Random Variable & Random Process Dedermmistic Mekuve> knocs the Te Sut cohidw is pig ts Wappesy before penforwaiing enpentovent Raheny eapeatemenct —> Devt-t Kove abst “the VeSHHt. Ora crane of 9 the enpemionre ans igmknorn before purPrmiag “Khe Saperiomneand eg ke ssimy of a Cain, Reltsna of dice Bante belaviour of — erpermertant ts enpressed bys Penloalsly ank statistics. Randers Variable A cantons Variable “X cao be emnsidined “be be a —funckion = oak APS al evewwke of he Sample. Space Lear — Poles on the cred vet's, Randes capermant 3 Tessieng of A een ter Ke A aandtom Variable Q Crrcoomnes = head H) so x= bal CH) Head “Tail ~ Mise ave gawidew Variable Frobsbiltty densty Sunetion F6e) FEO = P&=20 Randeny eaperiment 1s aondem © Oxkure ~ but Randews variates are. always Fixed, ‘Scanned with CamScanner9 PG==<05 P (x=T)=05 Yo Ya >. a T Kans Rv XK Poababiery of event of particles ardom Capentwent is esewed ko as POF 4 Types of Random Variable based on R-E 1 Corlvmoke Ctandans Vntalle CRY) Once er ty CeO 8 a eckure eg warasaring Kewoper eck / harnidely 6 a CHey a. Diserete Farkemn Vartatle GRY) of @ con eg we ssivy 3. maxed BY of CRY ADRV Rv's are Gaantinuens and Cows bina tien Some of he Sows of therm ave disevere, RE > Rolling of dice DRvV POF x Pod 1 4 2 the 3 1/6 ‘Scanned with CamScanner4 th 1/e GC the FGI =2 §6-)+ tb §G-dt +2 56-9 G a 4 a on k=l POF 460 will aluays be wo the hes of Urpalse fivetion hy DRY Pacbabilety distoibectio farction FEI Fkl= P(x £2q “FEA is prnbdilty of ay of te omtcome of RE FRI ts som ef all Pavbabilties of the evens Upte the presemt event, FO = e& «i= Ye FQ) = Per) =P &-D+ P&=2) = 2% c@ = gee L FED, A - —- - : ca a3 4 G FKI 7B a MG-8) + TE X is Dey, un distin -Pvetion [2 rtame of Step fonction, Sete 6 5 ‘Scanned with CamScanner! ! | j ( { Pavpertion of Probabibety, den srty function 4 04 £OD 424 ¥ 7 AG) olicstes probabiley of the event occuring Oo a oan dom eopeniment 2 = 2 f" 4ooda=41 6) FH f6d=4 ca =e es St: ja. F@d= [ feodx worse fea — 60 eae f= 4 $65 @ dee hn Seer Ocean a ff fGodx = FG FN fr bey Det ORvecry ‘Scanned with CamScanner Be spemeres elim ieee oe ke| Properties of Probably diatbtin Fencton +. FES) = F@e)= 1 le o4 Fee | Fepee- FAD) trae Se ctenserg oF Panchen — gvath alongs denrasing Bet We stoibetien er bat Mave Cou stant Bes" can have WY daw sry —fumetion P(r 2 LX 2x2) = F@2)— FGi) (6 Fa =Fed i Prebalilety dasrbection —Rnchor 15 cewetineus + onfinte stroak from Ke a cohnne OO Be oe ee ne cry) 4 noremnent iy. Pan= 4 F&O de ts on -Rinrction is also allel as (lety diswibuctos Iba! iia dteeribuction —Lmwehos Ene), Cusack ahve Qi, A aandoro Vartable K ds defimed ly CDF as | | { F@) =0 ; X40 2 ;,o4xet 2 =k ; X21 @ — Fiok dhe welue of Kk © Is ths aavlom Variable closer ete , Coacttvnrans a fined . ‘Scanned with CamScanner a < BABPBPIOOC oO i)@ Y P (4 2x4) @ p a cue G volute the pobobily dhot % exceeds 2 F dodt rrenpret vs at n=1 FOR, @ &=6)=1L 3 F(x-0) =k =4 > k=1 . F fe gph () The FD 1s ceormmunte Br 8221, X15 CRY ak a= 4, FD is dUsueke, RIS DRY ok Ket FED ts Seettwme, X is SRV a] > > > > 3 > 3 3 3 3 > 3 S i) S = = = S Neste > x 1s MEV Whenever dealing. ity MRv, use the prprter sO PG exzed= FM FY) ef DRv = el 4s 2 a a Z ttl, = os 2 se = al > 2 a x 3 S POdx= total aver = Ixbpos=t = a4 go eS 2 Meche Torte =a = Se Scanned with CamScanner! PC4 4x41) = f teodee 2 ' he @ p G eae) = gQy— F(4)— Pee=i) tyt 2 2 deol wre PG enci= AMG) x © P Grd) =1— PRED = !