Skip to content

Commit ae5c67b

Browse files
gururaj1512kgryte
gururaj1512
and
kgryte
authored
feat: add stats/array/nanvarianceyc
PR-URL: #7671 Co-authored-by: Athan Reines <[email protected]> Reviewed-by: Athan Reines <[email protected]>
1 parent 472e0d6 commit ae5c67b

File tree

14 files changed

+1263
-0
lines changed

14 files changed

+1263
-0
lines changed

‎lib/node_modules/@stdlib/stats/array/nanvarianceyc/README.md

Lines changed: 204 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,204 @@
1+
<!--
2+
3+
@license Apache-2.0
4+
5+
Copyright (c) 2025 The Stdlib Authors.
6+
7+
Licensed under the Apache License, Version 2.0 (the "License");
8+
you may not use this file except in compliance with the License.
9+
You may obtain a copy of the License at
10+
11+
http://www.apache.org/licenses/LICENSE-2.0
12+
13+
Unless required by applicable law or agreed to in writing, software
14+
distributed under the License is distributed on an "AS IS" BASIS,
15+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16+
See the License for the specific language governing permissions and
17+
limitations under the License.
18+
19+
-->
20+
21+
# nanvarianceyc
22+
23+
> Calculate the [variance][variance] of an array ignoring `NaN` values and using a one-pass algorithm proposed by Youngs and Cramer.
24+
25+
<section class="intro">
26+
27+
The population [variance][variance] of a finite size population of size `N` is given by
28+
29+
<!-- <equation class="equation" label="eq:population_variance" align="center" raw="\sigma^2 = \frac{1}{N} \sum_{i=0}^{N-1} (x_i - \mu)^2" alt="Equation for the population variance."> -->
30+
31+
```math
32+
\sigma^2 = \frac{1}{N} \sum_{i=0}^{N-1} (x_i - \mu)^2
33+
```
34+
35+
<!-- <div class="equation" align="center" data-raw-text="\sigma^2 = \frac{1}{N} \sum_{i=0}^{N-1} (x_i - \mu)^2" data-equation="eq:population_variance">
36+
<img src="https://cdn.jsdelivr.net/gh/stdlib-js/stdlib@3d46f4ed82e7419980cddcbf29a4ee1305522e1a/lib/node_modules/@stdlib/stats/base/nanvarianceyc/docs/img/equation_population_variance.svg" alt="Equation for the population variance.">
37+
<br>
38+
</div> -->
39+
40+
<!-- </equation> -->
41+
42+
where the population mean is given by
43+
44+
<!-- <equation class="equation" label="eq:population_mean" align="center" raw="\mu = \frac{1}{N} \sum_{i=0}^{N-1} x_i" alt="Equation for the population mean."> -->
45+
46+
```math
47+
\mu = \frac{1}{N} \sum_{i=0}^{N-1} x_i
48+
```
49+
50+
<!-- <div class="equation" align="center" data-raw-text="\mu = \frac{1}{N} \sum_{i=0}^{N-1} x_i" data-equation="eq:population_mean">
51+
<img src="https://cdn.jsdelivr.net/gh/stdlib-js/stdlib@3d46f4ed82e7419980cddcbf29a4ee1305522e1a/lib/node_modules/@stdlib/stats/base/nanvarianceyc/docs/img/equation_population_mean.svg" alt="Equation for the population mean.">
52+
<br>
53+
</div> -->
54+
55+
<!-- </equation> -->
56+
57+
Often in the analysis of data, the true population [variance][variance] is not known _a priori_ and must be estimated from a sample drawn from the population distribution. If one attempts to use the formula for the population [variance][variance], the result is biased and yields a **biased sample variance**. To compute an **unbiased sample variance** for a sample of size `n`,
58+
59+
<!-- <equation class="equation" label="eq:unbiased_sample_variance" align="center" raw="s^2 = \frac{1}{n-1} \sum_{i=0}^{n-1} (x_i - \bar{x})^2" alt="Equation for computing an unbiased sample variance."> -->
60+
61+
```math
62+
s^2 = \frac{1}{n-1} \sum_{i=0}^{n-1} (x_i - \bar{x})^2
63+
```
64+
65+
<!-- <div class="equation" align="center" data-raw-text="s^2 = \frac{1}{n-1} \sum_{i=0}^{n-1} (x_i - \bar{x})^2" data-equation="eq:unbiased_sample_variance">
66+
<img src="https://cdn.jsdelivr.net/gh/stdlib-js/stdlib@3d46f4ed82e7419980cddcbf29a4ee1305522e1a/lib/node_modules/@stdlib/stats/base/nanvarianceyc/docs/img/equation_unbiased_sample_variance.svg" alt="Equation for computing an unbiased sample variance.">
67+
<br>
68+
</div> -->
69+
70+
<!-- </equation> -->
71+
72+
where the sample mean is given by
73+
74+
<!-- <equation class="equation" label="eq:sample_mean" align="center" raw="\bar{x} = \frac{1}{n} \sum_{i=0}^{n-1} x_i" alt="Equation for the sample mean."> -->
75+
76+
```math
77+
\bar{x} = \frac{1}{n} \sum_{i=0}^{n-1} x_i
78+
```
79+
80+
<!-- <div class="equation" align="center" data-raw-text="\bar{x} = \frac{1}{n} \sum_{i=0}^{n-1} x_i" data-equation="eq:sample_mean">
81+
<img src="https://cdn.jsdelivr.net/gh/stdlib-js/stdlib@3d46f4ed82e7419980cddcbf29a4ee1305522e1a/lib/node_modules/@stdlib/stats/base/nanvarianceyc/docs/img/equation_sample_mean.svg" alt="Equation for the sample mean.">
82+
<br>
83+
</div> -->
84+
85+
<!-- </equation> -->
86+
87+
The use of the term `n-1` is commonly referred to as Bessel's correction. Note, however, that applying Bessel's correction can increase the mean squared error between the sample variance and population variance. Depending on the characteristics of the population distribution, other correction factors (e.g., `n-1.5`, `n+1`, etc) can yield better estimators.
88+
89+
</section>
90+
91+
<!-- /.intro -->
92+
93+
<section class="usage">
94+
95+
## Usage
96+
97+
```javascript
98+
var nanvarianceyc = require( '@stdlib/stats/array/nanvarianceyc' );
99+
```
100+
101+
#### nanvarianceyc( x\[, correction] )
102+
103+
Computes the variance of an array ignoring `NaN` values and using a one-pass algorithm proposed by Youngs and Cramer.
104+
105+
```javascript
106+
var x = [ 1.0, -2.0, NaN, 2.0 ];
107+
108+
var v = nanvarianceyc( x );
109+
// returns ~4.3333
110+
```
111+
112+
The function has the following parameters:
113+
114+
- **x**: input array.
115+
- **correction**: degrees of freedom adjustment. Setting this parameter to a value other than `0` has the effect of adjusting the divisor during the calculation of the [variance][variance] according to `N-c` where `N` corresponds to the number of array elements and `c` corresponds to the provided degrees of freedom adjustment. When computing the [variance][variance] of a population, setting this parameter to `0` is the standard choice (i.e., the provided array contains data constituting an entire population). When computing the unbiased sample [variance][variance], setting this parameter to `1` is the standard choice (i.e., the provided array contains data sampled from a larger population; this is commonly referred to as Bessel's correction). Default: `1.0`.
116+
117+
By default, the function computes the sample [variance][variance]. To adjust the degrees of freedom when computing the [variance][variance], provide a `correction` argument.
118+
119+
```javascript
120+
var x = [ 1.0, -2.0, NaN, 2.0 ];
121+
122+
var v = nanvarianceyc( x, 0.0 );
123+
// returns ~2.8889
124+
```
125+
126+
</section>
127+
128+
<!-- /.usage -->
129+
130+
<section class="notes">
131+
132+
## Notes
133+
134+
- If provided an empty array, the function returns `NaN`.
135+
- If provided a `correction` argument which is greater than or equal to the number of elements in a provided input array, the function returns `NaN`.
136+
- The function supports array-like objects having getter and setter accessors for array element access (e.g., [`@stdlib/array/base/accessor`][@stdlib/array/base/accessor]).
137+
138+
</section>
139+
140+
<!-- /.notes -->
141+
142+
<section class="examples">
143+
144+
## Examples
145+
146+
<!-- eslint no-undef: "error" -->
147+
148+
```javascript
149+
var uniform = require( '@stdlib/random/base/uniform' );
150+
var filledarrayBy = require( '@stdlib/array/filled-by' );
151+
var bernoulli = require( '@stdlib/random/base/bernoulli' );
152+
var nanvarianceyc = require( '@stdlib/stats/array/nanvarianceyc' );
153+
154+
function rand() {
155+
if ( bernoulli( 0.8 ) < 1 ) {
156+
return NaN;
157+
}
158+
return uniform( -50.0, 50.0 );
159+
}
160+
161+
var x = filledarrayBy( 10, 'generic', rand );
162+
console.log( x );
163+
164+
var v = nanvarianceyc( x );
165+
console.log( v );
166+
```
167+
168+
</section>
169+
170+
<!-- /.examples -->
171+
172+
* * *
173+
174+
<section class="references">
175+
176+
## References
177+
178+
- Youngs, Edward A., and Elliot M. Cramer. 1971. "Some Results Relevant to Choice of Sum and Sum-of-Product Algorithms." _Technometrics_ 13 (3): 657–65. doi:[10.1080/00401706.1971.10488826][@youngs:1971a].
179+
180+
</section>
181+
182+
<!-- /.references -->
183+
184+
<!-- Section for related `stdlib` packages. Do not manually edit this section, as it is automatically populated. -->
185+
186+
<section class="related">
187+
188+
</section>
189+
190+
<!-- /.related -->
191+
192+
<!-- Section for all links. Make sure to keep an empty line after the `section` element and another before the `/section` close. -->
193+
194+
<section class="links">
195+
196+
[variance]: https://en.wikipedia.org/wiki/Variance
197+
198+
[@youngs:1971a]: https://doi.org/10.1080/00401706.1971.10488826
199+
200+
[@stdlib/array/base/accessor]: https://github.com/stdlib-js/stdlib/tree/develop/lib/node_modules/%40stdlib/array/base/accessor
201+
202+
</section>
203+
204+
<!-- /.links -->

