Multiple dummies

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

Julia4
Posts: 1
Joined: Sun Jul 14, 2013 7:49 am

Multiple dummies

Postby Julia4 » Sun Jul 14, 2013 8:04 am

Hi,

I am comparing leverage data from two different periods (event study). However, I am struggling with the insertion of dummies. I have basically created two: 1 indicating whether the ratio is from before (0)or after the event(1) and another indicating to which industry the leverage ratios belong to (1,2,3,4). I wish to determine whether there is a difference between e.g. the leverage ratios 'before' and 'after' for a specific industry (so not the difference between industries). The comparison between before and after without taking the industries into account was simple, but I can't seem to find a way (not in the manual either) to split the overall data up in industries/control for the industry. If I use the 'expand' function, dropping the other industries to just keep one, the table shown after conducting a test (Kruskal wallis) also shows the leverage values of the industries which are not supposed to be researched (indicated by a 0,0 in the category statistics - this row also contains actual values, not NA). I am was wondering if these (0,0) values distort/influence the data in any way?

I also tried just splitting up the data in a new file, only containing leverage ratios of just 1 industry and 1 dummy accounting for the timing of the ratio. However, this would mean my test would change to a (Mann-Whitney test) again, as I only have 2 groups left and I am not sure that is the right way to go.

So, my question is whether it is possible to keep all the data in one file and insert multiple dummies? Or is it easier (and allowed) to just split up the data before inserting it into eviews (my data is in excel)?

Thanks in advance.

Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 1 guest