Example #1
0
def test_gauss_suff_stats():
    # High mean, tiny variance would lead to catastrophic cancellation
    # in a naive implementation that maintained the sum of squares.
    big = 400
    small = 0.0000001
    data = [big - small, big, big + small]
    true_sigma = math.sqrt(2 * small**2 / 3)
    (ct, mean, sigma) = stats.gauss_suff_stats(data)
    assert ct == 3
    assert mean == big
    assert relerr(true_sigma, sigma) < 1e-5
def estimate_mean(samples):
    """Estimate the mean of a distribution from samples.

    Return the triple (count, mean, error).

    `count` is the number of input samples.

    `mean` is the mean of the samples, which estimates the true mean
    of the distribution.

    `error` is an estimate of the standard deviation of the returned
    `mean`.  This is computed from the variance of the input samples,
    on the assumption that the Central Limit Theorem applies.  This is
    will be so if the underlying distribution has a finite variance,
    and enough samples were drawn.
    """
    (n, mean, stddev) = stats.gauss_suff_stats(samples)
    return (n, mean, stddev / math.sqrt(n))
Example #3
0
def estimate_mean(samples):
    """Estimate the mean of a distribution from samples.

    Return the triple (count, mean, error).

    `count` is the number of input samples.

    `mean` is the mean of the samples, which estimates the true mean
    of the distribution.

    `error` is an estimate of the standard deviation of the returned
    `mean`.  This is computed from the variance of the input samples,
    on the assumption that the Central Limit Theorem applies.  This is
    will be so if the underlying distribution has a finite variance,
    and enough samples were drawn.
    """
    (n, mean, stddev) = stats.gauss_suff_stats(samples)
    return (n, mean, stddev / math.sqrt(n))