This is a multi-part message in MIME format.
------=_NextPart_000_00CE_01C3091A.83704AC0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
What's univariate time series data? Is that like plotting time on x =
axis and approval on y? or is it just like a plot of a variable of our =
choice on x and approval on y?
T
------=_NextPart_000_00CE_01C3091A.83704AC0
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>What's univariate time series =
data? Is that=20
like plotting time on x axis and approval on y? or is it just like =
a plot=20
of a variable of our choice on x and approval on y?</FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT> </DIV>
<DIV><FONT face=3DArial size=3D2>T</FONT></DIV></BODY></HTML>
------=_NextPart_000_00CE_01C3091A.83704AC0--
In terms of lagging variables in lm(), is it necessary to create a new column
of variables in the dataframe corresponding to Y_t-1 etc. (this is the way we
did it in 1000), or is there a convenient way that R can handle this?
Thanks,
Phillip.
-------------------------------------------------
Phillip Y. Lipscy
Perkins Hall Room #129
35 Oxford Street
Cambridge, MA 02138
(617)493-4893 DORM
(617)851-8220 CELL
lipscy(a)fas.harvard.edu
http://www.people.fas.harvard.edu/~lipscy/
First Year Student, Ph.D. Program
Harvard University, FAS, Department of Government
-------------------------------------------------
As I mentioned in class, you are invited to an end-of-semester party at
our house on Saturday May 17th at 11am for lunch, etc. Please feel free
to bring someone along (and kids are invited as well). Ella Michelle (7),
Elizabeth (>7), and Blizzard and Snowflake (0.5 and 1.7 dog years,
respectively) will be there too. We're at 9 Beecher Road, in Brookline.
Its about 5 miles from HU, and easy to get to by Bus, T, or car.
Directions are at http://gking.harvard.edu/directions
I'd appreciate if you'd RSVP soon, by responding to this email, so I
can get a count for food. Let me know whether you can make it and if
you'll be bringing someone. I hope you can make it.
Gary
: Gary King, King(a)Harvard.Edu http://GKing.Harvard.Edu :
: Center for Basic Research Direct (617) 495-2027 :
: in the Social Sciences Assistant (617) 495-9271 :
: 34 Kirkland Street, Rm. 2 HU-MIT DC (617) 495-4734 :
: Harvard U, Cambridge, MA 02138 eFax (928) 832-7022 :
Hi,
For the formula on past shocks (slide 78 on smodels.pdf), should the
second-to-last formula be:
\mu_i = x_i \beta - (y_1 - \mu_1)(-\phi)^{i - 1} <- (was just i)
- \sum_{j-1}^{i-2} <- (was i-1)
...
I've checked this out with i=4 and it seems to be correct.
Charles
You might want to replace the last line of ternary() with
points((X[,2] - X[,3])*s3, X[,1], pch=pch, ...)
This way, your input for "pch" won't get ignored!
Kosuke
Hi
I would like to number each equation (such as the one we get with cases) and
have a left curly brace to embrace all the equations.
for example (Latex, Leslie Lamport page 49)
x={ y if y > 0
{ z+y otherwise
\[ x = \left{ \begin{array}{ll}
y & \mbox{ if $y > 0 $ \\
z+y & \mbox{otherwise}
\end{array}
\right. \]
what I want is to number each line as follow
x={ y if y > 0 (1)
{ z+y otherwise (2)
Any suggestions?
Thanks
Vick
_________________________________________________________________
Help STOP SPAM with the new MSN 8 and get 2 months FREE*
http://join.msn.com/?page=features/junkmail
I am having a strange VNC problem. I can't log on to VNC (ok, so I need
to vncfinger, make sure I have a session, and vncserver to get a new one).
However, at every prompt (ice1,ice2,fas,...) vncfinger begets "Command not
found".
When Colin logs on to the same server I try (whether he has a session
there or not), he can vncfinger/vncserver with no problem.
Help!
Ryan
--
------------------------------------------
Ryan T. Moore ~ Government & Social Policy
Ph.D. Candidate ~ Harvard University
This is a multi-part message in MIME format.
------=_NextPart_000_0046_01C30389.3F172470
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
In the lecture notes, when gary uses capital F in the log-likelihood of =
the ordinal probit model, he means the CDF of the standard normal and =
not the pdf, right?
Traci
------=_NextPart_000_0046_01C30389.3F172470
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>In the lecture notes, when gary uses =
capital F in=20
the log-likelihood of the ordinal probit model, he means the CDF of the =
standard=20
normal and not the pdf, right?</FONT></DIV>
<DIV><FONT face=3DArial size=3D2><BR>Traci</FONT></DIV></BODY></HTML>
------=_NextPart_000_0046_01C30389.3F172470--
In class, Gary mentioned the neccessity of having a control group in
experiements, in order to establish causal relationship between the
explanatory variable and the dependent variable. In regression though, is
this the same as having variation in the explanatory variable? Or is there
difference between the two and, if so, can someone kindly explain it to me?
yongwook
-----------------------------
Yongwook Ryu
PhD Student
Department of Government
Harvard University
Tel:617-493-3397
Email: yryu(a)fas.harvard.edu
-----------------------------