Scribd Logo
Upload

Welcome to Scribd!

  • FALLSEM2020-21 MAT2001 ETH VL2020210106214 Reference Material I 31-Aug-2020 MODULE 4 MAT2001-SE Materials - Smart Board - Module 4 PDF

    Uploaded by

    kshitiz college
    10 views52 pages

    Original Title

    FALLSEM2020-21_MAT2001_ETH_VL2020210106214_Reference_Material_I_31-Aug-2020_MODULE_4____MAT2001-SE_Materials_-_Smart_Board_-_Module_4 (1).pdf

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document

    Copyright:

    © All Rights Reserved
    Download as PDF or read online from Scribd
    Flag for inappropriate content
    10 views52 pages

    FALLSEM2020-21 MAT2001 ETH VL2020210106214 Reference Material I 31-Aug-2020 MODULE 4 MAT2001-SE Materials - Smart Board - Module 4 PDF

    Uploaded by

    kshitiz college

    Copyright:

    © All Rights Reserved
    Download as PDF or read online from Scribd
    Flag for inappropriate content
    of 52
    MAT2001 Statistics for Engineers Module 4 Probability Distributions Syllabus ity Distributions: ution - Gamma Special Probability Distributions Discrete Probability Distributions 1, Binomial Distribution 2. Poisson Distribution Continuous Probability Distributions 1, Normal Distribution 2. Exponential Distribution 3. Gamma Distribution 4, Weibull Distribution Binomial Distribution Definition: Let A be some event associated with a random experiment £, such that P(A) = p and P(A)'= 1 —p =q. Assuming that p remains the same for all repetitions, if we consider n independent repetitions (or trials) of E and if the random variable (RV) X denotes the number of times the event A has occurred, then X is called a binomial random variable with parameters n and p ot we say that X follows a binomial distribution with parameters n and p, or symbolically B(n, p). Obviously the possible values that X.can take, are 0, 1, 2, .... 7. Probability Mass Function of the Binomial Distribution P(X=r) =n, p'q"~"; r=0,1,2,...,m where p+ q=1 @) Binomial distribution is a legitimate probability distribution since x PX=1) = z aCe r=0 vse =@q+pfat [Bimid Dap Kee BGP] ARV Xfi &D Re tek OP Xn dad Bie Peer n6at)mig Fy X wna & on of fee Crpine Xa uas regs a a “4 ey) Vl : Prbably of ecm i tity yf file > pysy Gays}. i) Fo bof > ferew i » kam VY v=o. = b= air Mean and Variance of the Binomial Distribution E(X)=> xp, = Erne eer cy : n! ren? maa et a a. CV) et ee -er- w 2 Gonna =mp 3) (n-1)G,_y- pi-!-g@-9--) ret =np (q+ py" =np Q) Bar) = o=d, Pp, => (- +n ' r=0 (n- a? =n(n—-1)p? DY (n-2)C,_,p'-2.q""" + mp, { a2 [by (1) and(2)} =n(n—1) p?* (q+p)"*+np =n(n-1) p+ np Var(X) = E (X°)— {E 00)? =n(n-1) p> +np—n’p? =np (1—p) ="pq Poisson Distribution Definition: If X is a discrete RV that can assume the values 0, 1, 2, ..., such that its probability mass function is given by a nw rt : then X is said to follow a Poisson distribution with parameter A or symbolically X is said to follow P(A). (Note: Poisson distribution is a legitimate probability distribution, since Sd pe r=0 Mean and Variance of the Poisson Distribution qd) estén Q) = tor pene = Fay r lee 2 eo [by (1) and 2)) =Perer+ davon Var(X) = EQ) — {E00}? =V+A-V aA Poisson Distribution as Limiting Form of Binomial Distribution Poisson distribution is a limiting case of binomial distribution under the follow- ing conditions: (i)_n, the number of trials is indefinitely large, i.e.,n —> oe. (ii) p, the constant probability of success in each trial is very small, i.e., po. _ . . x x ‘ a (iii) np (© A) is finite or p = a and g=1- = where A is a positive real number. Note: if X is the Poisson RV E(X) = lim (np) =A a+ apoa and Var(X)= lim (mpq)= lim [A(1 ~p)] =A. p70 po npaa Example: Out of 800 families with 4 children each, how many families would be expected to have (i) 2 boys and 2 girls, (fi) at least 1 boy, (iii) at most 2 girls and (iv) children of both sexes. Assume equal probabilities for boys and girls. Lak X vepreeath ths No af L, “UA 23 Kay — Goby ?X>dR io *@). "4 ke p= pal why of ay 8G,}) Pale Hy C8 Gat as) POr=a) =4¢ ab gs sotation: Ne tte ing Cori PE eco Example: An irregular 6-faced die is such that the probability that it gives 3 even numbers in 5 throws is twice the probability that it gives 2even numbers in 5 throws. How many sets of exactly 5 trials can be expected to give no even number out of 2500 sets? he Xa 9193 A= 9342 —> BO,E) Qo - bevy P= 3) = axP=g)% Ee Pappa kn SPO = AEG Pgep TPs? Keys? % ) PCxco)= HG. fP gf =?) VP Orca) = aanx 2. ipo Re ra A — Ww Solution: Let the probability of getting an even number with the unfair die be Pp. Let X denote the number of even numbers obtained in 5 trials (throws). Given: P(X = 3) =2x P(X = 2) i 5C3 pq? =2x SC, pq? p=2q =21—p) 3p =2orp=2 = andg= 3 anda vie Now P(getting no even number) = P(X=0) 1y 1 =5Cy: p’-gi = (3) =— 5Cy p g 3 243 «'. Number of sets having no success (even number) out of N sets =N x P(X%=0) 1 “. Required ber of sets = 2500 x —— equired number of set oa = 10, nearly Example: Two dice are thrown 120 times. Find the average number of times in which the number on the first dice exceeds the number on the second dice. Sehz BCniP) n=lau p=? S=fo,0, aa)..-,009, @)), Ga). o, 6, 8a] (Sls s¢ Brake Ga-{20,0,6,a), or =) Cn )h Ps Ael iy we Arey = £@ = nabs as Solution: The number on the first dice exceeds that on the second dic, in the following combinations: 2 D: GB, D, G, 25 4 D, G 2) 4, 3s. G, Ds G, 2 5, 3); GS, 45 (6, D, 6, 2), 6, 3), (6, 4), (6, 5), where the numbers in the parentheses represent the numbers in the first and sec- ond dice respectively. P(success) = P(no. in the first die exceeds the no. in the second die) =15 5 = a This probability remains the same in all the throws that are independent. If X is the- to. of successes, then X follows a binomial distribution with parameters n (= 120) and p= %): EO =np = 120 x > = 50 Example: Fit a binomial distribution for the following data: = 0 1 2 3 4 @ ° ie 626 C7 Ni aw Total 80 Solution: Fitting a binomial distribution means assuming that the given distribution is approximately binomial and hence finding the probability mass function and then finding the theoretical frequencies. To find the binomial frequency distribution N(q + p)", which fits the given data, we require N, n and p. We assume N = total frequency = 80 and n= no. of trials = 6 from the given data. ‘To find, we compute the mean ofthe given frequency distribution and equate it to-np (mean of the binomial distribution). x: 0 1 2 3 455 fo 5 1 2 12 7° 6 fe 0 18 56 36 28 30 zo LSE, 192 ze ara 6 Total 4 80 24 192 np=24 or 6p =24 p=04andg=06 Ifthe given distribution is netty binomial the tioreticat frequencies are given by the successive terms in the expansion of 800.6 + 0.4)°. Thus we get, =o ft 2 $s 4 5 6 Theoretical f: 3.73 14.93 24.88 22.12 11.06 295 0.33 Converting these values into whole nurnbers consistent with the condition that the total frequency is 80, the corresponding binomial frequency distribution is as follows: a Oo 1 og 8 es 6 fo 4 15 2 2 MU 3 0 8 Example: The number of monthly breakdowns of a computer is « RV having a Poisson distribution with mean equal to 1.8, Find the probability that this computer will function for a month (@) without a breakdown, (b) with only one breakdown and (©) with atleast one breakdown. Shy WX = 0,493... X~ X= ', ©) 9 eran sAety BP Cray) eta = “fig Yl Prey) e Seay | ? Y=9,\,9- oe Solution: Let X denote the number of breakdowns of the computer in a month. X follows a Poisson distribution with mean (parameter) A = 1.8. “ P{X=r} rl (a) P(X 50) = e!* = 0.1653 (b) P(X = 1) = e* (1.8) = 0.2975 (©) P(X 21) = 1- P(X =0) = 0.8347 Example: Fit a Poisson distribution for the following distribution: x: 0 1 2 3 4 f: 142 156 69 27 5 5 Total 1 400 Solution: Fitting a Poisson distribution fora given distribution means assuming that the given distribution is approximately Poisson and hence finding the probability ‘mass function and then finding the theoretical frequencies. To find the probability mass function Pix=n) of the approximate Poisson distribution, we require A, which is the mean of the Poisson distribution. ‘We find the mean of the given distribution and assume it as 2. x: 0 1 2 3 4 $ Tot Pero) oe er fe: 0 156 138 81 20 5 400 fx. 300 ; f 400 ‘The theoretical frequencies are given by Neha where N= 400, obtained from the given distribution, ‘Thus, we