Scribd
Upload
36 views

ME 1 - Probability

Uploaded by

roshni mohan kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
36 views

ME 1 - Probability

Uploaded by

roshni mohan kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 105
‘een tee, Regulation 2019 Semester 1 Total Hours oo) ie "| _ Hours / Week | Category | Course Code Course Name c} Lo P Mathematical foundations of B 19PCSB10IT 3 1 0 4) Computer Science | Prerequisite Course (@) 1 Discrete Mathematics ~ i | | Course Objective (5): ‘The purpose of learning this course is to: | Understand the mathematical fundamentals that is prerequisites for a variety of courses like 1 Data mining, Network Protocols, analysis of Web traffic, Computer security, Software engineering, Computer architecture, operating systems, distributed systems, Bioinformatics, Machine learning. Develop the understanding of mathematical and logical basis to many modem techniques in information technology like machine learning, programming language design, and concurrency. 3._| ‘Study various sampling and classification problems. Course Outcome (s) (COs): At the end of this course, learmers will be able to: COl | Explain the basic notions of discrete and continuous probability. (CO2 | “Understand the role that sampling distributions play in those methods. IMlustrate the methods of statistical inference implemented in various models. ‘Summarize the correct and meaningful statistical analysis, ‘Understand the recent trends and application of statistics in the field ‘of computer science. PROBABILITY 43 | Probability mass, density, and cumulative distribution functions, Parametric families of distributions, Expected value, variance, conditional expectation, Applications ofthe univariate and multivariate Central Limit Theorem, Probabilistic inequalities, Markov chains UNIT IL RANDOM SAMPLES oF3 Random samples, sampling distributions of estimators, Methods of Moments and Maximum Likelihood. . UNIT MIT STATISTICAL INFERENCE oF3 Statistical inference, Introduction to multivariate statistical models: regression and classification problems, principal component analysis, The problem of overfitting model assessment. UNITIV GRAPH THEORY oF3 Graph Theory: Isomorphism, Planar graphs, graph colouring, hamilton cirulls and euler cles Permutations and Combinations with and without repetition. Specialized techniques to solve combinatorial enumeration problems ‘Approves ay Curriculum and Syllabus |2019 Regulation ot bane tk Haantien a sees ‘alee Nara UNITY. COMPUTER SCIENCE AND ENGINEERING APPLICATIONS: oF3 Computer science and engineering applications Data mining, Network protocols, analysis of Web traffic, Computer security, Software engineering, Computer architecture, operating systems, distributed systems, Bioinformatics, Machine learning. Recent Trends in various distribution functions in mathematical field of computer science for varying fields like bioinformatics, soft computing, and computer vision. Reference (8) 1 John Vince, Foundation Mathematics for Computer Science, Springer. K. TrivediProbability and Statistics with Reliability, Queuing, and Computer Science 2 Applications. Wiley. 