it's restricted, but not [0,1]. The contour should be over phi and sig2.
phi>0 and sig2>1 as in the lecture notes.
Kosuke
---------- Forwarded message ----------
Date: Tue, 4 Mar 2003 18:06:10 -0500 (EST)
To: Kosuke Imai <kimai(a)fas.harvard.edu>
Subject: contour limits
Kosuke:
Is the contour plot for 2b restricted to the interval [0,1] over
both x and y? If so, what do these axis represent?
This is a multi-part message in MIME format.
------=_NextPart_000_0128_01C2E28C.9A019910
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Simple question: what is this contour plot supposed to look like? Like =
the 3-D graphs Gary has in the lecture notes (am i supposed to have a =
mountain or hill?) or some curved lines that look like "concentric" =
brackets?
Traci
------=_NextPart_000_0128_01C2E28C.9A019910
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=3DContent-Type content=3D"text/html; =
charset=3Diso-8859-1">
<META content=3D"MSHTML 6.00.2719.2200" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial size=3D2>Simple question: what is this =
contour plot=20
supposed to look like? Like the 3-D graphs Gary has in the lecture =
notes=20
(am i supposed to have a mountain or hill?) or some curved lines that =
look like=20
"concentric" brackets?</FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT> </DIV>
<DIV><FONT face=3DArial size=3D2>Traci</FONT></DIV></BODY></HTML>
------=_NextPart_000_0128_01C2E28C.9A019910--
This is a multi-part message in MIME format.
------=_NextPart_000_0131_01C2E28C.BD998950
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
when i did it the first time, i got a beautiful rainbow! That can't be =
right!
T
------=_NextPart_000_0131_01C2E28C.BD998950
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=3DContent-Type content=3D"text/html; =
charset=3Diso-8859-1">
<META content=3D"MSHTML 6.00.2719.2200" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial size=3D2>when i did it the first time, i got a =
beautiful=20
rainbow! That can't be right!</FONT></DIV>
<DIV><FONT face=3DArial size=3D2>T</FONT></DIV></BODY></HTML>
------=_NextPart_000_0131_01C2E28C.BD998950--
Hi,
Our function for creating an inverse CDF for the Weibull distribution
takes in alpha and beta as parameters. When we compare it to the R
function "rweibull," how should the "shape" parameter relate to our alpha
and beta?
Thanks,
Colin
I would strongly encourage you all to apply. this is a great experience
for most who attend, entirely informal but intense. you'll meet everyone
in the field, faculty and grad students.
Gary
---------- Forwarded message ----------
Date: Mon, 3 Mar 2003 20:02:56 -0500
From: H-PolMeth <kjlong(a)umich.edu>
Reply-To: H-NET/APSA List for Political Methodology
<H-POLMETH(a)H-NET.MSU.EDU>
To: H-POLMETH(a)H-NET.MSU.EDU
Subject: H-POLMETH: 2003 Summer Political Methodology Meeting
Date: Fri, 28 Feb 2003 18:28:48 -0500 (EST)
From: Jonathan Nagler <jonathan.nagler(a)nyu.edu>
Subject: 2003 Summer Political Methodology Meeting
Dear Political Methodologists,
The 20th Annual Summer Political Methodology Conference will be held
July 17-19, 2003 at the University of Minnesota in Minneapolis. The meeting
is sponsored by the Society for Political Methodology, the APSA Political
Methodology Organized Section, and the National Science Foundation.
The Department of Political Science and College of Liberal Arts
at University of Minnessota are hosting the conference and providing
substantial support.
We are especially interested in papers presenting newly developed
methodological techniques. However, each year many excellent papers
are presented that demonstrate innovative applications of
methodological techniques to substantive problems in political science,
or that compare the relative usefulness of alternative methodological
techniques to examination of an important substantive problem.
Attendance at the meetings is by invitation. To apply to attend the
meetings fill out the application form at
http://web.polmeth.ufl.edu/apply2003.html
The deadline for applications is March 31, 2003. The program will be
finalized and invitations sent to participants by May 5.
Graduate students are particularly encouraged to apply. Those graduate
students who are accepted will have their airfare (up to a maximum of
$350) and conference registration paid by a grant from the National
Science Foundation.
Graduate students are selected based on the quality of their proposed
presentation, their ability to contribute to the intellectual quality
of the conference, and on the impact attending the conference is likely
to have on their future research. All graduate students attending will
be expected to present a sample of their work at a poster session.
Graduate student applicants will need a letter of recommendation from a
faculty sponsor. The sponsor's letter should be very clear about the quality
of the work the student will present, their level of methodological training,
and the likely future direction of their research.
Paper presenters are required to post their work on the Political
Methodology website at least 3 days prior to the start of the conference.
There is a registration fee of $150 for each faculty member, which
must be paid in advance of the conference. Faculty are expected to
seek support from their home institutions to cover their travel
expenses. Untenured faculty who are unable to obtain support from
their home institutions will be eligible for reimbursement of airfare,
but not the registration fee, up to a $350 maximum. All tenured faculty
are expected to be self-supporting. In unusual circumstances, support
will be available for tenured faculty, but this will be by prior arrangement
only. University of Minnesota is generously providing housing and meals
for the conference participants in addition to conference facilities.
Send any questions regarding the meeting to Jonathan Nagler
(jonathan.nagler(a)nyu.edu), President of the Society for Political
Methodology and the APSA Political Methodology Organized Section.
-jonathan nagler
--
##############################################################################
Jonathan Nagler jonathan.nagler(a)nyu.edu
Associate Chair Voice (o): 212 992-9676
Department of Politics Fax: 208 279-4334
726 Broadway - 7th floor http://homepages.nyu.edu/~jn23/
New York University
New York, NY 10003
##############################################################################
**********************************************************
Political Methodology E-Mail List
Acting Editor: Karen J. Long <kjlong(a)umich.edu>
Supervising Co-Editors:
Bradford S. Jones <bsjones(a)u.arizona.edu>
Robert J. Franzese, Jr. <franzese(a)umich.edu>
**********************************************************
Send messages to H-PolMeth(a)h-net.msu.edu
To join the list, visit http://www.h-net.msu.edu/~polmeth/
To leave the list, send the following message (and nothing
else) to listserv(a)h-net.msu.edu : signoff H-PolMeth
For more information on how to manage your subscription to
H-PolMeth, visit http://www.h-net.msu.edu/lists/help/
**********************************************************
For this question, you should "derive" the loglikelihood function. Report
each step of your derivation. Also, you should write your density
functions in R: i.e. don't use dpois etc.
Good luck,
Kosuke
Is it possible that there is a typo in the Weibull distribution
given in 1(b)?
The paratmetizaiton given in R help gives an inverse CDF of X =
beta * (ln(1-y))^-alpha, whereas I got
X = (ln(1-y))^(-alpha/beta)
from the equation in the problem set. If the equation in the
problem set had a -beta instead of a beta in the last term such
that it were
e^[-alphaX^{-beta}]
instead of
e^[-alphaX^{beta}]
then it would match the parametization in the R function.
Basically, I'm trying to figure out, is the parametization in
the R function different from the version given in the problem
set?
Thanks,
Olivia.
Hi all,
I want Latex to show multiplication of matrices, i.e. to put several matrices
one next to each other, and not one under the other. How do I do that?
Thanks,
Asif
