STAT 511
8 Solutions to Homework 9
Spring 2004 8
1. Use times to failure for high speed turbine engine bearings made from two dierent compounds. (a) Make normal plots for the lifetimes and log-lifetimes. i. We do not expect constant variance/normal distri
Stat 511 Exam1
February 24, 2009
Prof. Vardeman
I have neither given nor received unauthorized assistance on this exam.
K67
Name Printed 1. Consider a segmented simple linear regression problem in one variable, x. In particular,
suppose that n : 6 value
Stat 511 Final Exam
May 8, 2003 Prof. Vardeman
1. A classic data set of Wishart (later analyzed by Ostle and then Stapleton) concerns weight gains of
young pigs in a comparative feeding trial. 3 different foods were fed to pigs of both sexes. 5 male pigs
~y
Stat
511
Exam
II
April 7, 2004
Prof. Vardeman
I. Consider a 3 x 3 factorial analysis with factors A and B under an ordinary (fixed effects) linear model. The effects model under the R baseline restriction has parameter vector for mean responses 1 = (,u
Stat 511 Exam1
February 26, 2008
Prof. Vardeman
I have neither given nor received unauthorized assistance on this exam.
Name Printed 1. Consider a problem of quadratic regression in one variable, x. In particular, suppose that n : 5
values of a response
Stat 511 Exam 2
April 11, 2003 Prof. Vardeman
l. The rst printout attached to this exam concerns the analysis of some data from a tire grip study.
Drag, x (measured in %), is applied to a tire and the (grip) force, y (measured in lbs), with which it
holds
,?-6- -(
Stat 511 Final Exam
May 5, 2004 Prof. Vardeman -Z.?-Y~ In a study meant to determine the variability of diameters of widgets produced on a manufacturing line, ~ an engineer measures m = 10 widgets produced on the line once each. Then the engineer
Stat 511 Exam 1
February 23, 2004 Prof. Vardeman
1. Consider an instance of the linear model for n = 5 observations,
y1 1 0 O a]
y2 1 1 1 ,6] 82
y3 = 1 1 1 ,82 + £3
y4 1 1 1 ,63 £4 E,
ys 1 1 1 55 . I E.
41¢ a) This is a full rank model. One way to easil
Stat 511 Final Exam
May 7, 2008
Prof. Vardeman
I have neither given nor received unauthorized assistance on this exam.
KEY
Name Printed 1. Below is a small table of fake (x, y) data. Use them to compute smoothed/nonparametric
regression tted values for
Stat 511 Exam 2
April 7, 2009
Prof. Vardeman
I have neither given nor received unauthorized assistance on this exam.
[(61
Name
Name Printed l. A data set in Statistical Tools for Nonlinear Regression by Huet, Bouvier, Poursat, and Jolivet
concerns the d
Stat 511 Exam 1
February 24, 2003 Prof. Vardeman
1. In the calibration of a scientic instrument, true valuesx are known and produce experimental
readings y on the instrument. Suppose that we are willing to assume that the mean value of y is
proportional t
STAT 511 HW#2 SPRING 2009 PROBLEM 1: a) = b) i. ii. iii. It is known that = ( ). In addition : =0 = = 0 which means ( ) ( ) . that is orthogonal to , that is ( ) . So ( ) ( ) since columns of can be written as linear combinations of the columns of = 0, wh
STAT 511 HW#4 SPRING 2009 PROBLEM 1.
(a) y<-c(62.9,21.5,19.3,64.1,32.9,30.9,93.4,64.6,58.6,26.6,51.3) x1<-c(-1,-1,-1,0,0,0,1,1,1,-0.5,0.5) x2<-c(-1,0,1,-1,0,1,-1,0,1,0.33,-0.33) library(MASS) model1<- lm(y~x1+x2) summary(model1) Estimate Std. Error t valu
STAT511SolutiontoHW6Spring2008
> qr(B)$rank [1] 7 > optim(c(.07,.45,.37),minuslLstar2,Y=Y,B=B,hessian=TRUE)$par [1] 0.3437852 0.8087115 0.2848388 (h) C M LE = C REM LE = ( = 99.4551, = 9.7936) s2 <- optim(c(.07,.45,.37),minuslLstar,Y=Y,hessian=TRUE)$par
Stat 511 Exam 2
April 7, 2008
Prof. Vardeman
I have neither given nor received unauthorized assistance on this exam.
E (await/6 9:va hws
Name
Name Printed 1. An experimental data set in a set of slides due to SA. J enekhe found on the University of
Wash