You are on page 1of 9
(C-DRN-N-UUBA yet STATISTICS Paper—I Praite wra: dr we wae He ; 250 ne Allowed : Three Hours Maximum Marks : 250 wera & fire fare ght grr weit & sere BF & yd Prefer sete argeer ot ery ae wat ae wor Boat a rest F Ponti & oer fed ote aft dat FT wr Br) ater at ga wis weal @ aoe 28 81 yor wen 1ate 5 arart & war aet yeat Fa ged a wae =e fy got gee Oe wre a etn ew rer rer Re gate wera Foxe sat wert Re me a1 wav & aoe al marr 7 RA art ay Rrray arte anak vam-va F fa a 2 a Fe OTH RIE TH OTH META. (Hee) ART PTR ve ifr Prise wart 7 frat ara alee) afer Arar # silat ara ema me gat oe ae ae TET Pith a arava Bh, at ara stag ar was a, een orad Pree firey wa an aftattr 7 &, ada aur wecracht weft wae sraf Fo wyer #1 grat & gerd ab nora wager a ome wearer al Ba ver @ oO A TT HH We ae TIC SIA: fear mar By geegRaeT Foe eT BT FS TW Gee ae Hee ower ara wees a8 |ESTION PAPI ic. Please read each of the following instructions carefully before attempting questions ‘There are EIGHT questions divided in Two Sections and printed both in HINDI and in ENGLISH. Candidate has to attempt FIVE questions in all. Question Nos. 1 and 5 are compulsory and out of he remaining, THREE are to be attempted choosing ot least ONE from each section. The number of marks carried by a question/part is indicated against it “Answers must be written in the medium authorized in the Admission Certificate which must be stated clearly ‘an the cover of this Question-cum-Answer (QCA) Booklet in the space provided. No marks will be given {for answers written in a medium other than the authorized one ‘Assume suitable data, if considered necessary. and indicate the same clearly. Unless and otherwise indicated, symbols and notations carry their usual standard meaning. “Autempis of questions shall be counted in chronological order. Unless struck off. attempt of a question shalt ‘he counted even if attempted partly. Any page or portion of the page left blank in the answer book must be clearly struck off. CDRS LLABA Q 1@) Q. 1b) Q 16) Qi aH SECTION—A aft ual Ask B& fig, P(A)> 0 3 P(B)> OM, a zafex PR P(A| B)> P(A), aft atx Baa aff PCB | A) > P(B). BN ware, P(A B) < P(A) aR oft Fam ae P(B | A) < P(B). If for the events A and B, P(A) > 0 and P(B) > 0 then show that P(A | B) > P(A), if and only if P(B | A) > P(B). Likewise, P(A | B) < P(A), if and only if P(B | A) < P(B). 10 am am 1,23 3 aghow wr F fe Ey ei ee ae A oer woe fF wa rm se mt aPte wert We eT? ‘Three digits 1, 2 and 3 are written down in random order. What is the probability that at least one digit will occupy its proper place 7 10 aA N(u, 4) 8 we Beit wteRE -5, 0,2, 15H, a ps fire TH 95% favareneT sire wag Construct a 95% confidence interval for 1 in N(j, 4) from the following observed sample : -5, 0, 2, 15. 10 arr chiftre PX, sre xX, wait waTT der (ork ong Gh) aghow ae HY, Pre wT wie rT foasy=t on(-2} x20, 0>0 = 0, 30a WRU, = 0.6 X, + 0.4 X, ae U,=X, +X, Prof ae Bu, a U,* a Arar WH OF fq wate wftete 81 aR h(u,) = ECU, | v,), & cafe PR h(u,) HT FACT U, F wee F ctr eT Let X, and X, be iid, random variables and each has probability density function fo30)=5 on(-2} x20, 0>0 = 0, otherwise. If U, = 0.6 X, + 0.4 X, and U; = X, + X,, decide which one of U, and U, are sufficient statistics for @. If h(u,) = E(U, | u,), then show that it has smaller variance compared to Var(U,). 