-F@=2) = J-l=0 6R a Finns cust, Panchen Wo prbabilty fr 222 Uo AGI gtarh > PGr2) =0 de ns Consider a. andons Vanalle X% cut —Yxl FED = 0 e Ix 7am Psrtsonw Food @® FRI ) Rdlechanshp beteeen “a 24 @) PLazxeg) Aus @) % is crv — bbl Ta-eane fo Sen 2 00k en! ‘Scanned with CamScanner VTTTERRPRPRRDD 4aba Fey “{s e ae ; x70 ozo Ivo cases Xso a bo Fikl= bax f #60dn= fae dam Ss”, mes =o 6 Q>o — Exe oy OK a Scanned with CamScanner| —2b | @ PCa cxe2l = Fa FG) = 24-4 @_/ha_ as! b b tbe “a —b -ab e-e@ oa P(iexcd= ja = Pe Gee oe) C Condttiond Distribtion Z Densrly function Conditions| Distibettos fancten : Let A. anki B avers tuo” events am Weak {x 2} for Tretleaies Perction. of %, eho ¢ ia darnt-d as Fltla] amdc ry Graydern variable X If a is then the Cordrtoron| he ener B'S Keven 7 ts defied a8 - F (eta) - PE emlel- Rezod . rP® e a Condon) ensrly fare\on f.Glel= A rGil Note nt Except the heppening of exert “B, all the propertes one Khe Same as fer Prrloabilety distoibueue fun ctons and — Probably demsrty functions. Pa] = Pio dl PPPP PRP PD Pe] c p[2]= Pos) e EJ - £a08 x ‘Scanned with CamScanner°F] = rl] m0 Pte] Payels ono r ERD = tig) ee Pla} &%. Ranhoms Variable “Yo ts dtobsibuted accardivg -bo toe, Fumes fey = Tei ed] Determine WO Cunileiwe beokees os of © ‘& P{k> w| rec [es ice] uv 32 f[_x 3 =r 2 7@ a FI L : avea of A alall be 1 3 D> Najltude = = ai i ? x 3 > Tso Cases 3 2tLo ox Feo [2 4x0 a FRI=f Sedx rx; of xeL a 0 2 eo ~ a ~ St Gaddn= f Gadde = Zax-(4-/ 4 3 = as rxtb ; xLo ya p Scanned with CamScannerx70 xX o © F&I= f[ fed-= - Gado t J Cou) dx = Lexie (- 2c +¢ = 20) = poh j ; x70 Poe) = 1- rkeng = 1- Fg = 1-(-4+4 =) 5 2 "ee | = Pron x4) _ PeCLxL%) zh PGAT P&e th) Tar) SOY specs ps cae. F(h) PEexey,) = rozxep)e hb ‘ @ +F 7 ZS | or Kr A xr) ~ PGex= x=2X) « PGR) Pe) 7 To find ove “this, Stor ctang mm dice bens e ee! = f (rx a x>/,) on me ois EEO) RP Ghenerd & POM eeu = FR)- FU) . & Ve & ‘Scanned with CamScanner+ r(x) = fe _ 30 ae dc ~ = # 69 ox “Ye Opera-hors ob a Swgle crandow) Vortable. te Expectanon [mean Value of a RV [Ferst order Woment E® = fo KFA Eed) oo EW = Bi Xtoo xv) PenpuloMotRnen oy @- E Eowstad] = constant ® €& ka =k 6) Mien eils Sacctmnck <® TF 91 ah 9,G) are tro —Renctoos of a orvadors, Nartable x, then E ACo+ 9.4] = ED@]+ €G.c) @ E (yxtkd = keke ke GUE EPLE FSFE SPCSP SPSS AOM 32. Flyst order Centra Moment of a anders Varial{e. — Scanned with CamScannerPan pemlteo of Variance @ (© 7 © va lkyxte) = Ky Var CE] VV_UVUVUUKDTKUKOUUVHUHUUUUUYY uu ysSUY R w a a a4 rt Nar (Constant) =o Nar (kX) =k var od 4 statistical pavamcters * Mean | First order moment 2 Fisk avder Certral moment 2 Secon order amnowennt | MSV © Seek ovder Cansyd ronment | Vanance Sevti sical Avumges Meow Ef] gwes De compomeast value or Arerege 44) (eas) = Dc power Meas squave Vdue E(x?) = -to-tal power Nariawce = Msv— Gear)> = bot power— De power = AC power Ghandad deviacion = [vananve. = You = ms velue of AL Som posrcovet Kis ORV carly prrbabilety Mass —furetes as gnen bo the Exe below. EFebisbibea] ‘Scanned with CamScannerFuodk @ eI ® © (2x+3) ©) E(x @) e(@x+04} Ans @ aad x x f@)= E28 by x) #(*5 x8) ~ _ eos gL () ec (2x48) = 2 E643 = —ag42 = t4t 4 © b= 2 xf = tA E PH BS A eG@unM = E (4x rit $x) = 4 EG) + ECT FE@) #x2l yp + 4 (e3 ee = 8-2 ‘Scanned with CamScannera li A Mealdiple Random Vanables “Tarot _Punbelileyy distaibecven fimetien > Canady ko Qanden Variables {x} avk fy} tw we xy Plane: The ordered Parr ot Numbers. {x} is calleh Qaodenm Vector Oo the two chonem Stoel Produc Space oy Jadot Sample Space. yb lak toro events be A=[Xex} anh