Re: Distributions

Try a*sinh[b*(x-m)/s], where x is normal with mean m and variance s^2.

Ross Clement (Email address invalid - do not use) wrote:
> Can anyone please name a few distributions that are far more
> concentrated among the mean than the normal distribution. When I create
> a qq plot (qqnorm in R) for the data in question, the line is near
> horizontal except at the tails. And I do mean horizontal, not the x=y
> line for a perfect fit.
>
> I'm extremely tempted to consider the Cauchy distribution. The data are
> the errors when the place where a line meets the x axis is used to
> estimate a property. I'm aware that if we have lines at random angles,
> then the place where they intersect the x axis follows a Cauchy
> distribution. Hence I'm tempted to believe that if I'm looking at lines
> where the measured angle is a "true" angle plus an error angle, that
> the error of the x-intercept would follow a Cauchy distribution. But
> perhaps I'm misguided so I would appreciate comments and suggestions of
> other distributions that I should look at.
>
> Cheers,
>
> Ross-c

.

Relevant Pages

  • Re: Angles between vectors
    ... The 'Mahalonobis angle' metric will result if you transform ... If we have 5 books by ... that we have a such as the normal distribution defined by two ... I can define my distribution with a single number x. ...
    (sci.stat.math)
  • Re: OT raibow
    ... Looking at the picture of ray ... and a0 the angle at the vertex of the cone. ... conjecture corresponds to distribution with density concentrated at ...
    (comp.lang.perl.misc)
  • Distributions
    ... I'm extremely tempted to consider the Cauchy distribution. ... the errors when the place where a line meets the x axis is used to ... where the measured angle is a "true" angle plus an error angle, ...
    (sci.stat.math)
  • Re: Random directions
    ... between the random vector and a fixed vector. ... Because the RV is a fixed angle from the FV, ... what sort of random distribution on the cone do you wish to ...
    (comp.soft-sys.matlab)
  • Re: Random directions
    ... I would like a uniform distribution. ... Because the RV is a fixed angle from the FV, ... what sort of random distribution on the cone do you ...
    (comp.soft-sys.matlab)