Usage: 
{coef,knots,bound,logl,penalty,sample,del}=logsplinefit(uncensored,right,left,interval,lbound,ubound,indel,nknots,inputknots,inpenalty)

Input: 
 uncensored  vector of uncensored observations from the distribution whose density is
to be estimated. If there are no uncensored observations, plug in any nonnumeric type
to omit this parameter. However, either uncensored observations or the interval must be specified.

 right  vector of right censored observations from the distribution
whose density is to be estimated. If there are no right censored observations,
plug in any nonnumeric type.

 left  vector of left censored observations from the distribution
whose density is to be estimated. If there are no left censored
observations, plug in any nonnumeric type.

 interval  two column matrix of lower and upper bounds of observations
that are interval censored from the distribution whose density is
to be estimated. If there are no interval censored observations, plug in
any nonnumeric type.

 lbound, ubound  lower and upper bounds for the support of the density. For example, if there
is a priori knowledge that the density equals zero to the left of 0
and has a discontinuity at 0, the user could specify lbound=0.
However, if the density is essentially zero near 0, one does not need to
specify lbound. To omit these parameters plug in any nonnumeric type.

 indel  optional scalar, should stepwise knot deletion be employed (nonzero value) or not (zero, default)?

 nknots  optional vector, forces the method to start with nknots knots (indel=1) or to fit a
density with nknots knots (indel=0). The method has an automatic rule
for selecting nknots if this parameter is not specified.

 inputknots  optional ordered vector of values (that should cover the complete range of the
observations), which forces the method to start with these knots (indel=1)
or to fit a density with these knots (indel=0). Overrules nknots.
If inputknots is not specified, a default knotplacement rule is employed.

 inpenalty  optional scalar, the parameter to be used in the AIC criterion. The method chooses
the number of knots that minimizes 2*loglikelihood+inpenalty*(number of inputknots1).
The default is to use inpenalty=log(samplesize) as in BIC. The effect of
this parameter is summarized in logsplinesummary().

Output: 
 coef  coefficients of the spline. The first coefficient is the constant term,
the second is the linear term and the kth (k>2) is the coefficient
of (xt[k2])^3+ (where ^3+ means the positive part of the third power,
and t[k2] means knot k2). If a coefficient is zero, the corresponding
knot was deleted from the model. 
 knots  vector of the locations of the knots in the logspline model 
 bound  first element: 0  lbound was infinity, 1 it was something else;
second element: lbound, if specified;
third element: 0  ubound was infinity, 1 it was something else;
fourth element: ubound, if specified. 
 logl  the kth element is the loglikelihood of the fit with k+2 knots. 
 penalty  the penalty that was used. 
 sample  the sample size that was used. 
 del  was stepwise knot deletion employed? 