3 | M.Mitzenmacher and E. Upfal Probability and Computing: Randomized Algorithms and Probabilistic Analysis, 7 Alan Tucker, Applied Combinatorics, Wiley Approves By ot See 8 Hamantune Probability Prbability Ra mathemaltal moore ok Uncertatnty Probability tomy a branch aj, athonatls that deals ustth the analysts of uncertain evens py fanclom Zvents. Deffrttfon oa random experiment can vest tw ww vakuelly excluxive » exhaustive ant equally Kihely — ways cand > mw’ of them oat faveurable for on event 4, thon de etd MO cabled the probability of A cauntng £ TEE donoted by PCD Pt = He favourable rumbex of Corrs w aetal number of cares, Axioms oy Probobilfty » of Pca) 4) » PCs) =) 2 TH A 8B one muteally exclusive aes PCADB) = PCA) +PCB) Random — § x pertinent | An expertment £4 which the drome, cannt be prodictel utth certainty cobled a yourdom ex partment, age oll posible pubcomes ar2 lunown. Trtals: Fach performance ef a yandom export is cabled n tral - EX Toting a cof stimu faz trial. Sample» space The Act eb all parsnible owtcoma of a yandom experiment called. fs som Space and % donstad he iS EX Tos a cm One > = {Hj Te cow, Torsel > Sa SHH, tr, THT Event! Arig pobrek a tho sample space SD Cobled an event The null set & 2 Xs’ one pw events. gt called the tmposstble event Bais galled +t. Sure or certatn ov Multeally px cluytw Events ' io events 2 sald to be yusbually xtc CF they have ve wanes events hh \coren (e they Cammst OCCU sirabtaneousty J Ey; When a dic & Yolled . tre events Sa s5y and Sa,n bh oe mutually exclustte. ~event™ Exhaustive evenks the ullection of vents ohare untor 3B a whole cample erate are’ called exhuutve events. fxs when we oh dons CoP ttee 5 events oh gellfrg bo heads, exactly one hoa, wo look a2 exhaurbtywe events, Equolly Atkely events Tosv ate ore events aually Mk YF cach ow of them hw an ayal chance of occ wrthg Ex voben we bAS a cotn, hoad & tal ~~ 24 volly Siroly evenk $ ave sald fo be Random vaxfable ge’ ts sample probability manntt and x’ Bo function. defined ever the dlomonks ofS’, thon x’ sy lla a rardone vastoble Te ob alse cdbed or a chan ve vatfable | space wrth a tra ebochastic valtable - Probabthity ditctadten funtion of X- Lp! & a vandom vortable, then the funcdon FOO deh nad 3 FOO= Pi xeny é fundion of X- Tyr Random sib cr Dis erete Random vi Gn) Cottnuow — Random on Diseree — Yandow vartable inn “A Yandom vortable whose sok ae pour Values % oftber fertte or countably wpihete called -dltecre» Yandlom vartable - ‘ fe 2 te gee ee reprcsok the HM | called the dtatribut Probabilty MAS funcifon Th xX Be a Atscrete yandom. vartable, thon tho functin pony = PUX=%] ts called the probabiltty mays function of x. pene ( Plx=2) = per) = Px. QW ex) B non - nggaltve for all real “x: aid the sum ch ok pr) over all peastble Values of XY B om- We) 2p = } A vardom yortable i aatd te be cottons tf fe takos all porstble Vanes behoom cortatn Lemits- oe Tho Dength ab tomo during which a vacue ina, Cee, 1 pc RE OF aye SEM: ot 5 Noe ah x vw for any a,b A » then Pla ZN 2% ) = Pou ZX 4%) = P(x, 