‎lib/node_modules/@stdlib/stats/array/nanvarianceyc/benchmark/benchmark.js

Lines changed: 104 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,104 @@
1+
/**
2+
* @license Apache-2.0
3+
*
4+
* Copyright (c) 2025 The Stdlib Authors.
5+
*
6+
* Licensed under the Apache License, Version 2.0 (the "License");
7+
* you may not use this file except in compliance with the License.
8+
* You may obtain a copy of the License at
9+
*
10+
* http://www.apache.org/licenses/LICENSE-2.0
11+
*
12+
* Unless required by applicable law or agreed to in writing, software
13+
* distributed under the License is distributed on an "AS IS" BASIS,
14+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15+
* See the License for the specific language governing permissions and
16+
* limitations under the License.
17+
*/
18+
19+
'use strict';
20+
21+
// MODULES //
22+
23+
var bench = require( '@stdlib/bench' );
24+
var uniform = require( '@stdlib/random/base/uniform' );
25+
var bernoulli = require( '@stdlib/random/base/bernoulli' );
26+
var filledarrayBy = require( '@stdlib/array/filled-by' );
27+
var isnan = require( '@stdlib/math/base/assert/is-nan' );
28+
var pow = require( '@stdlib/math/base/special/pow' );
29+
var pkg = require( './../package.json' ).name;
30+
var nanvarianceyc = require( './../lib' );
31+
32+
33+
// FUNCTIONS //
34+
35+
/**
36+
* Returns a random value or `NaN`.
37+
*
38+
* @private
39+
* @returns {number} random number or `NaN`
40+
*/
41+
function rand() {
42+
if ( bernoulli( 0.8 ) < 1 ) {
43+
return NaN;
44+
}
45+
return uniform( -10.0, 10.0 );
46+
}
47+
48+
/**
49+
* Creates a benchmark function.
50+
*
51+
* @private
52+
* @param {PositiveInteger} len - array length
53+
* @returns {Function} benchmark function
54+
*/
55+
function createBenchmark( len ) {
56+
var x = filledarrayBy( len, 'generic', rand );
57+
return benchmark;
58+
59+
function benchmark( b ) {
60+
var v;
61+
var i;
62+
63+
b.tic();
64+
for ( i = 0; i < b.iterations; i++ ) {
65+
v = nanvarianceyc( x, 1.0 );
66+
if ( isnan( v ) ) {
67+
b.fail( 'should not return NaN' );
68+
}
69+
}
70+
b.toc();
71+
if ( isnan( v ) ) {
72+
b.fail( 'should not return NaN' );
73+
}
74+
b.pass( 'benchmark finished' );
75+
b.end();
76+
}
77+
}
78+
79+
80+
// MAIN //
81+
82+
/**
83+
* Main execution sequence.
84+
*
85+
* @private
86+
*/
87+
function main() {
88+
var len;
89+
var min;
90+
var max;
91+
var f;
92+
var i;
93+
94+
min = 1; // 10^min
95+
max = 6; // 10^max
96+
97+
for ( i = min; i <= max; i++ ) {
98+
len = pow( 10, i );
99+
f = createBenchmark( len );
100+
bench( pkg+':len='+len, f );
101+
}
102+
}
103+
104+
main();

‎lib/node_modules/@stdlib/stats/array/nanvarianceyc/docs/img/equation_population_mean.svg

Lines changed: 42 additions & 0 deletions
Loading

0 commit comments

Comments
 (0)