and 34:
(1/B n )(m − A n )instead of the
- Page 35 and 36: along with ξ. For example, if ξ i
- Page 37 and 38: µ( − p0) ÷np0 (1 − p0)nhas an
- Page 39 and 40: distribution of the maximal term |s
- Page 41 and 42: ξ (ω) + ... + ξ (ω)n1n{ω :|
- Page 43 and 44: P{max ξ(t) ≥ x} = 0.01, 0 ≤ t
- Page 45 and 46: 1. This example and considerations
- Page 47 and 48: IIV. N. TutubalinTreatment of Obser
- Page 49 and 50: structure of statistical methods, d
- Page 51 and 52: Suppose that we have adopted the pa
- Page 53 and 54: and the variances are inversely pro
- Page 55 and 56: It is interesting therefore to see
- Page 57 and 58: is applied with P(t) being a polyno
- Page 59 and 60: ut some mathematical tricks describ
- Page 61 and 62: It is clear therefore that no speci
- Page 63 and 64: of various groups of machines, and
- Page 65 and 66: nnA(λ) x sin λ t, B(λ) = x cosλ
- Page 67 and 68: of the mathematical model of the Br
- Page 69 and 70: dF(λ) = f (λ) dλ, so that B( t
- Page 71 and 72: usually very little of them. Indeed
- Page 73 and 74: This is the celebrated model of aut
- Page 75 and 76: applications of the theory of stoch
- Page 77 and 78: achieved by differentiating because
- Page 79 and 80: u(x 1 , x 2 , t 1 , t 2 ) = v(x 1 ,
- Page 81 and 82: Reasoning based on common sense and
- Page 83 and 84: answering that question is extremel
- Page 85: IIIV. N. TutubalinThe Boundaries of
- Page 89 and 90: at point x = 1. However, preceding
- Page 91 and 92: He concludes that since the action
- Page 93 and 94: The verification of the truth of a
- Page 95 and 96: In the purely scientific sense this
- Page 97 and 98: ought to learn at once the simple t
- Page 99 and 100: the material world science had inde
- Page 101 and 102: values of (2.1) realized in the n e
- Page 103 and 104: *several dozen. The totality µ ica
- Page 105 and 106: Mendelian laws. It is not sufficien
- Page 107 and 108: example, the problem of the objecti
- Page 109 and 110: a linear function is not restricted
- Page 111 and 112: 258 - 82 - 176 cases or 68.5% of al
- Page 113 and 114: The Framingham investigation indeed
- Page 115 and 116: or, for discrete observations,IT(ω
- Page 117 and 118: What objections can be made? First,
- Page 119 and 120: eliability and queuing are known to
- Page 121 and 122: Kolman E. (1939 Russian), Perversio
- Page 123 and 124: measurement is provided. Recently,
- Page 125 and 126: which means that sooner or later th
- Page 127 and 128: The foundations of the Mises approa
- Page 129 and 130: A rather subtle arsenal is develope
- Page 131 and 132: 4.3. General remarks on §§ 4.1 an
- Page 133 and 134: BibliographyAlimov Yu. I. (1976, 19
- Page 135 and 136: processes are now going on in the s
- Page 137 and 138:
obtaining a deviation from the theo
- Page 139 and 140:
VIOscar SheyninOn the Bernoulli Law