10 Q Ie) Q a) Q. 20) we wen deme we ate Ae Bowles oe 81 dome F ver F oe wraG, 2014 & wet ® Prefeias sive & a quay as | wart | eect | tt via | aT wieat A det | 22 | 12 18 10 20 18 30 Sore vaas A ukteora 8 Pe Pe ht af A wae A ot oa cleat wT ayo dds ds1i 2121381 we Ree A 5% aria a The ART! (FR 5, gas ~ 12-59) ‘A tourist resort is visited by tourists from many countries. The resort operator has the following data in the month of January, 2014 = ‘Country USA [UK | Canada] Italy | Germany| France| Japan No, of tourists 22 | 12 18 10 20 is | 30 “The resort operator has a hypothesis that the proportion of tourists visiting in the month of January of any year is 2: 1:2: 1:2: 2: 3. Test this hypothesis at 5% level of significance (Given x3, g95 = 12.59). 10 aR ow ughow TCX a safle WAR TT f(x) = 630x41 —h, O< <1, =0, see aa we wa A sift ae ae HX aor ste BATH Peer (y+ 20) 3 Ae aon ae wea geet RR se are oT Prey oft A ot are ‘The probability density function of a random variable X is given by F(x) = 630x4(1 — x)! for0zez Om el wel 220 we pia 2 COPPA eke Q 2%) Q 3(a) Q. 3(b) For a random variable X with probability density function a * 5 forx>0, aL £0652) , otherwise; where 2 2 0 is.an integer, show that P(0—. 1s r aa : GW TeT (die) A 15 ae ern ore 3 feed Prafafia vor ure aa ze : wm: 10020 3 4 5 6 TTT : 0. 1 4 0 4 6 ‘ort gefira & aver a 8, A ote eel & fy Meaiade-fercie varie er Te IE PRAT F Dys. gos = 0.304) A die is rolled 15 times with the following results Face value 1 2 3 4 5 6 Frequency 9: 0 1 4 0 4 6 Use Kolmogoroy-Smirnov statistic to test whether the die is unbiased or not. (Given 1.304) 15 Dis; 005 = wrt fife ow Bh arr A nme ar adem fr ot wer 2 ote ae ue ae ae ard car oer 2 oa we PR rat oa a a aie) wears Peer der a are we a Rr Her Fara oe, oF fae aieer dale sae ue Aq oth HO POX 2) A ara ARE) aa ae wae OF ada A Pere war (ere wertet) oer FR ote caigy A ara SoM Warr By Suppose n items are put on test simultaneously and the test is continued until r items fail. Assuming an exponential failure distribution with mean life time 0, obtain the maximum likelihood estimator for @ and hence estimate P(X 2 1). Also obtain the Fisher information about the parameter 6 and show that the estimator is asymptotically normal. 20 are ARR X~N (Da wT AeA NO, 121 aia Be wear a wer we RY pe fee ae sme wee aie) ek mer ay fee A ura aR Let X ~N (, 1) and the prior distribution of pis N (0, 1). Assuming squared error loss function, obtain the Bayes estimator for u, Also obtain Bayes risk. 1s Q. 3) agen wa S GH aye A ateeT Fo sieve ate dew F afer a Ree Aig) cafey Re aR _X, wr XA wikia A aaron a A sea sh ahr) a weer frie oft mA & 7 CDIN NAA aahe ta ot Q 4a) Q: 4(b) Q 40) Define convergence in probability and convergence in distribution of a sequence of random variables. Show that convergence of X,, to X in probability implies convergence of X, to X in distribution. Is the converse also true ? 