Additional Topics for Discussion
Calculation of Power
Suppose 1,000 observations were collected on a binary response variable and 4 continuous
predictors.
Binary response variable (Y ):
y
1= sucess, 0
Homework 2 (Due 1-28)
Instructions: Turn in at the beginning of class. Include all relevant R commands
and output (including plots) in your homework. The Course Info document provides
guidelines for h
Homework 5 (Due 2-28)
Instructions: Turn in at the beginning of class. Include all relevant R commands
and output (including plots) in your homework. Try to keep it 4-5 pages or less. Late
homework no
Homework 9 (Due 4-18)
Data on the percentage of body fat, age, weight, height, and ten body circumference measurements are recorded for 252 men. Use the fat data in the faraway package for this
proble
Homework 5 (Due 3-20)
Instructions: Turn in at the beginning of class. Include all relevant R commands and
output (including plots) in your homework. Try to keep it 4-5 pages or less. Late homework
no
STATS 500 - Lecture 16
STATS 500 - Lecture 16 p. 1/22
Poisson Regression
STATS 500 - Lecture 16 p. 2/22
Poisson Regression
Poisson regression is commonly used to model count data
Certain Poisson model
Stat 500 Homework 4 (Solutions)
Read in data and fit the model:
> library(faraway)
> data(teengamb)
> g = lm(gamble ~ sex + status + income + verbal, data = teengamb)
> summary(g)
Coefficients:
Estima
Homework 2 (Due 1-31)
Instructions: Turn in at the beginning of class. Include all relevant R commands
and output (including plots) in your homework. Try to keep it three pages or less.
Late homework
STATS 500 - Lecture 2
STATS 500 - Lecture 2 p. 1/29
Brief Intro to R
STATS 500 - Lecture 2 p. 2/29
Some Information About R
R is free software
Downloadable at http:/www.r-project.org/
Runs on UNIX pla
Stat 500 Homework 2 (Solutions)
1. The R output (only relevant part) for the fitted model is given below.
> library(faraway)
> data(uswages)
> g<-lm(wage~educ+exper,uswages)
> summary(g)
Coefficients:
STATS 500 - Homework 3
Due in class Wednesday, October 4, 2017
1. Using the sat data (see help(sat) for the description of variables) from
faraway package:
1. Fit a model with total sat score as the r
Stat 500 Homework 4 (Solutions)
Read in data and fit the model.
> library(faraway)
> data(sat)
> g<-lm(total~expend+salary+ratio+takers,data=sat)
1. > plot(g$fit, g$res, xlab="Fitted", ylab="Residuals
STATS 500 - Homework 4
Due Wednesday, October 11, 2007
1. Based on Chapter 4, problem 1 (p. 97)
Using the sat dataset, fit a model with the total SAT score as the
response and expend, salary, ratio an
Stat 500 Homework 3 (Solutions)
1. The model is fit and the tests are performed below:
> data(sat)
> g<-lm(total ~ takers + ratio + salary, data = sat)
> summary(g)
Coefficients:
(Intercept)
takers
ra
Stat 500 Homework 1 (Solutions)
After loading the data, fix the categorical variables race, smsa, ne, mw, so, we, and pt so that
they are treated as factors (e.g. for race, use the following command d
Orientation Schedule 2017 (Tentative)
Below is a list of orientation events required for all incoming Quant students. In addition to
theses, we encourage you to attend as many International Center wor
CORE DISCUSSION PAPER
2006/80
MODELLING FINANCIAL HIGH FREQUENCY DATA USING POINT
PROCESSES
Luc Bauwens1 and Nikolaus Hautsch2
September 18, 2006
Abstract
In this chapter written for a forthcoming Han
Lecture 5
An Introduction to Big Data and
Artificial Intelligence in Finance
(Investing)
ALFSHD
(Analytics&Learning for Financial, Social and Human Dynamics)
Big Data Revolution
Whats Big Data?
ML and
FAR: A Fault-avoidance Routing Method for Data Center
Networks with Regular Topology
Yantao Sun
School of Computer and Information Technology
Beijing Jiaotong University
Beijing 100044, China
[email protected]
Chapter 9: Transformation
Stats 500, Fall 2017
Brian Thelen, University of Michigan
443 West Hall, [email protected]
1 / 28
Transformation
Transforming the response
Transforming the predictors
Why?
Chapter 11: Shrinkage Methods
Stats 500, Fall 2017
Brian Thelen, University of Michigan
443 West Hall, [email protected]
1 / 39
Shrinkage Methods
Principal components regression
Partial least squares
STATS 500 - Info and Practice Exam 1 Questions
October 18, 2017
Information: The First Exam will be Thursday, October 26 from 6:00-8:00pm in Weiser
Hall 170. It will cover all the material in the Lect
STATS 500 - Practice Exam 1 Solutions
1. n = 30, p = 4 predictors (5 parameters) and
= 31.5.
2. 10 28.92 = 289.2Kcal/kg more.
3. This corresponds to W ater = 100 and the rest=0 so the predicted cont
Stat 500 Exam 1 Solutions
Fall Semester - 2015
This study was undertaken in the context of proposals for a guaranteed annual wage (negative
income tax). The data are from a national sample of 6000 hou
STATS 500 - Homework 1
Due in class Monday, September 21
Chapter 1, problem 2 (page 12)
The dataset uswages is drawn as a sample from the Current Population Survey in 1988. Make a numerical and graphi
STATS 500 - Homework 4
Due Wednesday, October 14, 2015
Based on Chapter 6, problem 2 (p. 97)
Using the teengamb dataset, fit a model to predict gambling expenditure
from all other available variables.