At 12:32 AM 3/30/02 +0530, Manoj Kumar wrote: >Dear All: > >This posting may only interest the finance researchers subscribed to this >group. So let me begin by apologising to all others for the following >cross-posting. > >I am presently engaged in conducting an event study, directed at >knowing the stock prices impact of a firm-related event. Following >issues bother me: > >1. Should researcher consider the "trading days" or the "calendar >days" for the event period? Means if researcher specifies the event >period to be 100-days before and 100-days after the "event date", >then whether he is talking of 100 trading-days or 100 calendar-days. >Which of the two choices is better, and why?
well, what days can you get DATA on? i assume that the data you want relate to financial things ... if that is only available on trading days ... does that not answer your question? on the other hand, if the data you want to collect (events) are "things" that can occur on any day of the week ... independent of what happens on the trading days ... then it seems like calendar days makes more sense ... >2. If I consider trading days, then how about the weekend returns? >While on other week-days, we essentially calculate one day return >(Single-period return). The returns on weekend are after three days >i.e., Saturday, Sunday and Monday (Multi-period returns). How one >justifies this non-uniformity? i think the answer to #2 depends on your answer to #1 >3. How one deals with the non synchronous trading? Is it fine to >consider the previous day price for the next day, if stock doesn't >trade during the next trading day? How this may affect the research >results? Are there any better ways to deal with this problem? you might have to work with "blocks" of days ... not individual days ... blocks of days would help to remove the problem above ... AND, also ... would tend to stabilize the data you want to see i think for a list like this to be more helpful ... you have to be more specific as to what you are really interested in examining ... ie, more details about the aims of your research >I am sure some of you may have faced or may be facing similar >dilemmas. I will appreciate if you may share your views on the stated >issues. Some references of the prior event stdies, clarifying the >above issues will also be useful. > >Thanks, >Manoj Kumar >Senior Research Scholar [Finance] >SJM School of Management >Indian Institute of Technology >Powai Mumbai >India >ZIP:400076 > > > >. >. >================================================================= >Instructions for joining and leaving this list, remarks about the >problem of INAPPROPRIATE MESSAGES, and archives are available at: >. http://jse.stat.ncsu.edu/ . >================================================================= Dennis Roberts, 208 Cedar Bldg., University Park PA 16802 <Emailto: [EMAIL PROTECTED]> WWW: http://roberts.ed.psu.edu/users/droberts/drober~1.htm AC 8148632401 . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
