time-to-botec

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

test.md (6833B)


      1 ## Statistical Tests
      2 
      3 The test module includes methods that enact popular statistical tests.
      4 The tests that are implemented are Z tests, T tests, and F tests.
      5 Also included are methods for developing confidence intervals. Currently
      6 regression is not included but it should be included soon (once matrix
      7 inversion is fixed).
      8 
      9 ## Statistics Instance Functionality
     10 
     11 ### zscore( value[, flag] )
     12 
     13 Returns the z-score of `value` taking the jStat object as the observed
     14 values. `flag===true` denotes use of sample standard deviation.
     15 
     16 ### ztest( value, sides[, flag] )
     17 
     18 Returns the p-value of `value` taking the jStat object as the observed
     19 values. `sides` is an integer value 1 or 2 denoting a 1 or 2 sided z-test.
     20 The test defaults to a 2 sided z-test if `sides` is not specified. `flag===true`
     21 denotes use of sample standard deviation.
     22 
     23 ### tscore( value )
     24 
     25 Returns the t-score of `value` taking the jStat object as the observed
     26 values.
     27 
     28 ### ttest( value, sides )
     29 
     30 Returns the p-value of `value` taking the jStat object as the observed
     31 values. `sides` is an integer value 1 or 2 denoting a 1 or 2 sided t-test.
     32 The test defaults to a 2 sided t-test if `sides` is not specified.
     33 
     34 ### anovafscore()
     35 
     36 Returns the f-score of the ANOVA test on the arrays of the jStat object.
     37 
     38 ### anovaftest()
     39 
     40 Returns the p-value of an ANOVA test on the arrays of the jStat object.
     41 
     42 ## Static Methods
     43 
     44 ## Z Statistics
     45 
     46 ### jStat.zscore( value, mean, sd )
     47 
     48 Returns the z-score of `value` given the `mean` mean and the `sd` standard deviation
     49 of the test.
     50 
     51 ### jStat.zscore( value, array[, flag] )
     52 
     53 Returns the z-score of `value` given the data from `array`. `flag===true` denotes
     54 use of the sample standard deviation.
     55 
     56 ### jStat.ztest( value, mean, sd, sides )
     57 
     58 Returns the p-value of a the z-test of `value` given the `mean` mean and `sd` standard
     59 deviation of the test. `sides` is an integer value 1 or 2 denoting a
     60 one or two sided z-test. If `sides` is not specified the test defaults
     61 to a two sided z-test.
     62 
     63 ### jStat.ztest( zscore, sides )
     64 
     65 Returns the p-value of the `zscore` z-score. `sides` is an integer value 1 or 2
     66 denoting a one or two sided z-test. If `sides` is not specified the test
     67 defaults to a two sided z-test
     68 
     69 ### jStat.ztest( value, array, sides[, flag] )
     70 
     71 Returns the p-value of `value` given the data from `array`. `sides` is
     72 an integer value 1 or 2 denoting a one or two sided z-test. If `sides`
     73 is not specified the test defaults to a two sided z-test. `flag===true`
     74 denotes the use of the sample standard deviation.
     75 
     76 ## T Statistics
     77 
     78 ### jStat.tscore( value, mean, sd, n )
     79 
     80 Returns the t-score of `value` given the `mean` mean, `sd` standard deviation,
     81 and the sample size `n`.
     82 
     83 ### jStat.tscore( value, array )
     84 
     85 Returns the t-score of `value` given the data from `array`.
     86 
     87 ### jStat.ttest( value, mean, sd, n, sides )
     88 
     89 Returns the p-value of `value` given the `mean` mean, `sd` standard deviation,
     90 and the sample size `n`. `sides` is an integer value 1 or 2 denoting
     91 a one or two sided t-test. If `sides` is not specified the test
     92 defaults to a two sided t-test.
     93 
     94 ### jStat.ttest( tscore, n, sides )
     95 
     96 Returns the p-value of the `tscore` t-score given the sample size `n`. `sides`
     97 is an integer value 1 or 2 denoting a one or two sided t-test.
     98 If `sides` is not specified the test defaults to a two sided t-test.
     99 
    100 ### jStat.ttest( value, array, sides )
    101 
    102 Returns the p-value of `value` given the data in `array`.
