<div dir="ltr">With amm() and eventstudy() all of it sounds great. There is nothing about EventUS that we aren't already doing, except perhaps the various regression methods (OLS, EGARCH, GARCH, ScholesWilliams) and the traditional statistical tests (PATELL, JACKKNIFE). And all of these will be possible within the function interfaces that is under discussion. <div>
<br></div><div>Having said that, I think we need at least OLS implemented and the devil is in the details for the eventstudy() method. What are the various arguments here? I propose the following:- </div><div><br></div><div>
eventstudy():- </div><div><br></div><div>[1] data (matrix of calendar-time data)</div><div>[2] events (dataframe of events)</div><div>[3] adjustment method (ols, egarch, garch, ...)</div><div>[4] adjustment factors (a matrix of factors: if just market model, then just the market returns, if Fama-French factors, then the three factors etc.)</div>
<div>[5] inference (bootstrap, patell, jackknife,...)</div><div><br></div><div>We can speak through the details. Perhaps building a pseudo code with the shell for the whole package will be a good place to start. </div><div>
<div><div class="gmail_extra"><br><br><div class="gmail_quote">On 6 February 2014 12:53, Ajay Shah <span dir="ltr"><<a href="mailto:ajayshah@mayin.org" target="_blank">ajayshah@mayin.org</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Vikram and I spoke about this and we felt:<div><br></div><div>We should have a main function amm() and then setup plot() print() summary() methods as is the case with many R estimators. One big thing we want out of AMM estimation is residuals; this would be done as residuals(m) a la lm() and other estimators in R.</div>
<div><br></div><div>In similar fashion we should have m <- eventstudy() and then something like plot(m, type=3).</div><div><br></div><div>This should help simplify the API of the package. Other than print() plot() and summary() what would you suggest?</div>
<div><br></div><div>Does all the florid functionality of (say) EventUS, that we will eventually build, fit this way of thinking?<span><font color="#888888"><br clear="all"><div><br></div>-- <br>Ajay Shah<br>
<a href="mailto:ajayshah@mayin.org" target="_blank">ajayshah@mayin.org</a><br>
<a href="http://www.mayin.org/ajayshah" target="_blank">http://www.mayin.org/ajayshah</a><br><a href="http://ajayshahblog.blogspot.com" target="_blank">http://ajayshahblog.blogspot.com</a>
</font></span></div></div>
<br>_______________________________________________<br>
Eventstudies-discussion mailing list<br>
<a href="mailto:Eventstudies-discussion@lists.r-forge.r-project.org" target="_blank">Eventstudies-discussion@lists.r-forge.r-project.org</a><br>
<a href="https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/eventstudies-discussion" target="_blank">https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/eventstudies-discussion</a><br>
<br></blockquote></div><br><br clear="all"><div><br></div>-- <br><br>Vimal Balasubramaniam<br><br><a href="tel:%2B44%20755%20750%204880" value="+447557504880" target="_blank">+44 755 750 4880</a><br><a href="tel:%2B91%20981%20829%208975" value="+919818298975" target="_blank">+91 981 829 8975</a>
</div></div></div></div>