Name

---

    BOOTSTRAP_MEAN

Purpose

---

    Calculates the mean and a confidence limit on the mean based on
    bootstrap resampling.

Category

---

    Math

Calling Sequence

---

    Result = BOOTSTRAP_MEAN(Values)

Inputs

---

    Values: A vector of values whose mean and error is to be calculated.

Keyword Parameters

---

    NBOOT: Number of bootstrap resamplings. Default: 1000.
    CONFLIMIT: Confidence limit. Default: 0.68 (equivalent to 1sigma
                for a normal distribution).
    UNIQLIST: If independent points are associated with more than one
                element of Values, then they should all be included or
                excluded together in the bootstrap resampling. In this
                case, set UNIQLIST to the result of running UNIQ on
                a list with the same length as Values containing the
                unique identifier associated with each. Note that for
                this to work, Values must be sorted in order of the
                identifier.

Example

---

    Compares the expected error in the mean of normally-distributed values
    to the bootstrap-determined error:
    IDL> vals = RANDOMN(seed, 100)
    IDL> vals = 2.5*RANDOMN(seed, 100)
    IDL> PRINT, BOOTSTRAP_MEAN(vals)
        -0.26419502 -0.014198994 0.22447498
    IDL> PRINT, 2.5/SQRT(100)
        0.250000

Outputs

---

    Returns a 3-element vector containing the lower limit, mean, and
    upper limit.

Modification History

---

    Written by: Jeremy Bailin
    12 June 2008 Public release in JBIU