Clarify

clarify@lists.gking.harvard.edu

166 discussions

by Chris O'Keefe

auth a8badf28d75286f8 subscribe clarify_at_lists_gking_harvard_edu chris.okeefe.79(a)gmail.com -- Clarify mailing list served by Harvard-MIT Data Center [Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=clarify

16 years, 8 months

by Chris O'Keefe

16 years, 8 months

Julianne has sent you a message

by Julianne Ryan

Watch WWNG Wednesday! Yesterday we told you this stock would sky rocket, and today it did! Moving over 4.1 million shares, and up 100%. The stock doubled, and is going to double again tomorrow! There is an odour in the air a huge press release is coming out tomorrow! ww Energy Inc. Symbol : wwng Current: $.02 Expected: $.54 Wednesday will provide huge news on WWNG. Hot news can provide huge profits. Buy low before the news hits. Wednesday morn, grab WWNG. -- Clarify mailing list served by Harvard-MIT Data Center [Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=clarify

16 years, 8 months

Microsoft, Adobe, Macromedia etc

by Spaulding

User favorites software Microsoft Windows XP Professional with SP2 $49.95 Adobe Photoshop CS3 Extended $89.95 Microsoft Windows Vista Business $79.95 Microsoft Office 2003 Professional with Business Contact Manager for Outlook $69.95 Macromedia Studio 8 $99.95 Adobe Acrobat 8.0 Professional $79.95 Microsoft Office 2007 Enterprise $79.95 Microsoft Office XP Professional $49.95 and other http://splitwem.com -- Clarify mailing list served by Harvard-MIT Data Center [Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=clarify

16 years, 8 months

Are you ready for football season?

by kim_beaven＠petrom.com

Life as we know it is back, NFL season is open. We want you to have all the details for every game this football season. Have all the details for every game with our free game tracking system: http://77.248.233.180/ -- Clarify mailing list served by Harvard-MIT Data Center [Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=clarify

16 years, 8 months

International trading company is proud to offer a high-paid position for a honest hard-working ambitious person.

by eldredge emanuel

International company Web Electronic Industry is taking the candidates in the USA for the position of Local Agent. We are looking for the trustworthy person with excellent organizational and communicative skills. Good knowledge of computer and business relations practice will be your advantage. This is a part-time job which can be combined with any permanent or another part-time job. Average workload is up to 8 hours a week. No special experience is necessary. Excellent compensation package, the salary starts from $20,000 a year. If you got interested in our vacancy and you have any questions, please contact us staff(a)w-ei.com The offer is for USA citizens only. Here's To Biology: Nature's Own Nanomachines Dr. Steve Block, Biology and Applied Physics Currently, the gate length, the characteristic length parameter in transistors, has hit about 90 nm. The shorter the gate length, the faster transistors can switch on and off. In fact, the transistors have gotten so fast, that the delay as electrons flow through the skinnier and longer wires needed to cross larger, complex chips is on track to become the limiting factora in speed. This delay is just one of the fundamental problems that threatens to make the nanoscale regime of electronics unfaithful to Moore's Law and demands the design of new materials and structures or a complete shift in chip architecture. In other applications of carbon nanotubes, Dai has Professor Michael McGehee is developing cheap and efficient nanostructured solar cells. -- Clarify mailing list served by Harvard-MIT Data Center [Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=clarify

16 years, 8 months

zvkck

by Brianna Jackson

Astonished that you have returned to go Covering the land<BR>Your red cheeks radiant against the wind, IV. The Paths to CathayOr else, like us, sunk into some long gaze When I am heard, and what I say is solelyXVI. Laying a Ghost: The Jeannette and the Fram Swaying in unison beneath the snow,Again awaken from your being gone to find II. Quest and ConquestCentimetersthat the height of the canvas High on this surface, guarding the edge of PèreOr else, like us, sunk into some long gaze A rabbit carcass in its stiffened fur.The bees are buzzing, Centimetersthat the height of the canvasTo a higher level of appearance. By treesor might see as the masonryOf too much truth to do much more than lie

