Name

---

  MPNORMLIM

Author

---

  Craig B. Markwardt, NASA/GSFC Code 662, Greenbelt, MD 20770
  craigm@lheamail.gsfc.nasa.gov
  UPDATED VERSIONs can be found on my WEB PAGE:
      http://cow.physics.wisc.edu/~craigm/idl/idl.html

Purpose

---

  Compute confidence limits for normally distributed variable

Major Topics

---

  Curve and Surface Fitting, Statistics

Calling Sequence

---

  Z = MPNORMLIM(PROB, [/CLEVEL, /SLEVEL ])

Description

---

  The function MPNORMLIM() computes confidence limits of a normally
  distributed variable (with zero mean and unit variance), for a
  desired probability level. The returned values, Z, are the
  limiting values: a the magnitude of a normally distributed value
  is greater than Z by chance with a probability PROB:
    P_NORM(ABS(X) > Z) = PROB
  In specifying the probability level the user has two choices:
    * give the confidence level (default);
    * give the significance level (i.e., 1 - confidence level) and
      pass the /SLEVEL keyword; OR
  Note that /SLEVEL and /CLEVEL are mutually exclusive.

Inputs

---

  PROB - scalar or vector number, giving the desired probability
          level as described above.

Returns

---

  Returns a scalar or vector of normal confidence limits.

Keyword Parameters

---

  SLEVEL - if set, then PROB describes the significance level.
  CLEVEL - if set, then PROB describes the confidence level
            (default).

Example

---

  print, mpnormlim(0.99d, /clevel)
  Print the 99% confidence limit for a normally distributed
  variable. In this case it is about 2.58 sigma.

References

---

  Algorithms taken from CEPHES special function library, by Stephen
  Moshier. (http://www.netlib.org/cephes/)

Modification History

---

  Completed, 1999, CM
  Documented, 16 Nov 2001, CM
  Reduced obtrusiveness of common block and math error handling, 18
    Nov 2001, CM
  Convert to IDL 5 array syntax (!), 16 Jul 2006, CM
  Move STRICTARR compile option inside each function/procedure, 9 Oct 2006
  Add usage message, 24 Nov 2006, CM