15 ATT AA Xp, Xp eareees ,X, Be RATT ATT UO, 6) F sea Uw Mgaw wae BI Hy:0=0,,H, 10% 0, % Tae & fq TATE qa GH GRTATA: waaoH Tee (UMP) eden oer FAT | Let Xj, Xpp wsmeny Xq be @ random sample drawn from a uniform U(0, 8) distribution. Obtain a. UMP test of size of for testing Hy : © = Op against H, : 8 # 0, 20 Preafaferr vomit st fre atfire (i) appt woftea aga wenn (SPRT) wet waferaT GF ata wT tat BL (ii) SPRT# 2log > at PAZ|>0/H}> 0,8 fra fie A 0 N. By fe" (MT) =1 98% Sy= DZ. i Prove the following results : (i) A sequential probability ratio test (SPRT) always terminates with probability one. f(x|H, (ii) For a SPRT with Z=log. LAD such that P.{| Z| > 0| H} > 0, then prove that f(x|Hg) w Ey, €€5% [MOQT™}=1. when Sy =D 4%. 15 X sie yar wife FT Pocer={% (=p), x=0(1) ns PYey) yl) yo =| Lop hy ent tlene (22) er py yeanrt & a& fra fie PX ar] = PLY sa]. Q. Sia) Q 5(b) Q S(e) COP LABA Let the probability function of X and Y be pocer("}p8 =p)" x=00)n; -1 even (2 pt d-phyent stn Prove that P[X 2 1] = PLY sn}. 15 we SECTION—B a Y,, Yq, Y; a wade Rew A geared E(Y,) = By ~ By + By, E(Y,) = By ~ 28>, ECV) = By + By +B, AR VY) = 0%, i= 12,38 fie Bat By Bote B, & Ry apram af smmae ore we) wT are G2a RAfAG are wee Ft aed? ava Te Boge A why Ae Let Y,, Y>, Y, be three independent observations havirig expectations E(Y,) = By ~ By + Bay EY) = By ~ 29, E(Y,) = By +B, + By and V(Y,) = 0? for i= 1, 2,3. Obtain least square estimates of By, B, and B,. Can you obtain unbiased estimate of o? ? Justify your claim. 10 Wen, AC my BARC STE wate A Arete TE A oat my =Ny (i) ate 18 . %~Ny (iy Ds wy = (10, 15}, uy = (10, 25] a(t 2] BT aoe ye ae nectifte gt an sRaaa afr) If’, and x, denote two bivariate normal populations where 1, ~Np (11;,2) and 18 12 12.32 distance between m, and x. 10 wafee sara 10% fay, enfee Re ufemret PT aca aTyRtw views (SRS) A SY SP 3 faftne ard ah oR at orherat eh At & fret Pe wee gr A ane a wear ai ™~N3 (Hy 2s", = (10, 15], uy = [10, 25] and 2+ } ‘Compute the Mahalonobis Q. 5(@) Q 5) Q. 6(a) Q. 6(b) COIN LABA For a population size 10, show that in SRS without replacement the probability of drawing a specified unit at 5" draw is equal to the probability of drawing it at the first draw. 10 art aifie Bos esa A arte 4 eet afte UE ayReage dew se (@RAD,) 21 wai FR orcas, aie 21 Consider a RBD with 4 treatments arranged in 5 blocks. Show that RBD is orthogonal. 10 wR X,, XX), X, ate X, UF ada ste wderr aes aghew afte a, Pas mor ite pote weve arg E gi, M Y=X,-X, +X, -X, +X, wT Fe7 aN AR Let X,, Xp, XX, and X, be independent and identically distributed random vectors with ‘mean vector 1 and covariance matrix E. Find the distribution of Y = X, ~ X, +X; ~X, +X. 10 wr ee X~N, (q, ¥), Tet (1 “0 “| x@ “| yp Xp -axd ret X Ey @ XO 8 afte det a we Ae ae XA = x@ fa ar Let X ~ N, (Hs 2), where 1 1 x Hon (= *| bH=| Q) 2 Xo Hagel Za 22 Obtain the conditional distribution of X" given X®) = x®), 20 wrt aire PR LL way TR 4g WH (GER) F ww shel Rey AE ata a fer at Bi may HR wet 8 ae aye OS) BI mea ae wae HE (TR) H gama we wend (8a) Fi get wea S sre F aren af th (Ss) 200081 way Fie wR (gat) # He F are w ss 82508 ste GP SS 30000 @ a Cia ‘are (ANOVA table) feféra Consider the area under wheat for a sample of 44 clusters selected from 11 different villages. Four clusters were selected from each of the 11 villages and each cluster consists, of 8 consecutive survey numbers (fields). Here sum of squares (SS) due to between villages is 2000, SS due to between clusters within villages is 8250 and Total SS is 30000. Write the ANOVA table. 