Laabu ya Roulette · Laabu · Ebibalo · eddakiika 8

Obukulu mu Kubala kw'Ebibalo

“Eky'amakulu” kitegeeza nti tekisuubirwa ku nnamuziga omwesimbu, so si nti “kya mazima” era si nti “kya magoba”.

Eky'okuddamu mu bufunze

p-value ya 0.05 etegeeza nti nnamuziga omwesimbu yandivuddemu engeri ekyamye bw'etyo omulundi gumu ku amakumi abiri. Bw'otunuulira nnamuziga amakumi abiri, emu ejja kuyita mu butanwa.

empisa
p < 0.05
omuwendo gw'ebivuddemu eby'obulimba
5% ku buli kigezo
eddagala
okuddamu
ky'etali
p(nnamuziga asosola)

p-value kye ki

Assuming the stated null model, the p-valuelaabup-valueObusoboka bw'okulaba enjawulo eyenkana oba esinga ku eyo eyalabiddwa, singa nnamuziga abadde mwesimbu.Soma byonna → is the probabilityokubalaObusobokaObusoboka bw'ekivaamu, okuva ku 0 okutuuka ku 1 oba 0% okutuuka ku 100%. Ennamba emu: 1/37 = 2.70%.Soma byonna → of a test statistic at least as extreme as the observed one. It is not the probability that the wheel is fair or that the result arose by chance. Interpretation also depends on the design, assumptions and tests attempted.

ekigambokituufu?
p = 0.03 kitegeeza nti nnamuziga omwesimbu awa data ey'ekika kino 3% ku biseerayee
p = 0.03 kitegeeza nti waliwo obusoboka bwa 97% nti nnamuziga asosolanedda
p = 0.03 kitegeeza nti ekinnya ekyokya kijja kusigala nga kyokyanedda
p = 0.03 oluvannyuma lw'okukebera nnamuziga 30 bwe bujulizi obw'amaanyinedda; osuubira ebivuddemu bimu oba bibiri eby'engeri eyo mu butanwa
p = 0.03 emirundi ebiri, ku byokulabirako bibiri ebyetongodde okuva ku nnamuziga y'emukati kigwanidde okufiibwako

Okugeraageranya okungi

Buli kigezo ky'okola ku nnamuziga omwesimbu kirina obusoboka bwa 5% obw'okuyita ku mutendera gwa 5%. Kebera nnamuziga amakumi abiri, emu eyita. Kebera nnamuziga emu mu biseera amakumi abiri, ekimu kiyita. Kebera ekyokulabirako kimu n'okugatta kwa binnyaebikozesebwaEkinnyaKimu ku bisenge 37 ebiriko ennamba ku rotor. Era biyitibwa: slot, cup.Soma byonna → 37, okugatta kwa bitundu bya nnamuzigannamuzigaEkitundu kya nnamuzigaEkitundu ky'ebinnya ebigoberegana ku nnamuziga, nga kyawukana ku kibinja ku mmeeza ya zzaala.Soma byonna → mukaaga n'okugatta kwa langi kusatu, waliwo ekiyita. Eddagala kwe kusalawo ekigezo nga tonnatunuulira data, okikole omulundi gumu, era okakase ku data empya. Okukebera okuzuula nnamuziga “asosola” emirundi mingi kye kyaleeta ekivuddemu.

Obusoboka bw'ekivuddemu kimu oba okusingawo eky'obulimba ku p < 0.05%
ekigezo 1
5%
ebigezo 5
22.6%
ebigezo 10
40.1%
ebigezo 20
64.2%
ebigezo 37 (kimu ku buli kinnya)
85.0%
%
042.5085.0%
1 − 0.95ⁿ. Okukebera buli kinnya kyokka kumpi kukakasa okuzuula ekimu “eky'amakulu”.

Amakulu ku bunene

A large sample can detect a small departure from fairness that still does not make a bet profitable. At a true pocket probability of 1/36.5, a 35:1 bet has negative expectation. At 1/36 it breaks even. A p-value does not measure the size or practical value of an effect.

Amaanyi g'ekigezo

Power is the chance of rejecting the null under a specified alternative. For one pocket chosen in advance, an exact one-sided 5% binomial test on 1,000 spins rejects at 37 or more hits. If the true rate is 1/30, its power is about 28%, not 50%.