5 XE%a) = POA S XK % )/ a Conf ruoud yandom voxrrable Probability densely funclfon For a contXrmows sparcom yarfoble %, & prabability doniity function fo B a functfon Sud thot w Fi >o > ford) I) Pape yb front - area under fo) | from a bb | D pend the probability mars furction. gor gelthra zig -whon tys0 dice ano thrown. Soln’ - Too dige ase Tmo. her Xx be 4 vandon vartable -oh golfing wumber ob 3's. x tan take values orl 2 Sampe space S= } Cm U2, U3) Ged , WE GE Qn? 22> , VD, QL BSD,26) B/G2) BD, BD, 6b) (4! @r2>v Qa- (44), @s) Lao 61D D> Ds Gy - Ore (a) 6), G27 G3) GH, Ws), © ») p(n 3) = PCxs0) = 25 BL Plow *3) = PCx=1) = Jo 3b P(two-r) = P(X=2) = ley Probability mars fundior. iz oss ! pt PIK=*) 25a, oh — Yab A arden vartable x hos “the fallacing mars UM. H ee ee es 4a as G PO=%) k 3k 5k Fk 4k Nik 13k 1) rl k > Evaluate P(x '24), Plxo5) 2 PB exch) Jnt- wkT SPR=?, ? Z Pp Cx=9) =). Aso =a) 4 P = D9 PlX= 4) 4 Pecos) P(xs0> 4 P(x=)l) 4+ P& + P(xz6)= J Seg Bk KA AK A AKANKHIBK = ) 4aqk =) Gy PCXSH) =POrce) + POr= 1) + POX=2) + P(e22) ere +3, pt wb wt tat a ha aay P(X >5) = plx= ae =), Pra 5) Solni- ' cD PCKL =. [foods i ) ~ fe dee bem ef-s) -& = cm pix oO- Pex! DR mal? 7: Js Co dh 4 Joram ae han +f 54 x 3 — Lica + 1 (eo = ag Os x! 2 7 pp en tr C-t-( 2») — ou aD aie = PlxeD Sood f BKAS > = fede = Jiedn fo : sre HREM ax >2 DA Continues vandom vortable x has the. ECan) = ° rE 22) | je tenes 1 TF x>g Hrd ke poaltol di abibulton oo ola = = Nk Fon = 9 en) ae r $e = 4f X24 Wad $$ Lanes : if Kg Bel pati ~ r pets Sf Fem x=] Fak (aaSdx sii \ a3 Kfar 4 4 fas ; 2oe Kfar J) = k (te -0) =) key : oA 5) nd a @rtant b>o, fee 1S ,OLh oO ew For the pdt we have oo { fen) da =) 0 b > (dn =) BL | 6 4 (ey b =0-355 Btho Dongth of Xme (fh mints) that a cortain Jady speaks an the telephone -h found to be yandon phenomenon wtih a proba funckton specttied by the function.» ae for 220 ° O.W- 8) Find A’ that maker Lexy g pat b) What f fae Probab Ali, that the no of pevsni nk erate eit minutes that she will Ask wver +thephore fs G) wore Than to ofrutes > Jews than & wlnnkzs CID pebuacen + & Lo minutes oO a) Ste doe), nr % fae Bd. = A ‘(= ) =) Ve 2 ra (eee) 2] —5A (o-D =) SBA =) b> we have ee / R20 © 0.\0 the. prebabstitey ahok the Sadly talks moe than (o whukes per He prore f& given by hey, PC x> Io). % Py, “1 fey wre ae i604 4-2, = -(2 “¢ = “Te - 3.9) on mines bye the phon is dive by POX 45) = pee — | " PCxes)= ex! z CHD the probability ot #Q {0 ntrutes aver by x Xi = ¢ (ody. o% ; aaa a 1°’ ; nape S - 4 Ce] Lemus) =. ere , eC WF e Lee j yi . = ¢ eee!) Cros Can = /€-l ex Distribution Function teal coomllblive Drstrtbubton cuntin © Clf) Tx & ee Pee ee Properttes — ob -Cundotive D\Atri bution Fin tion Dro ha nm -decrety functton of Gey tf m2ag thn Flt1) £ FOle) 2) FC-w0)=0, Flxo)=! DU x b ag disuece rv thon P(x eae) = FOr) — FOGH) [Relation bro pmr 2 cdf J A st x % A confrune y-v there 4s Eta) = F0) vohere. Fx) ts differendtall [ polation wo PAL gcadt] > Consider the Xpertment of taving a faty cfr atimes, Balthe Keo. Tf 78 3 | beach yet, Yo heal appears, Kaw TF Sor 4 head appends - pri. ..c.df