get = 0 1 23 64 6s Theoretical ff 147.15 147.15 73.58 24.53 613 1.23 ‘The theoretical frequencies for x = 6,7, 8, ... are very small and hence neglected. Converting the theoretical frequencies into whole numbers consistent with the ‘condition that the total frequency = 400, we get the following Poisson frequency distribution which fits the given distribution: x 0 1 2 3 4 5 Theoretical f 147 147-7825. Exercise: It is known that the probability of an item produced by a certain machine will be defective is 0.05. If the produced items are sent to the market in packets of 20, find the number of packets containing at least, exactly and at most 2 defective items in a consignment of 1000 packets using (i) binomial distribution and (ii) Poisson approximation to binomial distribution. Exercise: . Ifa fair coin is tossed at random 5 independent times, find the conditional probability of 5 heads relative to the hypothesis that there are at least 4 heads. Exercise: -A car hire firm has 2 cars which it hires out day by day. The number of demands for a car on each day follows a Poisson distribution with mean 1.5. Calculate the proportion of days on which (i) neither car is used and (ii) some demand is not fulfilled. Exponential Distribution EDC ») Definitions: A continuous RV X is said to follow an exponential distribution or negative exponential distribution with parameter A> 0, if its probability density function is given by aan 220 pdf = roy={ 7 aa We note that j f@) dx= j A e** dx = 1 and hence f(x) is a legitimate density function. Fe _polf: Tos oC now) ® irs) Ih= Jodny Meey = 4 Mean and Variance of the Exponential Distribution E(X) = Mean of the exponential distribution = p= 2 2 CO) = m= 3 &. Var(X) = E(X*) - (E00) Gamma Function epay Pee ide rena fe xldx, 10, and when n = integer > 0, we have ['(n) = (n — 1)! Beta Function . The gamma function is related to the beta function, B(m,n), as follows: B(m.n)= fx \— x) de T(m)T(n) Bm.) = Bm) = Fy Table for Gamma Function 2 Tm) nn) hn) 100 100000 125 0.90640 150 o.aaez3 tor ogo433 | 126 «0.90840 151 088650 to2 09864 127 0.90250 152 0.88704 103 gees | 128 © 0.90072 «159 0.88767 tot o.97e44 129 0.80008 154 o.88818 105 097350 190 0.80747 155 0.88087 10s 096874 131 0.89600 158 O.88068, 107 ages | 132 0.80464 157 20040 jos ogse7a 133 0.89038 158 ogov4e too ogssas | 184 0.80222 150 ogon4s TO 095135 | 195 O80TTS 160 0.80052 tm oge7g 196 0.80018 © 161 ogoaes 112 ogasso 137 0.88031 162000502 113 093003 198 0.88854 163 0.80726 14 093642 139 0.88785 L64 0.80868, 118 0.93004 140 0.88726 165 0.00012 116 0.92000 «141 0.88678 © 168 .90167 117 0.92670 «142 (0.88636 © 1.67 0.90330 118 092573 143 0.88608 168 0.90500 119 0.92088 © 144 0.88580 169 0.90678 120 ostei7 145 0.88565 170 0.90868 121 o9tss3 148 0.88560 171 0.91057 122 oststt 147 0.88563 172 0.91258 123° osto7s 148088575 173.9146 124 0.90852 149 0.88595 178 ©9689 175 176 ww 178 179 1180 181 192 183 184 185 196 187 188 189 190 191 192 193 194 195 196 197 198 199 2.00 Tn) 0.91906 0.92137 0.92376 0.92623, 0.92877 0.93138 0.93408 0.93685 0.93969 0.94261 0.94561, 0.94869 0.95184 0.95507 0.95838 0.96177 0.96523, 0.96878 0.97240 0.97610 0.97988 0.98374 0.98768 0.99171 0.99581 1100000 General Gamma or Erlang Distribution Definition: A continuous RV X is said to follow an Erlang distribution or General Gamma distribution with parameters A > 0 A>Oandk> |k>0, if its probability density function is given by EB Ck x CK, d) 2! Ax bd} = p= Ta for x20 . otherwise We note that | f(s) dx= Af Mt dy 0 1) 9 tk} ons 1 9 : == e~ dt, [on putting A.x = 1) © : =1 Hence f (x) is a legitimate density function. Mean and Variance of the General Gamma or Erlang Distribution os Mean = E(X) = +) k x 7 ® 2 Var(X) = E(X*) TEGO? eG) A Fe tkik+ 1)-B) = IPl> Gamma Distribution & D Cx) 1. When A = 1, the Erlang distribution is talled Gamma distribution or 7 Gamma distribution with parameter k whose density function is f(x) = kt 5 > ie of! PS x 20; k > 0. 2. When k = 1, the Erlang distribution reduces to the exponential distribution with parameter 2 > 0. 