B=fye ys hers tha Jolact Prvbabibty distatbustors —Purncton by the Jolect Queue { Keo, Yeh is defod as Fd = Ply 2g Yeu} Pooperts of Sewst pistrbetten fiction He = a (,e)=1 2 of F(&y)et my 3. F@&pisas srnonctenie anh bon deer ea siong fametos of bath Ly. Ertan tanreasing or constnns) 4. he sororiginnal distributes —florctions ave gwen by FR) = FG, y¥=0) tnkeall unbue of y tr gwen 3¢ FO) = F&=e,)) Vent PA Vee - - Scanned with CamScanner . and Y ext elements os fee eee secant a ARE AA BAO BAAAAAARAA ah kf ~~ a»5.1 PROBABILITY FUNDAMENTALS 5.1.1 Definitions Sample Space and Event: Consider an experiment whose outcome is not predictable with certainty. Such an experiments called arandom experiment. However, although the outcome of the experiment «will not be known in advance, let us suppose that the set of all possible outcomes is known. This set of all possible outcomes of an experiment is known as the sample space of experiment and is denoted by S. Some examples follow. 1. Ifthe outcome of an experiment consist in the determination of the sex of a newborn child, then § = (g, b} where the outcome g means that the child is a girl and bis the boy. 2. Ifthe outcome of an experiment consist of what comes up on a single dice, then S = {1, 2,3, 4, 5,6}. If the outcome of an experiment is the order of finish in a race among the 7 horses having post positions 1, 2, 3, 4,56, 7; then S = fall 7! permutations of the (1. 2,3, 4,5, 6, 7)} 5, 4, 7) means, for instances, that the number 2 horse comes in first, then the 3. The outcome (2, 3, 1,6, number 3 horse, then the number 1 horse, and so on. Any subset E of the sample space is known as Event. Thal is, an event is a set consisting of some or all of the possible outcomes of the experiment. For example, in the throw of a single dice S=1, 2, 3, 4, 5, 6] and some possible events are E, = (1.2.3) E, = (3.4) E, = (1,4,6}etc. experiment is contained in , then we say that E has occurred. Aways E< 8. Ifthe outcome of the may be effectively used to represent & solve probability Since E & S are sets, theorems of set theory’ problems which are more complicated. Example: If by throwing a dice, the outcome In the child example - (i) If E, = (g]. then E, is the event that the child is a gir Simteny i se tnen tne event that he cid @boy. These ae examples of Simple events Compound avant may consist of more than one outcome. Such as E = 1,3, 5] for an experiment of throwing a dige, We say event has happened ithe dice comes up 1 or 3 or 5 is 3, then events E, and , are said to hare occured Scanned with CamScannerFor any two events E and F of a sample space S, we define the new event E WF to consists of all outcomes that are either in E or in F or in both E and F. That is, the event E WF will occur i either E or F of both occurs. For instances, in the dice example (i if event E = (1, 2) and F = (3, 4) then EUF=(1,2,3, 4). ; That is E UF would be another event consisting of 1 or 2 or 3r 4. The event E WF is called union of event E and the event F. Similarly, for any two events E and F we may also define the new event ENF. called intersection of E and F, to consists of all outcomes that are common to both E and F $ s @ (@) Shaded region EOF (b) Shaded region: EF s KM , (6) Shaded region : E (a) ECF 5.1.2 TypesofEvents 5.1.2.1 Complementary Event The event E° is called complementary event for the event E. It consists of all outcomes not in E, but in S. For example, ina dice throw, if E = (Even nos} = (2, 4, 6) then EC = {Odd nos} = {1, 3.5} 5.1.2.2 Equally Likely Events Two events E and F are equally ikely iff PIE) = pF) For example, E = (1,2,3) F = (45,6) are equally likely, since P(E) = pF) = 1/2, 5.1.2.3 Mutually Exclusive Events Two events E and F are mutually exclusive, it EF = 9 i.e. p(E-F) = 0. nother words, if E occurs. F cannot occur and fF occurs, then E cannot occur (i.e. both cannot occur together). 