ob xX. Sealy When 4 Coors he forsed , tho sample spate B S= Hem, UHHD, wera), THR), ene, (eer, WITH , tery, UTD, (THT, (rund, Were LTT ort) THD (777) ws) = te fen X=0 if out ¥ ' a mon. tf 5 xege 7, Fog 4 nm 0 find = Probabt lity me 6 ~—: eee ee Po): r L 3 fo find cdf Fon) = POX en) rte) POX ed) = Pred == \b FD = pixer) =Pk=o) + Peat) aby bee Ee Fo) = P(Ke2d = Pear) +P 2) J POD =e br Silk rie ee =! A rv ox has the prohabi Qty pundlten given by © 1 2 93 14 ok ob 71S 2. Ja fa a IBA Isa 17a nts) = Wen x20 Ff OW WG + inhead) haan X=t tf eC x= 0% wf 3 or a ae Pn 0 find Probabt lity Ae o oo pa). $5 le ip. J fo find cdf Ecw) = PCxXex) Figo) = PC xX oo)= (xsd) == \b FOD = plxes) = P&=o) 4 P=) =my bo ol Fel te AE Fo) = P(xe2) = Pleat) POE 2+) J pee 3) erp hy & Vee e =} F(2) =) > A . rv ox hw the probability puncken given by z o : es = 4 a PCK= a) a 3a a Ta qa “lla (BA Isa Ia Bend Cd the value vf 4 Gn pind cdf bY. ® To feral 4a” : : Powe). wekT rh ra % po§ then 2 OF) =) (fe) a 4304 5ay Far 444 NadBat FAFA =| eazy Oi) qo gerd cdf the gfver —problen can yeuoritten a4 x D ! D Ss 4 sb 1 ee Poca) + 3 Piet tl, Bw h 2 ee! gt OBI AA WET FEL) SPO Ex) Fe) = P(X 40) = Pico) = 1. al FO1) = POcey) = Pleco) pple!) = kh - at 3 ie Fo) = P(x 42) = PGr=0) + POt=1) + POt=g) Se bo al ate =o BCs) © POKES) = Phen) 4 P(e 1) FPO = 0) Pee ay sht S45 4H i 3! s! ata ee Fl #l yi F(A) = 25 7 F(6)= 3h 3) F(b) = 4q. gy! FCs) = 64 9! Cg) = 8h _ | gl the fof x & : : . a fo . Ff bb 2 a | FX) & 4 4 g & 5 ge 2) 4 Tandon varfable K hus the sollmotng disb?bulfon, m2 Oe N a, 4 & 6 7 Pm - 6 gk ak Ko WK ) Ferd k Gi PURE Lx «Here ) Wi the mallee value of for PUKE > by Wk: ; Z p(y =), D> OPKF QW SktBkrke4 H+ TK | Fe + OK? _ | ie beh 44k-\ 0 Tie kek o k= -1 Cove term ae [es Yo] condthinal Fob nD : OD PCF ex 2 ae ‘pF vo) ler) p(s) =? =P(Qrexd ws) ~F (ore tne ner) PCs wea P(x >2) TP <2), =. Plw=D4+PX=4) | POX £22 » ~ .X& 43 Beg | 1 (OFa+ Ey 1, = Br We a | 3" 4 4 (GID Fre) = Px 2b) 20 FC) = Pie e1)= PCws0) 4 pire) SO a dg = 692, 1 19 2 F(a) = POX S22) = PLK=O FP l=H) 4+ PGr= a) =orh+2 =O FI + = Ho HOSS (3) =P (x £2) = oth+2 42.590 te TS eta . ve AX EC Aad = PCXEA) = 0tb42 +243, eo he > ee To To lo 7o™ By given cond ton, Problems =m Continuo random yortahle, 19 Th Hee density funetfon of a Continua y. ¥ x & given by fre) TR OS KET 12nxe., 2aK ‘gene 3 3 clase where i) FRA phe value of 27 w tnd CDF ef x, 28. wkr (Simdasy -—A oO \ 2 20 4 dur foxy Linen at Jjsmax ffm x4 [foo xa f i F | W) ere fo oF Jando fades (ee aie 4 p =) ° t 2 -. 41 ee 3 on | 4 A(x] 1 Gan-axt J = « ° ' 2S ad) 4a (a4 84(3-2)-% Sie: a» w+ BA -Sh._ a +2 Bea! a t+gayba-F& _| oo ae S| z & lis Lhe —o tb pa ePixe@ =e tn Pe f%e° Tn the interval, oexel a x z dy = FIn) = Jaa =] ude © Xm 7) =e R tT do - af the Trterval, J2ae @ : ys Fea) f da f Era) = finydee { - 3 pb — : i % "i a Fro) 2-4-4 tn interval , genes y Km ren) = fea) du eo 5 4 = Saednt Sada + [> doe 2\! 1 j x (Beto Bad) = 4 0) +41) 13 (-2) (24) Fp 54-922 4' ! ibe eas oe nr - FHr-e ZF eet) = Sa -B 5 Fcx 2 Be Tn Hee Prloryal + X>S FX) = (feay de 2# a i (1dr thant ia yd foss ; 3 } ! 