← Back to Documentations

Signature Description Parameters 
include <DataFrame/DataFrameStatsVisitors.h>

template<arithmetic T, typename I = unsigned long>
struct  ConfIntervalVisitor;

// ----------------------------------

template<std::floating_point T, typename I = unsigned long>
using coni_v = ConfIntervalVisitor<T, I>;
This is a "single action visitor", meaning it is passed the whole data vector in one call and you must use the single_act_visit() interface.

A confidence interval is a range of values derived from sample data that is likely to contain the true, unknown population parameter. It's calculated as a point estimate (like the sample mean) plus or minus a margin of error. The accompanying confidence level, such as 95%, indicates the long-run probability that repeated sampling would result in intervals containing the true parameter.
A 95% confidence interval does not mean there is a 95% probability that the true population mean lies in this specific interval . Instead, it means that if you were to conduct this procedure many times with different samples, 95% of the intervals you generate would contain the true population mean.
    explicit
    ConfIntervalVisitor (value_type conf_level = 0.95);

conf_level: Confidence level must be between 80% and 99.9% inclusive,
            otherwise the result is NaN.
There are also the following member functions:
  get_result(): Returns a std::pair<T, T> containing lower and upper limits of
                plausible values for the true population parameter.
  get_error_margin(): Returns the the margin pf error.
T: Column data type.
I: Index type.
 
static void test_ConfIntervalVisitor()  {

    std::cout << "\nTesting ConfIntervalVisitor{ } ..." << std::endl;

    using StrDataFrame = StdDataFrame<std::string>;

    StrDataFrame    df;

    try  {
        df.read("IBM.csv", io_format::csv2);
    }
    catch (const DataFrameError &ex)  {
        std::cout << ex.what() << std::endl;
        ::exit(-1);
    }
    df.load_column("Extra Col", std::vector<double> { 5.1, 4.9, 5.0, 5.3, 5.2, 4.8 }, nan_policy::dont_pad_with_nans);

    ConfIntervalVisitor<double, std::string>    ci_v1 { 0.95 };

    df.single_act_visit<double>("Extra Col", ci_v1);
    assert(std::fabs(ci_v1.get_error_margin() - 0.149697) < 0.000001);
    assert(std::fabs(ci_v1.get_result().first - 4.9003) < 0.0001);
    assert(std::fabs(ci_v1.get_result().second - 5.1997) < 0.0001);

    ConfIntervalVisitor<double, std::string>    ci_v2 { 0.96 };

    df.single_act_visit<double>("Extra Col", ci_v2);
    assert(std::fabs(ci_v2.get_error_margin() - 0.159023) < 0.000001);
    assert(std::fabs(ci_v2.get_result().first - 4.89098) < 0.00001);
    assert(std::fabs(ci_v2.get_result().second - 5.20902) < 0.00001);

    coni_v<double, std::string> ci_v3 { 0.99 };

    df.single_act_visit<double>("IBM_Close", ci_v3);
    assert(std::fabs(ci_v3.get_error_margin() - 1.39119) < 0.00001);
    assert(std::fabs(ci_v3.get_result().first - 128.601) < 0.001);
    assert(std::fabs(ci_v3.get_result().second - 131.383) < 0.001);
}

C++ DataFrame