time-to-botec

Benchmark sampling in different programming languages
Log | Files | Refs | README

repl.txt (5045B)


      1 
      2 {{alias}}( x[, y][, options] )
      3     Computes a one-sample or paired Student's t test.
      4 
      5     When no `y` is supplied, the function performs a one-sample t-test for the
      6     null hypothesis that the data in array or typed array `x` is drawn from a
      7     normal distribution with mean zero and unknown variance.
      8 
      9     When array or typed array `y` is supplied, the function tests whether the
     10     differences `x - y` come from a normal distribution with mean zero and
     11     unknown variance via the paired t-test.
     12 
     13     The returned object comes with a `.print()` method which when invoked will
     14     print a formatted output of the results of the hypothesis test.
     15 
     16     Parameters
     17     ----------
     18     x: Array<number>
     19         Data array.
     20 
     21     y: Array<number> (optional)
     22         Paired data array.
     23 
     24     options: Object (optional)
     25         Options.
     26 
     27     options.alpha: number (optional)
     28         Number in the interval `[0,1]` giving the significance level of the
     29         hypothesis test. Default: `0.05`.
     30 
     31     options.alternative: string (optional)
     32         Indicates whether the alternative hypothesis is that the mean of `x` is
     33         larger than `mu` (`greater`), smaller than `mu` (`less`) or equal to
     34         `mu` (`two-sided`). Default: `'two-sided'`.
     35 
     36     options.mu: number (optional)
     37         Hypothesized true mean under the null hypothesis. Set this option to
     38         test whether the data comes from a distribution with the specified `mu`.
     39         Default: `0`.
     40 
     41     Returns
     42     -------
     43     out: Object
     44         Test result object.
     45 
     46     out.alpha: number
     47         Used significance level.
     48 
     49     out.rejected: boolean
     50         Test decision.
     51 
     52     out.pValue: number
     53         p-value of the test.
     54 
     55     out.statistic: number
     56         Value of test statistic.
     57 
     58     out.ci: Array<number>
     59         1-alpha confidence interval for the mean.
     60 
     61     out.nullValue: number
     62         Assumed mean under H0 (or difference in means when `y` is supplied).
     63 
     64     out.alternative: string
     65         Alternative hypothesis (`two-sided`, `less` or `greater`).
     66 
     67     out.df: number
     68         Degrees of freedom.
     69 
     70     out.mean: number
     71         Sample mean of `x` or `x - y`, respectively.
     72 
     73     out.sd: number
     74         Standard error of the mean.
     75 
     76     out.method: string
     77         Name of test.
     78 
     79     out.print: Function
     80         Function to print formatted output.
     81 
     82     Examples
     83     --------
     84     // One-sample t-test:
     85     > var rnorm = {{alias:@stdlib/random/base/normal}}.factory( 0.0, 2.0, { 'seed': 5776 });
     86     > var x = new Array( 100 );
     87     > for ( var i = 0; i < x.length; i++ ) {
     88     ...     x[ i ] = rnorm();
     89     ... }
     90     > var out = {{alias}}( x )
     91     {
     92         rejected: false,
     93         pValue: ~0.722,
     94         statistic: ~0.357,
     95         ci: [~-0.333,~0.479],
     96         // ...
     97     }
     98 
     99     // Paired t-test:
    100     > rnorm = {{alias:@stdlib/random/base/normal}}.factory( 1.0, 2.0, { 'seed': 786 });
    101     > x = new Array( 100 );
    102     > var y = new Array( 100 );
    103     > for ( i = 0; i < x.length; i++ ) {
    104     ...     x[ i ] = rnorm();
    105     ...     y[ i ] = rnorm();
    106     ... }
    107     > out = {{alias}}( x, y )
    108     {
    109         rejected: false,
    110         pValue: ~0.191,
    111         statistic: ~1.315,
    112         ci: [ ~-0.196, ~0.964 ],
    113         // ...
    114     }
    115 
    116     // Print formatted output:
    117     > var table = out.print()
    118     Paired t-test
    119 
    120     Alternative hypothesis: True difference in means is not equal to 0
    121 
    122         pValue: 0.1916
    123         statistic: 1.3148
    124         df: 99
    125         95% confidence interval: [-0.1955,0.9635]
    126 
    127     Test Decision: Fail to reject null in favor of alternative at 5%
    128     significance level
    129 
    130     // Choose custom significance level:
    131     > arr = [ 2, 4, 3, 1, 0 ];
    132     > out = {{alias}}( arr, { 'alpha': 0.01 });
    133     > table = out.print()
    134     One-sample t-test
    135 
    136     Alternative hypothesis: True mean is not equal to 0
    137 
    138         pValue: 0.0474
    139         statistic: 2.8284
    140         df: 4
    141         99% confidence interval: [-1.2556,5.2556]
    142 
    143     Test Decision: Fail to reject null in favor of alternative at 1%
    144     significance level
    145 
    146     // Test for a mean equal to five:
    147     > var arr = [ 4, 4, 6, 6, 5 ];
    148     > out = {{alias}}( arr, { 'mu': 5 })
    149     {
    150         rejected: false,
    151         pValue: 1,
    152         statistic: 0,
    153         ci: [ ~3.758, ~6.242 ],
    154         // ...
    155     }
    156 
    157     // Perform one-sided tests:
    158     > arr = [ 4, 4, 6, 6, 5 ];
    159     > out = {{alias}}( arr, { 'alternative': 'less' });
    160     > table = out.print()
    161     One-sample t-test
    162 
    163     Alternative hypothesis: True mean is less than 0
    164 
    165         pValue: 0.9998
    166         statistic: 11.1803
    167         df: 4
    168         95% confidence interval: [-Infinity,5.9534]
    169 
    170     Test Decision: Fail to reject null in favor of alternative at 5%
    171     significance level
    172 
    173     > out = {{alias}}( arr, { 'alternative': 'greater' });
    174     > table = out.print()
    175     One-sample t-test
    176 
    177     Alternative hypothesis: True mean is greater than 0
    178 
    179         pValue: 0.0002
    180         statistic: 11.1803
    181         df: 4
    182         95% confidence interval: [4.0466,Infinity]
    183 
    184     Test Decision: Reject null in favor of alternative at 5% significance level
    185 
    186     See Also
    187     --------
    188