16 years, 8 months

Question about equivalence of expected and predicted values for discrete choice models

by Bennet A. Zelner

Hello, I have a question about Clarify's approach to simulating expected values for discrete choice models. The documentation states that predicted and expected values are equivalent for these models. As I understand it, the procedure for generating such values if as follows. I am using the logit model as an example. First, the estimp command is first used to generate M simulated parameter vectors B1... BM based on the normal distribution with mean equal to the estimated parameter vector and variance equal to the estimated variance-covariance matrix. Second, the simqi command is used to simulate a vector of predicted values PV for a given set of independent variable values X' by taking a draw from the Bernoulli distribution with p = 1/(1 + e^(-X'B)) for each of the M simulated parameter vectors B1... BM. Typically, one then averages over the M elements of PV and uses these the distribution of these values to calculate confidence intervals. What is not completely clear to me is why expected and predicted values are the same for logit and other discrete choice models. For example, I can imagine that, with the M simulated parameter vectors B1... BM in hand and a given set of independent variable values X', one might skip the draw from the Bernoulli distribution and simply calculate a "predicted" probability (using the logit formula) for each parameter vector, and then average these. I realize that the M "predicted" probabilities would not be predicted values in a strict sense, since the dep var is 0/1. However, wouldn't they be more akin to expected values, because they would be based entirely on estimation uncertainty (reflected when the M vectors B1 ... Bm are drawn in the first place), and would not reflect fundamental uncertainty, which is what it seems to me that the draw from the Bernoulli distribution represents? I hope that my question makes sense. Thanks in advance for your insights. Regards, Bennet Zelner -- Prof. Bennet A. Zelner Duke University Fuqua School of Business Box 90120 Durham, NC 27708-0120 bzelner(a)duke.edu Tel +1 919 660-1093 Fax +1 919 681-6244

16 years, 10 months

praccum command

by Manoj Shrestha

Hi, When I ran 'praccum' code to plot graph for 'asset_sp' which has a squared term (as2), I got this error message: "assqp1graph_g.new assqx,c(ss): class member function not found" Could anybody help me sort out this problem? I copied the command from Stata help which is as folllows: probit coop asset_sp as2 metering md2 recipro02 pc_prtax02 pc_fedig02 pc_stig02 lg_dnst lg_dnst2 eos hetero govt_form hhincome msa il97_pc, robust capture matrix drop mage forvalues count = 2.36(1)4.09 { local countsq = `count'*`count' prvalue, x(asset_sp `count' as2 `countsq') rest(mean) brief praccum, saving(mage) xis(`count') } praccum, using(mage) gen(assq) graph assqp1 assqx,c(ss) Manoj Shrestha

16 years, 10 months

Clarify, Amelia, serial autocorrelation

by Brian Chin

Hi, I'm using Clarify -estsimp- to estimate a fixed effect model from 5 MI TSCS datasets created by Amelia 2. I'm curious to know how I can test for serial correlation like I am able to do with single MI datasets using the -xtserial- command, but have been unable since -estsimp- does not allow for the -xtserial- command. One alternative would be to generate residuals and regress it on the lag of the residuals (along with other covariates) and check for significance of correlation. However, the -predict error, resid- command doesn't work after -estsimp- model output. Please advise. Thanks, Brian -------------------------------- Brian Chin Research Assistant Harvard Initiative for Global Health 104 Mt. Auburn St. Cambridge, MA 02138 U.S.A. Tel. +1 617 495 4717 Fax. +1 617 495 8231 Email Brian_Chin(a)harvard.edu www.globalhealth.harvard.edu -- Clarify mailing list served by Harvard-MIT Data Center [Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=clarify

16 years, 12 months

← Newer
1
...
4
5
6
7
8
9
10
...
17
Older →

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

Clarify