代写STATS 763 - 2022 - Midterm test代做留学生SQL语言程序

STATS 763 - 2022 - Midterm test

6 April 2022, 10:00-11:30NZST

Question 1 [21 marks total]

Wilms’ tumour is a rare childhood cancer of the kidney. Treatment is successful for the majority of patients, but a minority do relapse. An important risk factor for relapse is disease stage (how far it has spread).

The following data on all U.S. paediatric Wilms’ tumour patients between

1980 and 1994, inclusively, were collected:

•  Year: Year of diagnosis, from 1980 to 1994

•  Stage: Disease stage (I [least advanced], II, III, IV [most advance])

•  rel5: Relapse within 5 years (0 [No], 1 [Yes]), hereafter called ”relapse” .

We fit a relative risk model of rel5 on Year*Stage, to capture any secular trend in relapses by disease stage, and obtain the following results:

Call:

glm(formula=  rel5~Year*Stage,  family=binomial(link="log"),  data=wilms)

Coefficients:

Estimate  Std .  Error  z  value  Pr(>|z| )

(Intercept)         52 .59226      38 .93026      1 .351      0 .1767

Year                       -0 .02767        0 .01960    -1 .412      0 .1581

StageII             -107 .15715      52 .12848    -2 .056      0 .0398  *

StageIII               40 .62429      50 .38844      0 .806      0 .4201

StageIV               -29 .17571      53.37873    -0 .547      0 .5847

Year:StageII         0 .05422        0 .02623      2 .067      0 .0387  *

Year:StageIII      -0 .02008       0 .02537    -0 .792      0 .4286

Year:StageIV          0 .01525        0 .02687      0 .568      0 .5703

Selected rows and columns from the estimated variance matrix of the coef- ficient estimates are given below:

(Intercept)       Year       StageIV    Year:StageIV

(Intercept)        1515 .6      -0 .763       -1515 .6         0 .763

Year                         -0 .763    0 .000384          0 .763    -0 .000384

StageIV             -1515 .6        0 .763          2849 .3        -1 .434

Year:StageIV           0 .763  -0 .000384        -1 .434      0 .000722

(a) [12 marks total]

We replace Year in the model by Year1980  <- Year-1980.

i. [6 marks] What are the values of the new estimates for (Intercept), Year1980, StageIV and Year1980:StageIV?

ii. [6 marks] What are the standard errors of the new estimates for Year1980, StageIV and Year1980:StageIV?

(b) [5 marks]

According to the model, what is the estimated relative risk of relapse between a patient at Stage IV in 1990 and a patient at Stage III in 1980?

(c) [4 marks]

According to the model, what is the estimated diference in log-risk of relapse corresponding to an increase in the year of diagnosis of 5 years for a patient in Stage I, and what is the standard error of this estimate?

Question 2 [16 marks total]

We t a GLM by solving the score equation Σin= xTiw i(Yi  - μi) = 0, where xi  is the ith  1 × p covariate vector, μi  = g-1(xiβ) and 0 is the 1 × pvector of all zeros. The GLM involves a dispersion parameter φ > 0.

(a) [4 marks]

Explain why wi  = 1 when the canonical link is used.

(b) [4 marks total]

What is wi  in the following settings?

i. [2  marks]  Variance function V (μ)  = μ2 , μ  ∈ R+  and link function g(μ) = log(μ).

ii. [2 marks]  Poisson(μ) family and identity link.

(c) [4 marks]

How do we usually estimate φ? Write an expression for the estimator.

(d) [4 marks]

For a certain value of β0 , you are given the observed values

(this last subscript means “evaluated at β = β0 ”).

Write down a test statistic that you can approximately compare to a χp(2) quantile to test H0  : β = β0  vs H1  : β ≠ β0 .

Question 3 [8 marks total]+4 bonus Answer the following questions:

(a) [4  marks]   You have written a scientific paper containing results from a linear regression model E[YjX = x] = xβ fitted to independent count data. The data set was large and you estimated the variance of β(^) using a sandwich estimator.

A reviewer writes that count data are not normally distributed, and there-fore your Wald confidence intervals are incorrect because 1)β(^) is therefore not normally distributed either and b) the variances are wrong because they are estimated under the wrong model.  How do you respond?

(b) [2 marks]  Describe one situation in which a quasi-likelihood model may fail to produce reliable standard errors.

(c) [2 marks]  True or False: Data sampled according to the outcome will yield biased regression estimates unless it is appropriately weighted.

(d) [4 marks]  (bonus)  A regression coe代cient estimated from a parametric gen-

eralised linear model has covariance matrix Cov(β(^)) = φ(XTX)-1 .  Find two combinations of family and link that will yield this covariance.



热门主题

课程名

mktg2509 csci 2600 38170 lng302 csse3010 phas3226 77938 arch1162 engn4536/engn6536 acx5903 comp151101 phl245 cse12 comp9312 stat3016/6016 phas0038 comp2140 6qqmb312 xjco3011 rest0005 ematm0051 5qqmn219 lubs5062m eee8155 cege0100 eap033 artd1109 mat246 etc3430 ecmm462 mis102 inft6800 ddes9903 comp6521 comp9517 comp3331/9331 comp4337 comp6008 comp9414 bu.231.790.81 man00150m csb352h math1041 eengm4100 isys1002 08 6057cem mktg3504 mthm036 mtrx1701 mth3241 eeee3086 cmp-7038b cmp-7000a ints4010 econ2151 infs5710 fins5516 fin3309 fins5510 gsoe9340 math2007 math2036 soee5010 mark3088 infs3605 elec9714 comp2271 ma214 comp2211 infs3604 600426 sit254 acct3091 bbt405 msin0116 com107/com113 mark5826 sit120 comp9021 eco2101 eeen40700 cs253 ece3114 ecmm447 chns3000 math377 itd102 comp9444 comp(2041|9044) econ0060 econ7230 mgt001371 ecs-323 cs6250 mgdi60012 mdia2012 comm221001 comm5000 ma1008 engl642 econ241 com333 math367 mis201 nbs-7041x meek16104 econ2003 comm1190 mbas902 comp-1027 dpst1091 comp7315 eppd1033 m06 ee3025 msci231 bb113/bbs1063 fc709 comp3425 comp9417 econ42915 cb9101 math1102e chme0017 fc307 mkt60104 5522usst litr1-uc6201.200 ee1102 cosc2803 math39512 omp9727 int2067/int5051 bsb151 mgt253 fc021 babs2202 mis2002s phya21 18-213 cege0012 mdia1002 math38032 mech5125 07 cisc102 mgx3110 cs240 11175 fin3020s eco3420 ictten622 comp9727 cpt111 de114102d mgm320h5s bafi1019 math21112 efim20036 mn-3503 fins5568 110.807 bcpm000028 info6030 bma0092 bcpm0054 math20212 ce335 cs365 cenv6141 ftec5580 math2010 ec3450 comm1170 ecmt1010 csci-ua.0480-003 econ12-200 ib3960 ectb60h3f cs247—assignment tk3163 ics3u ib3j80 comp20008 comp9334 eppd1063 acct2343 cct109 isys1055/3412 math350-real math2014 eec180 stat141b econ2101 msinm014/msing014/msing014b fit2004 comp643 bu1002 cm2030
联系我们
EMail: 99515681@qq.com
QQ: 99515681
留学生作业帮-留学生的知心伴侣!
工作时间:08:00-21:00
python代写
微信客服:codinghelp
站长地图