    103 `sides` is an integer value 1 or 2 denoting a one or two sided
    104 t-test. If `sides` is not specified the test defaults to a two
    105 sided t-test.
    106 
    107 ## F Statistics
    108 
    109 ### jStat.anovafscore( array1, array2, ..., arrayn )
    110 
    111 Returns the f-score of an ANOVA on the arrays.
    112 
    113 ### jStat.anovafscore( [array1,array2, ...,arrayn] )
    114 
    115 Returns the f-score of an ANOVA on the arrays.
    116 
    117 ### jStat.anovaftest( array1, array2, ...., arrayn )
    118 
    119 Returns the p-value of the f-statistic from the ANOVA
    120 test on the arrays.
    121 
    122 ### jStat.ftest( fscore, df1, df2)
    123 
    124 Returns the p-value for the `fscore` f-score with a `df1` numerator degrees
    125 of freedom and a `df2` denominator degrees of freedom.
    126 
    127 ## Tukey's Range Test
    128 
    129 ### jStat.qscore( mean1, mean2, n1, n2, sd )
    130 
    131 Returns the q-score of a single pairwise comparison between arrays
    132 of mean `mean1` and `mean2`, size `n1` and `n2`, and standard deviation (of
    133 all vectors) `sd`.
    134 
    135 ### jStat.qscore( array1, array2, sd )
    136 
    137 Same as above, but the means and sizes are calculated automatically
    138 from the arrays.
    139 
    140 ### jStat.qtest( qscore, n, k )
    141 
    142 Returns the p-value of the q-score given the total sample size `n`
    143 and `k` number of populations.
    144 
    145 ### jStat.qtest( mean1, mean2, n1, n2, sd, n, k )
    146 
    147 Returns the p-value of a single pairwise comparison between arrays
    148 of mean `mean1` and `mean2`, size `n1` and `n2`, and standard deviation (of
    149 all vectors) `sd`, where the total sample size is `n` and the number of
    150 populations is `k`.
    151 
    152 ### jStat.qtest( array1, array2, sd, n, k )
    153 
    154 Same as above, but the means and sizes are calculated automatically
    155 from the arrays.
    156 
    157 ### jStat.tukeyhsd( arrays )
    158 
    159 Performs the full Tukey's range test returning p-values for every
    160 pairwise combination of the arrays in the format of
    161 `[[[index1, index2], pvalue], ...]`
    162 
    163 For example:
    164 
    165     > jStat.tukeyhsd([[1, 2], [3, 4, 5], [6], [7, 8]])
    166     [ [ [ 0, 1 ], 0.10745283896120883 ],
    167       [ [ 0, 2 ], 0.04374051946838586 ],
    168       [ [ 0, 3 ], 0.007850804224287633 ],
    169       [ [ 1, 2 ], 0.32191548545694226 ],
    170       [ [ 1, 3 ], 0.03802747415485819 ],
    171       [ [ 2, 3 ], 0.5528665999257486 ] ]
    172 
    173 ## Confidence Intervals
    174 
    175 ### jStat.normalci( value, alpha, sd, n )
    176 
    177 Returns a 1-alpha confidence interval for `value` given
    178 a normal distribution with a standard deviation `sd` and a
    179 sample size `n`
    180 
    181 ### jStat.normalci( value, alpha, array )
    182 
    183 Returns a 1-alpha confidence interval for `value` given
    184 a normal distribution in the data from `array`.
    185 
    186 ### jStat.tci( value, alpha, sd, n )
    187 
    188 Returns a 1-alpha confidence interval for `value` given
    189 the standard deviation `sd` and the sample size `n`.
    190 
    191 ### jStat.tci( value, alpha, array )
    192 
    193 Returns a 1-alpha confidence interval for `value` given
    194 the data from `array`.
    195 
    196 ### jStat.fn.oneSidedDifferenceOfProportions( p1, n1, p2, n2 )
    197 
    198 Returns the p-value for a 1-sided test for the difference
    199 between two proportions. `p1` is the sample proportion for
    200 the first sample, whereas `p2` is the sample proportion for
    201 the second sample. Similiarly, `n1` is the sample size of the
    202 first sample and `n2` is the sample size for the second sample.
    203 
    204 ### jStat.fn.twoSidedDifferenceOfProportions( p1, n1, p2, n2 )
    205 
    206 Returns the p-value for a 2-sided test for the difference
    207 between two proportions. `p1` is the sample proportion for
    208 the first sample, whereas `p2` is the sample proportion for
    209 the second sample. Similiarly, `n1` is the sample size of the
    210 first sample and `n2` is the sample size for the second sample.