5.1.2.4 Collectively Exhaustive Events Two events E and F are collectively exhaustive, i E UF = S.ie. together E and F include all possible outcomes, p(EUF) = p(S) = 1 Scanned with CamScanner5.1.2.5 Independent Events ‘Jwo events E and F are independent iff PIENF) = p(E)*p(F) Also p(E | F) = p(E)and p(F | &) = p(F) Whenever E and F are independent. i.e. when two events E and F are independent, the conditional probability becomes same as marginal probability. i.e. probability E is not affected by whether F has happened or not, and viceversa i. 5.1.3. DeMorgan’sLaw » GS-88 (a8) «Se Example: (E, VE) = ESnES (E, OE) = E,CUE,S Note that E,° 9 E,° is the event neither E, nor E>. E, UE, is the event either E, or E, (or both). Demorgan’s law is often used to find the probability of neither E, nor E,, \€. PEP ME,S) = pl(E, VE,)") = 1-plE, VEY. es 5.1.4 Approaches to Probabil ity There are 2 approaches to quantifying probability of an Event 1. Classical Approach: when E is independent of F, then F is also independent of PIE) = a8) \.e. the ratio of number of ways an event can happen to the numb mace, is the probability of the event. Classical approach assum. ikely. er of Ways sample space can es that all outcomes are equally ‘Scanned with CamScanner5.2.2 ArithmeticMean 5.2.2.1. Arithmatic Mean for Raw Data Ex The formula for calculating the arithmetic mean for raw data is: X= ~~ X - arithmetic mean x. - refers to the value of an observation n_- number of observations. ILLUSTRATIVE EXAMPLES Example: The number of visits made by ten mothers to a clinic were; 8655745974 Calculate the average number of visits. Solution: D ‘otal of all these numbers of visits, that is the total number of visits made by all mothers. B+6454+54+74+44+5494+74+4=60 Number of mothersn = 10 Ix _ 60 n 10 6 The formula for the arithmetic mean calculated from a frequency distribution has to be amended to include the frequency. It becomes Z(t) _ _ 3K nant ILLUSTRATIVE EXAMPLES Example: To show how we can calculate the arithmetic mean of a grouped frequency distribution, there is a example of weights of 75 pigs. : Scanned with CamScannerThe classes and frequencies are given in following table: Weight (kg) Midpoint of class | Number of pigs | fx x f(frequency) O& under 20 15, 1 15 20 & under 30 25 7 175 30 & under 40 35 8 280 408 under 40 45 7 495) 50 & under 60 55 19 1045 60.& under 70 65 10 50 708 under 80 75 7 525 808 under 90, 85 5 425, 90 & under 100, 95 4 0 700 & under 110 105 3 215 Total 75 4305 Solution: With such a frequency distribution we have a range of values of the variable comprising each group. As our values for xin the formula for the arithmetic mean we use the midpoints of the classes. =(fx) _ 4305 rh” 76 In this case x= =57.4kg. 5.2.3 Median Arithmetic mean is the central value of the distribution in the sense that positive and negative deviations from the arithmetic mean balance each other. Itis a quantitative average On the other hand, median is the central value of the distribution in the sense that the number of values less than the median is equal to the number of values greater than the median. So, median is positional average. Median is the central value in a sense different from the arithmetic mean. In case of the arithmetic mean its the “numerical magnitude” of the deviations that balances. But, for the median itis the ‘number of values greater than the median which balances against the number of values of less than the median. 5.2.3.1 Median for Raw Data In general, if we have n values of x, they can be arranged in ascending order as: HSA My.— -th value However, ifn is even, we have two middle points ‘h ® (3) value +(2 +1) value Median = ILLUSTRATIVE EXAMPLES, Example: The heights (in cm) of six students in class are 160, 157, 156, 161, 159, 162. What is median’ height? Scanned with CamScannerSolution: Arranging the heights in ascending order 156, 157, 159, 160, 161, 162 ‘Two middle most values are the 3" and 4", Median = F(1s9+ 460) = 159.5 5.2.3.2, Median for Grouped Data on (N42)" 1, Identify the median class which contains the middle observation (2) observation) This can be done by observing the first class in which the cumulation frequency is equal to or more than ae - Here, N = Ef = total number of observations. 2. Calculate Median as follows: N+1 (F +1) Median = L+ xh hy Where, Lower limit of median class Total number of data items = EF Cumulative frequency of the class immediately preceding the median class Frequency of median class width of median class ILLUSTRATIVE EXAMPLES Example: Consider the following table giving the marks obtained by students in an exam MarkRange | { NoofStudents | Cumulative Frequency 0-20 2 2 20-40 3 5 40-60 10 15 60-80 15 30 80-100 20 50 Solution: Here, ot = 255 The class 60-€0 is the median class since cumulative frequency is 30 >25.5 Median = 82+[255~(15+1)] ae ea x 20 = 69.66 ~ 69.7 -. Median marks of the class is approximately 69.7, i.e. (at least) half the studer ants ¢ Got less than 89.7 and (almost) halt got more than 69.7 marks Scanned with CamScanner52.4 Mode Mode is defined as the value of the variable which occurs most frequently. 52.41 Mode for Raw Data in raw data, the most frequently occuring observation is the mode. That is data with highest frequency ismode. If there is more than one data with highest frequency, then each of them is a mode. Thus we have Unimodal (single mode), Bimodal (two modes) and Trimodal (three modes) data sets. ILLUSTRATIVE EXAMPLES Example: Find the mode of the data set: 50, 50, 70, 50, 50, 70, 60. Solution: 1. Arrange in ascending order: 50, 50, 50, 50, 60, 70, 70 2. Make a discrete data frequency table: Data | Frequency 50 4 60 1 70 2 Since, 50 is the data with maximum frequency, mode is 50. This is a unimodal data set. 5.2.4.2 Mode for Grouped Data Mode is that value of x for which the frequency is maximum. Ifthe values of x are grouped into the classes (such that they are uniformly distributed within any class) and we have a frequency distribution then: 1. Identity the class which has the largest frequency (modal class) 2. Calculate the mode as b-f Mode = La 5 xh Where, L = Lower limit of the modal class Largest frequency (frequency of Modal Class) Frequency in the class preceding the modal class Frequency in the class next to the modal class h = Width of the modal class ILLUSTRATIVE EXAMPLES Example: Data relating tothe height of 252 schoo! students are given in the following frequency distribution Calculate the modal height. Heigh (in feel) [Number of students 30-35 12 35-40 7 40-45 79 45-50 182 50-55 65 55-60 Total 352 Scanned with CamScanner