Homework Assignment 1: Whats That Got to
Do with the Price of Condos in California?
36-402, Advanced Data Analysis, Spring 2011
SOLUTIONS
The easiest way to load the data is with read.table, but you have to tell
R that the rst line names the variables:
>

Homework Assignment 2: The Advantages of
Backwardness
36-402, Advanced Data Analysis, Spring 2011
SOLUTIONS
This problem set was based on the preliminary analysis in the paper
E. Maasoumi, J. S. Racine and T. Stengos, Growth and convergence: a prole of di

Simulation
36-402, Advanced Data Analysis
1 February 2011
Contents
1 What Do We Mean by Simulation?
2 How Do We Simulate Stochastic Models?
2.1 Chaining Together Random Variables . . . . . . . .
2.2 Random Variable Generation . . . . . . . . . . . . .
2.2

Homework Assignment 5: Bootstrapping Will
Continue Until Morale Improves
36-402, Advanced Data Analysis, Spring 2011
SOLUTIONS
1. Answer:
library(MASS)
cats.lm1 <- lm(Hwt ~ 0+Bwt,data=cats) # "0+" sets intercept to zero
summary(cats.lm1)
# Quick view of r

Homework Assignment 6: Nice Demo City, But
Will It Scale?
36-402, Advanced Data Analysis, Spring 2011
SOLUTIONS
1. Answer: Taking the log of both sides gives
log y = log
Y
N
=
log Y log N
log(cN b ) log N
=
log c + log N b log N
=
log c + b log N log N
=

Cosma Shalizi
36-402, Undergraduate Advanced Data
Analysis
Spring 2013
Tuesdays and Thursdays, 10:30-11:50 Porter Hall 100
The goal of this class is to train
you in using statistical models to
analyze data as data summaries,
as predictive instruments, and

36-410 Practice midterm 2008
Hints:
This exam is longer than the one youll actually have in class.
If you fully understand the material, there is a short way to each solution. If you nd yourself attempting long, elaborate calculations, then
it is almost

Final Exam
36-402, Advanced Data Analysis
Due at 10:30 am on 13 May 2013
This exam has two parts, involving dierent data and (potentially) dierent
techniques. Points are as indicated.
You can use your notes, the textbooks, and indeed anything you nd in th

CMU 18-447 Introduction to Computer Architecture, Spring 2013
Midterm Exam 2
Date: Wed., 4/17
Name:
LU
TI
O
NS
Instructor: Onur Mutlu
TAs: Justin Meza, Yoongu Kim, Jason Lin
Legibility & Name (5 Points):
Problem 1 (90 Points):
Problem 2 (35 Points):
Probl

18-447 Intro to Computer Architecture, Spring 2012
Midterm Exam II
Instructor: Onur Mutlu
Teaching Assistants: Chris Fallin, Lavanya Subramanian, Abeer Agrawal
Date: April 11, 2012
Name:
SOLUTIONS
Problem I (60 Points)
:
Problem II (50 Points)
:
Problem I

1 Splus on the CMU Campus
Splus is available on many public machines on campus, as well as the private machines held by
departments such as Statistics.
All of the following public cluster machines have some version of Splus (for details, see
http:/www.cmu

Appalachian Red Spruce
80
N
N
N
N
N
N
60
N
N
N
N
N
Damage
40
N
N
N
N
N
N
N
N
N
20
N
N
N
N
N
N
N
S
N
N
S
S
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
N
S
S
N
N
N
800
S
S
1000
1200
Elevation
1400
S
1600
1800

Introduction to S-plus
Getting started
First read the Unix Summary handout and perform the onetime tasks described there.
A typical homework session includes the following steps:
0 Log on to a Solaris computer.
0 Type cd S401 to get to your class dire

Homework 8 Solutions
401 Fall 2001
Brian Junker and Kimberly Sellers
Thursday December 6, 2001
1. RWG pp284-285.
Problem 4 page 285. Extract principal components, and construct a scree graph. How many
components should we retain?
Note: For this problem, I

Homework 7 Solutions
401 Fall 2001
Brian Junker and Kimberly Sellers
Thursday November 29, 2001
There is one problem on this homework set (YEAH!). It is the ICU Problem from the DASL site.
1. Perform a logit regression of vital status on the following pre

Homework 6 Solutions
401 Fall 2001
Brian Junker and Kimberly Sellers
Thursday November 15, 2001
1. RwG problem 16 chapter 5 page 180.
The rst test in this problem is to nd decent initial values. Recall that the negative exponential model
has the form
. Th

Additive Models
36-402, Advanced Data Analysis
17 February 2011
Readings: Farway, ch. 12; sections 2.62.9 of Berk
Contents
1 Partial Residuals and Backtting for Linear Models
1
2 Additive Models
3
3 The Curse of Dimensionality
4
4 Example: California Hous

Evaluating Statistical Models
36-402, Data Analysis
18 January 2011
Optional Readings: Berk, chapter 2.
Contents
1 What Are Statistical Models For? Summaries, Forecasts, Simulators
1
2 Errors, In and Out of Sample
3
3 Over-Fitting and Model Selection
5
4

Homework Assignment 10: Use and Abuse of
Conditioning
36-402, Advanced Data Analysis, Spring 2011
SOLUTIONS
1. (a) Answer: Observe that occuatpion blocks all back door paths between smoking and cancer, and that occupation is not a descendant
of smoking. L

Homework 10: Estimating with DAGs
36-402, Advanced Data Analysis
Due at the start of class, Tuesday, 19 April 2011
This homework will illustrate some of the advantages of using a known DAG
structure. You will need to read the lectures on graphical models