3. Sometimes, the Erlang distribution itself is called Gamma distribution. Mean and Variance of the Gamma Distribution Mean = FO) = & Ver Od & Weibull Distribution \)(oly bs) Definition: A continuous RV X is said to follow a Weibull distribution with parameters c > 0, if the RV ¥ = o:X ? follows the exponential distribution with density function Fy) = e”, y > 0. Density Function of the Weibull Distribution Since ¥ = a- X°, we have y= a: x?. By the transformation rule, derived in chapter 3, we have fy(x) = fy(») ae 7 7 where f(x) and fy(y) are the density functions of X and ¥ respectively. fx) = €% BxP-* pd: =apx’'e®x>0 [+ y>0) When B wrameter Ot , Weibull distribution reduces to the exponential distribution with Mean and Variance of the Weibull Distribution 7 (E+) Mean = EO) = _ a Var(X) = E(X*) — {E(X)} el Normal (Gaussian) Distribution NOY Definition: A continuous RV X is said to follow a normal distribution or Gaussian distribution with parameters u and 0, if its probability density func- tion is given by ae -&-wrRe, _ 4, e Pal = f@=*5 fox ¢ ; 0 Symbolically ‘X follows N (44, 0)’. Sometimes it is also given as N (44, 07). Note: f(x) is a legitimate density function, as = 1c [ fe x= re | ¢ cole Ge ap che J €? oN2 dt, (co rsing 24) =~ W928 ay Standard Normal Distribution The normal distribution N (0, 1) is called the standardised or simply the standard normal distribution, whose density function is given by 1 [o. e This is obtained by putting # = 0 and o= I and by changing x and frespec- tay nto and 9. has atbon Mo) and fz = Fen we cn prove that Z has distribution N (0, 1). —we Aopon $e) = fae; — Se F400) © 5 OPPenite PGs -), G) dans 7 i = - M8) Zag = Fade Pa, Solution: Let X denote the mileage obtained with the tire 1 f@= 40,000 e400 50 1 67 7140,000 gy 20,000 40,000 (i) P(X 2 20,000) = eT =e = 0.6065 ; “| 1 140,000 ii) P(X < 30,000) = —er a& a PC : J 40,000 ° . = [- eo oe ~= 1-6°% = 0.5270 Exercise: ‘The time (in hours) required to repair a machine is exponentially distributed with parameter A= 1/2 (a) What is the probability that the repair time exceeds 2 h (b) What is the conditional probability that a repair takes at least 10h given that its duration exceeds Lh? Nt: : KN EO, wk A=), % PCx> 9) P O21 bot PRH10 Coie, x>9) ~Y0e9) o Example: Ina certain city, the daily consumption of electric power in millions of kilowatt- hours can be treated as a RV having an Erlang distribution with parameters A= ; and k = 3. If the power plant of this city has a daily capacity of 12 millions kilowatt-hours, what is the probability that this power supply will be inadequate on any given day. Say, Xw &O,b) POr>ia) Solution: Let X represent the daily consumption of electric power (in millions of kilo- watt-hours). Then the density function of X is given as 1 3 sox G) eo? x>0 P (the power supply is inadequate) t =P(X>12)=f fix) dx (+ The daily capacity is only 12) — 16 4 at¢ 16 (288 + 96 + 16) = 25 e* = 0.0625 Example: If the life X (in years) of a certain type of car has a Weibull distribution with the parameter B= 2, find the value of the parameter ar, given that probability that the life of the car exceeds 5 years ise~°**. For these values of aand f, find the mean and variance of X. Solution: ‘The density function of Xs given by $@)=2axe**,x>0 (B22) eee fee Given that 4 “35 For the Weibull distribution with parameters rand BE = a°¥#|( +1 satan (55)*{() oo) 12 =1xt{(5) a5. Exercise: Each of the 6 tubes of a radio set has a life length (in years) which may be considered as a RV that follows a Weibull distribution with parameters a = 25 and f= 2. If these tubes function independently of one another, what is the prob- ability that no tube will have to be replaced during the first 2 months of service? Example: The marks obtained by a number of students in a certain subject are approxi- mately normally distributed with mean 65 and Standard deviation 5. If 3 students are’selected at random from this group, what is the probability that at least | of them would have scored above 75? Solution: If X represents the marks obtained by the students, X follows the distribution NGS, 5). P(a student scores above 75) = PK> 15) =P (BES < XS 75) =0.05 ie. p(-w< At Boe ) =0:10ana o oC p( T= XH Fy 45

    You might also like