2 yy =. (B)'+ deel 1Ga- z @ = AC -wy4h o4Z (3-2) -L@-a) 44 a+ 2 q Se ve iP aly HRTFs a Fox) \l DA Contrumn VX teak Gan BOLE TE Valun bee acg Lace be the damiity given by Flay ek CX) - Ard PL x44] & PL3 Th C & Gonbant, thn -ECC)=C. CW th a, b ase Constants , Hen + Efaxtb] = ate(x)+b GID & (x+y) = ECx)FECY) w Eexy) Pind fu expected yandeom varlable X it given helow : nm * \ 2 = 4 5a P(xsmi ©) oO) o.3 o-G 2 Solu'- E(w=H= 2 ae PCX= 9) = J (oy) +2 fouy+3(0-ar+ 40-8) +5 (0-2) E(w) = au, Be. Find dtspersivn : ECA) = 42 xt Plr<%) _ Cos 44 Or)# (0 aye yb (0-2) 4aS(02) EOU=12. Vartyy = EC) -Eooy” =13-@-a97 D> rind Ye mean value oh the RY Wwhase pat fs given by -5 fm = Ee Roo-X), 042% S50 — Goln- Given Seay = B10" Ceol Moen = Ec) =f fro) dat. 00 loo fx [3 lo me Coo x5}Ax , > loo “$15 fives 9] de ° r foo jor * [100 28 = te ] _- Ss 4 ° io? joo (100) 7 a) | = * v D ler x be a wort RV wht pdf f-2,, x2. PYrd .(W) whore wae wkT E(Wi< J wong “[S&) ob} = Le dean. 2g,ay, - e. ae | 4] -0 -(-3)] -$@) WY % x =3 -2 -) 0 ; 2 F | Pix) OF i ola, (4x45) pnd 1) ECO Gd) £Cex+£3) WD & 1 gw EA). Y vind wd voox £3) Soln- 7 WM EQ=p = 2 We P(x= a) =-3 =(-3Yo08) 4 (-2) (oF Yo.3) 404° sos) + 2 (ors) +3 (0-1) ECA = 0Q5 Ge (2x3)? ° wir ECaxtb)= 4 E(x) 4b & (axt = 2 EOOTS = 2 (025)43 wr 20.28) -3 } E@aj=a7 © - 2 Gi) ECKID= 4 EOS + = 4(oas)ts = (iv? £8 = E92 9 (xe a9) f=-3 =» * (oro 5st Heo Coys €19* (0-3 Ot -1%(03)+ 2 10 Is42? (Co nr) E (x)= 245 () VG) = BO) SEO” 29.95 — ©2597 V(X) = 2-8STS” (vv) V (2x43) yar (art b> zat var (9 ylaxra) = Q Var (xd ~4(2 995) V (aaa y= I 8 5) Find the ecpeded value of the "o cho a die when than, lot x $e a random varfable which repre thee we ma die when thrown. (te) K= h2, 3,05 & ! PCr) =4 feb drt (EOD SEY FAC K) #3) ACL) ECD HL oe 34 &+5+6) ¢ + (AF) -% E Cy) ios G, Condittmat expectatfen. T mY) & a tw dimostoned biltty moss Atcerete R.V wt fathe probe | functfon, Py, then the condfifonal 2x pectaltn, | of g(x ¥) ate Aeftrad as follows E ; gGon) [Y= vi = gg eye Pods = Aqori) oe E fg) xan) = F sao * Th yd ea jun -Atmastonal - p af fry), Phen Contos RV watt foRnt E 4 ca dty} ce Sa Coy) F(xly) an fe far Wx} = faces) af eylrdoy In prattcular, Pyie = Bey Ix) = = fyi yoy yy ECM = Fat tlyee Propertios: a Th x @ Y are endopendont RVs then E(Y/x) = ECY) = Cxly) = Ele) ® EPEQ kM] = HB GW de) E FecykJ = ECYI elTecx¥) =EO) @ EL qo 9. == fi ERAT alla, Tn pare EC) = efx: E(yAD J L Parametric Fanntlin » ofp Distriputton: a DePtttm ¢ Paramebrte Family) A paramore gamily (of probability distribu, te a collection ob probability, denstty functions( probability . mars function) om @) trdewed by the palamoter space Q, that & a ollactton of donsttics of, dle form. [f(9): Bey Given a patamebfc farily one, HE Unig val pecifizs a probability denatty funchon| F (use). : ea re | Were, og paromeher space @ will be a ge | Subvaek of Rt for some Xk. Leg ok the patametiie familizs ob diatabuHfon_| (i) Expmenstal- “Families | TF port Polesem, Gramma, Noval, Beta, | Negeie Binendal, Geometric CW) -Transgornalfon. Garoup familias (it) “vedo exponential families (1) Mubfivestate Normal oltxtribubfon. (v) Chi -squared and von conbra obé -6yyared distytbublons - | Dicbtbulim .) Braomials Distrib udttin ce § Foe = 6 pq py” 1 Nae ‘ea AN(n-ay/ caf io Fuad. 1a) . . / Ke DCP ph" R is Pz Yostriction $P<),.. 