trend_slope()

double MayaFlux::Kinesis::Stochastic::Estimate::trend_slope ( std::span< const double >  samples )

staticnoexcept

Linear trend slope across a span.

Parameters

samples

Values to analyze

Returns

Least-squares slope in units of (value per sample index), 0.0 for spans of size < 2

Definition at line 301 of file Estimate.cpp.

{
    if (samples.size() < 2)
        return 0.0;
 
    const auto n = static_cast<double>(samples.size());
 
    double sum_x = 0.0;
    double sum_y = 0.0;
    double sum_xy = 0.0;
    double sum_xx = 0.0;
 
    for (size_t i = 0; i < samples.size(); ++i) {
        const auto x = static_cast<double>(i);
        const double y = samples[i];
        sum_x += x;
        sum_y += y;
        sum_xy += x * y;
        sum_xx += x * x;
    }
 
    const double denom = (n * sum_xx) - (sum_x * sum_x);
    if (std::abs(denom) < 1e-12)
        return 0.0;
 
    return ((n * sum_xy) - (sum_x * sum_y)) / denom;
}

Referenced by MayaFlux::Kinesis::approach_rate(), and update_trend().

Here is the caller graph for this function: