Hi, I am looking at bond tender
offers, i.e. situations where a firm trys
to buy back its bonds (publicly traded debt) from investors prior to the
actual maturity date of the bonds. I am interested in two things. First,
what determines the premium above current market price offered by
the firm in the tender offer. Second, what determines the percentage
of bonds tendered by investors. Obviously premium and percent
tendered are endogenously determined.
Since percent tendered is constrained
between 0 and 1, I don't want to
use OLS for this particular equation. Instead I want to estimate the
following:
glm percent_tendered premium other_controls,
family(binomial)
link(logit) sca(x2)
(For and explanation of this regression methodology, see Papke and
Woolridge, 1996, Econometric methods for fractional
response variables with an application to 401 (K) plan
participation rates, Journal of Applied Econometrics 11, 619-
632.)
Can I incorporate
this non-linear regression into the reg3
command, or am I limited to manually doing 2-stage least
squares?
Sincerely,
Eric A. Powers
Assistant Professor of Finance
The Moore School of Business
University of South Carolina
Columbia SC, 29208