1 $0.12. } by pee 5 2 = fone. ny Megan = hp Modes: - pene) ap. 8 Of penny 2 j x ' Pliny FS an topos 2 OW Vortance _ nP ep) Skoonm - |-2p V np (t-p) kurtosis Ly an z Std. Aaiatton - i i ‘a = Vet) Q. Potsanm — Desivibutfn - xe pom. _ fw=se wpe mM) At tal CAf - FX) =e z ow rote {7 “At yO Domain x2 fo. ba, ae dE : 1 Made At At-1 IF 4 i an Snbege, “4 L o otherutsa t Voslance re Skownoms —& ; tot an en 2 At < oNpwimade DBidb i pm “ se! foe Tae” Ge caf - No format ' Qc: 4s ra Maer, OOF oe -Domafy '--2 4 mae ' iy Bze Yip n(&) = 4 . The bean’ ak diatibudton Geng PR AGP BUSY Ucn Ss S Ter a browdal adistyiputtoe, moan ob , 90. Beve % ead fivat 2 tons AE the ‘Aictitbulfin . ) \ Hans np=b verlanve. = (¢.9)* = iz)" =a ney = . — = en ne 6 "3 Now -we have - PCK=a)= AG PE | Feo 9 Th fk on drm ate given HY nme) PU=D= 46 (HY (4)T = Unf POG = 14) {%) (4) . ew | = a: (4) ey \f a PO) = 6 (4) = Paty to Gal ee DILL ¥e is Binomt all Atatribubed RV tothe Elyza, $,VAM=sa, i P-lts5) Mean -np= & vailance = WP] = 4/, nop SEH T-%, Prl-wels nP =m w(t =n “sy -nsb i 6 6G = 6, pee SA) a) a eo, ¢ Job (US () Pies) = tar(=) A) The moan yortance -ee a, irentel vate ao. RL hy end Pe) Soln'.- rype a = ae Axd = WPL SMe Ms =k Pa % n(%)=4 he 4X4 = 6 P(x >)) = t-plxz 0) ={- Pcxze) = l- 0G (%) (4) G aes = 1b) Pox ar) =0-9986 ‘ Dm 0 company —sy/i defective components: O42 produced . Whak i the probability et ablauk 5 components are to be palaces tn vvdler to gee = dopedtves? Gm velar fo examine” 2 deportes, 5 OF move, Componontt mu 22 exounined. Hore > Peo0e, Y= 0 Probability phat atleut 5 components ato to be examina. = plx 2B) i Th ace eal a ee j- P(ASB) , ae [Blo [o-05) (0°45), + 56,008) (0% + Bly (word (04D 1 Fly tosh cet 2 ‘2 7 When a Fair coin is. tossed Ooottmas, Ped the mean Werfanie 45D Gitven N= 200 bet Pq ae probabili fice of gettrry haa, tail yoypectivaly , r Pe ¢ ty For bihemfal lt sbributton Mean = np = Bor ($)= (po vattanue= pq = Qoorl xt = boy SD = Va. =\R= Yor, D Find ta probability in amy a’ Colm dines » WS tow ull open: 1 ahead W atals £ ohoads Gd Atloat Whead Wy “het “more Man (tall "pot x pe the 2V donating the number of hoadt obleuned . - p= \o : y=) a’ eh tokT Pea =P grt) anole & WH P (gattry prance) hir=2, . =5e3 (4) Px=a) = 10 Lye ott gl Foi WD P(yetitre 3 tatle and ahoads) =P Cyelfing. 2 heads) = P(x =2,) , = bea (4) (4,)= 10 (24, =O: 3loe : fa Gi) Pe galftrg atleast | head) = p(k 21) = 1+ Px Zi) = |- Plx <0) ; =1- 56S ee ee = f= O103)o5¥ = 0+ 4688 Gu) P (gdfing nok mae ‘thon 1 tail) = +p Cgatting o tei) )) +P (getting Ld = pL gat ail heads) 1 (Jethg 2 jaa) ep-lxzs) 4 PUk= A) Bees 2 5dg (DY etytb) BD evt # = peat Ue = 6 Ba) = 3fy | 8) a} oe ab the screws produced aubemalfc machfne ae aejecthya 2 Bend fhe prob. that out eh D0 Seveus elected at random, thew ato DO exadly 9 de fect ves GD Amos 3 defective Gi Atlant: 2 dofedttves Qu) bh 125 dopedttves Cn clntve ) Grtven : h=20 PL pb. of