Omutindo ogw'enkola

Okwogera ku kusosola kusaanire okufiibwako: ekigezo ekyalondebwa edda, p < 0.01 mu kifo kya 0.05, okuddamu ku kyokulabirako ekyetongodde eky'obunene obufaanagana, n'emirundi ebinnya ebisinga okujja gye bijja egiteeberezebwa ku 1/34 oba okusingawo oluvannyuma lw'okuddamu. Omutindo ogwo gutuukiddwako emirundi mitono mu byafaayo by'omuzannyo, era tegutuukiddwangako, ebiwandiiko ebya lukale bwe biraga, ku nnamuziga ow'omulembe alabirirwa.

Ebibuuzo

Lwaki 0.05?

Mpisa okuva mu myaka gya 1920. Tewali kyakuwuniikiriza mu yo; 0.01 kkomo lya magezi okusingawo bw'oba okebera nnamuziga nnyingi.

p bw'eba ntono nnyo, nnamuziga asosola ddala?

Oboolyawo tavaamu bivuddemu byenkanankana. Kiyinza okuba ekikolebwa croupier, ensobi mu kuwandiika oba ekizibu mu kuyingiza data. Ddamu.

Ekivuddemu eky'amakulu kimbuulira ekinnya eky'okusibako zzaala?

No. That requires a separate estimate of hit probability, its uncertainty and the actual payoutssenteEnsasulaZzaala ewangudde ky'ekomyawo, ekyogerwa nga “X ku 1” okwongera ku ssente za zzaala ezizzibwayo.Soma byonna →.

Okwesanyusa n'Okubala

Gezaako bino ggwe kennyini okusooka. Buli kugonjoola kuzingiddwa; kuggulewo ng'oli mwetegefu.

  1. Suppose a dozenzzaalaDazeni1–12, 13–24 oba 25–36, esasula 2:1.Soma byonna → chosen before data collection appears 742 times in 3,000 independent double-zeronnamuzigaZeeroEkinnya kimu ekya kiragala ekitabikkibwa zzaala ya emu ku emu, eya dazeni oba ey'empagi; y'ensibuko y'enkizo ya kaasino. Era eyitibwa: zeero emu, 0.Soma byonna → spins. Under the uniform model, how many standard deviationsokubalaEkipimo ky'enjawukanaEkikolo kya kkubo bbiri eky'enjawulo y'ebivaamu; ebbanga ery'abulijjo ekivuddemu we kiba okuva ku muwendo ogusuubirwa.Soma byonna → below the mean is that? What is the probabilityokubalaObusobokaObusoboka bw'ekivaamu, okuva ku 0 okutuuka ku 1 oba 0% okutuuka ku 100%. Ennamba emu: 1/37 = 2.70%.Soma byonna → of 742 or fewer hits?

    Laga okugonjoola

    Eky'okuddamu Nga ebipimo by'enjawukana 8.1 wansi. Nnamuziga ow'obwenkanya yandikikoze nga omulundi gumu ku kugezaako 3 × 10¹⁵, kwe kugamba tekibaawo. Eky'okuddamu ekyafulumizibwa n'ekibuuzo kigamba 11.75; ffe tufuna 8.07.

    Under the stated model, X is binomial with n = 3,000 and p = 12/38. Its mean is np ≈ 947.37 and its standard deviation is √(np(1 − p)) ≈ 25.46.

    The standardized difference is (742 − 947.37)/25.46 ≈ −8.07. Summing the exact binomial probabilities from 0 through 742 gives P(X ≤ 742) ≈ 9.77 × 10⁻¹⁷. A normal approximation with continuity correction gives about 4.25 × 10⁻¹⁶; the relative error is large this far into the tail.

    This is the probability of the specified data event under the model, not the probability that the wheel is fair. Such a result calls for checking the observations, independence, uniformity and analysis plan. Selecting the worst-looking dozen after inspecting data, or searching many wheels or time periods, requires accounting for that selection.

Eky'okusesa

Nnamuziga omu ku amakumi abiri abeesimbu “wa makulu”. Ekyo kye kitegeeza omuwendo ogwo.

Nnamuziga omu ku amakumi abiri abeesimbu “wa makulu”. Ekyo kye kitegeeza omuwendo ogwo.

Ensibuko

  1. Pearson, K. “On the criterion that a given system of deviations from the probable…” https://www.amstat.org/asa/files/pdfs/P-ValueStatement.pdf
  2. Feller, W. An Introduction to Probability Theory and Its Applications, Vol. 1. https://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/chsqgood.htm
ekyokulabirako: roulette ya Bulaaya, zeero emuenkola y'okubalirira ↗ensibuko ↗