15 Q. 6(c) Q. Ha) Q 7b) a1) DAI LENBA arn $a we ata af stern ted.) wTRC we TEES, 8 ow aie Pre ‘Afra Pre Afre Ar oRunf Rare, v= b= S,rak= 4a A= 3 wreetl afee OF vga ah den after @areta) ert Construct an LSD of size 5. Delete one column from this LSD. Prove that the resulting design is a symmetrical BIBD with parameters v= b= 5,r=k=4and4=3. 15 dkeg-aremes (AT) & eae mrer arpee ar ale ARIEL eae A AT are TARE mer er aaa sea BI Explain Horvitz-Thomson estimator of the population mean. Show that H-T estimator is unbiased estimator of population mean. Also obtain its variance. 20 Bewr T. A cheats ARC) eas aguas AR fe ww a aTET) cw Re EIT Sea Ny(y, B) 8 ara 3. UH geo witeet Ay ate Ee Prete sare arma Re G(s 3) 7 = uye [j] 1 stern wet fe Teaerly wR A Define Hotelling T?. State-any one of its applications. ‘A random sample of size 3 from a bivariate normal N,(j1, 5) distribution gave following unbiased estimates of and E (i (5, 3) ‘Compute T?-statistic to test the hypothesis H, : 1 = Hy = ( ). 15 7 ae sae sata A grt Fave, 27 aafte agomerh whe Sw GET wes a ara 83 ave a Prat ARC) ah wads ote caeeige cai eritrafhrre Fafa we sada ge ws He Fe eam afte ae Te ae Construct a key block of 27 confounded factorial experiment into a block of size 8 by choosing suitable interactions only. Write all the independent and generalized confounded interactions, Further obtain two or more blocks using key block. 15 Q 8a) Q 8(b) Q 80) a® grt v= 1) =b,r=k=58e A=29 ae UH Agia spl dew aftEerT (BIBD) a ata Boe ae cmae oh we ape sre a Te ARIEL HATE, vi, -t,),i#m u ‘amet #AfaTE | Consider a BIBD with parameters v= 11 = b, r= this design and its non-zero eigen value. Hence obtain 5 and 2 = 2. Obtain matrix of vi, )§#M=L, nog 20 aw air B 200 agat se 100 TSAR A ew veer Ae TAH are wre say Fae ae veer Prevfaftr & arene & : ah wat a we are ote WaT N, ¥ny hy ast 200 40 10 afta 100 30 20 arg Praat wt gears FA ET THT 30-7 Uw aTgROw afte se Fe HET Prat ? aqua wate Hor Fame a eT we FATT 200 boys and 100 girls of a college appeared in an examination. Means and variances of their scores are as given below : Category | No. of Students | Mean Marks Variance N ¥n, oh, Boys 200 40 10 Girls 100 50 20 How will you draw a random sample of size 30 using proportional allocation ? Hence ‘obtain the variance of the estimator of the population mean. 15 aie-anfa area (Y, XB, 0%) FR vara awh ore Xx B=xXY Sea Fo a wa Bm Bh () srtaa FeT A a fre AAC Gi) waft Are RH wheel a geaaT sx eT ra eer FH In the Gauss-Markov set up (Y, XB, ol) a least square estimate is given by a solution of the system : xY i) Justify the above statement. (ii) Establish that the above system of equations is always consistent 15 CORI TABA ke

You might also like