sy ,& defective) = 12 0+] = 1 , lo Ga An b= t-o.l= oufog 2 PLXe w= MC ph gM% 4 nz Orb QO D) PC Pracly a defectives) | : Je 2 1% -zox 4 =PC(K=2) Wlieas (i) “Zz = 190 a ; CD PUBmort aacesfies) = PO SB) =P =0) 4 POX= , p(x ea) pbe=3) aot, US B+ 2c Ha) Hac aS an a 7 f eB) meee gl 7 oro0F tod dole gt, ew Groen fo} 140] T(s49) GP Catlaakt 2 defectives) =POK72) = I~ PXL2) =e [PCxeoy4 Plxer)J he LARP RC BT jo. 19 \y els Sleds bo fom Qu) Pl bho tre 2 thvee) ( mebutve) =PC 1Exe2) =P(x =a) $POr 22) F ROL =B) : F: 4 140 qt : alt ot Gat (5)t™ (45) = 4, [tor Hated Nas], a = [a4 re, 3) 4 nrachine manugactustry scr [knoe to produce by. dofoskive’ Did «, Ragolonge nie eh is screws hak is tha, proby tak thee oe CH) exactly » dofecttves pNak mae than 3 defective 1 dk P= pred. of Seve0o b clefestie= 5 _ Dos “ [0d L= I-P = [0 ose 0.”7e- hu = tet wk —— Plesa)= NO pr 4 ™ , CD Probability Coractly sddpectives) = POE) ” = 150, (0-059 tg, a5) = 455 (02 0@12e)fo. S4ogb) = b0Gory ~ t “ QD PC Nob more than 3 dofectives) = Pex 22) = Plexo) FPO) + PCa 2)4P O93) = 150 glo @Aas)'y sé, “ os @a'sy'ty Istgloos) (6. as) my SC orton =o O- 4b 4 O-3b57 +0. 3474 o: oss = 0994. A) An trvegular bfacod die Ys Huon such that th prob: that i aye Seven numbers th Sthyows % twice thy pb, that Pb gue & even numbers Th sthews. How ri vee of exactly - strfala Gn be 2xpectod to qe no even number, out off ose at f Lok p be tie prob. of getting Ppt tha throw of a Ae PUR) = 5Cy PRG Given Pltead> af P X= 2) 5 Cy Py = 2.50, Pa? Pa® xa? P =a (1 Poin 3p <2) [PE%) > BEB fee vr- Atha timber! oh seks hat eae Pr ope, stbey ls = asm Plt >0) = -mBeisSe08] ern v « 54 ~5q) | ( = oe = spoamaol) 5) An tregulal AIK "Javad die is thang 2 the. expedition Hal th lothous, it wl ig : even pon te wid the expetation “thet will gfe four evan pumlors « Hmamany timed 2 lorsco sets: oF to ‘throws ack > tamed qou, axred FL ap ghe oe ha? Git A An PE, = Be, Phe Lop) Wg! Defthttfon - Poteson pretribukfen A RY CX’ B wil & —hllne 2a. polsson clistibulten ff Tt assumes ondiy hon nogabtve (posite) yolues £ Pts prof a gfven by Dron POX =2) =Pon = e3 seo © 2 d20 ° other wise dB kaon os parameter of the Passo Distifbutfon , tee: whore the POSSI ° prpabitty haus can be apt deedtive Home produacd fr the ma of deatfs -due toa yave olfsease. ‘s) No of mistakes committed by a typlsé per mgr a em poss vata such that PX=8) = Pte 4) +40 Kesicad!, Sand hctcllionin P =x) = pin . ot Oe S y P —Pla)=e =f L Pies) ~~ pia) « Sot 4! ib Rab) i. ve 7 Pl-a) = 4p(x=4) 4490 plx=6) <* Sue ke qoeN ! Al 6! oF. nT en] eRe aR Haak -4 = © (xy 4 gee -4=0 x (pea) 10+) =O rea) O*- 0 =O To oe At n bung trafic junction the prohabt ity of an individual havthg an acct dusty Qa ore part op the a4 eee ne though the Junto what Bale probally Hag fwo or mone accidents occur duning Hot eee bot ‘x’ be the RY . donaetig the mumber at accidents during a certatn paar of a dey. Given -Pp=0-01, N-=tooo donk & pool However Mgan = AP= Ilevo X0.0} =to PCa’ ncetdent ocout 2” a spodifted period) = Ply=x) = po a PCR or mare acetdent oCour Tr Specified period ') = P(vsa) =1-PU%

You might also like