0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
2 .\"
|
|
3 .\" Standard preamble:
|
|
4 .\" ========================================================================
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
6 .if t .sp .5v
|
|
7 .if n .sp
|
|
8 ..
|
|
9 .de Vb \" Begin verbatim text
|
|
10 .ft CW
|
|
11 .nf
|
|
12 .ne \\$1
|
|
13 ..
|
|
14 .de Ve \" End verbatim text
|
|
15 .ft R
|
|
16 .fi
|
|
17 ..
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
23 .\" nothing in troff, for use with C<>.
|
|
24 .tr \(*W-
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
26 .ie n \{\
|
|
27 . ds -- \(*W-
|
|
28 . ds PI pi
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
31 . ds L" ""
|
|
32 . ds R" ""
|
|
33 . ds C` ""
|
|
34 . ds C' ""
|
|
35 'br\}
|
|
36 .el\{\
|
|
37 . ds -- \|\(em\|
|
|
38 . ds PI \(*p
|
|
39 . ds L" ``
|
|
40 . ds R" ''
|
|
41 'br\}
|
|
42 .\"
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
45 .el .ds Aq '
|
|
46 .\"
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
50 .\" output yourself in some meaningful fashion.
|
|
51 .ie \nF \{\
|
|
52 . de IX
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
54 ..
|
|
55 . nr % 0
|
|
56 . rr F
|
|
57 .\}
|
|
58 .el \{\
|
|
59 . de IX
|
|
60 ..
|
|
61 .\}
|
|
62 .\"
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
65 . \" fudge factors for nroff and troff
|
|
66 .if n \{\
|
|
67 . ds #H 0
|
|
68 . ds #V .8m
|
|
69 . ds #F .3m
|
|
70 . ds #[ \f1
|
|
71 . ds #] \fP
|
|
72 .\}
|
|
73 .if t \{\
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
75 . ds #V .6m
|
|
76 . ds #F 0
|
|
77 . ds #[ \&
|
|
78 . ds #] \&
|
|
79 .\}
|
|
80 . \" simple accents for nroff and troff
|
|
81 .if n \{\
|
|
82 . ds ' \&
|
|
83 . ds ` \&
|
|
84 . ds ^ \&
|
|
85 . ds , \&
|
|
86 . ds ~ ~
|
|
87 . ds /
|
|
88 .\}
|
|
89 .if t \{\
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
96 .\}
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
107 . \" corrections for vroff
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
112 \{\
|
|
113 . ds : e
|
|
114 . ds 8 ss
|
|
115 . ds o a
|
|
116 . ds d- d\h'-1'\(ga
|
|
117 . ds D- D\h'-1'\(hy
|
|
118 . ds th \o'bp'
|
|
119 . ds Th \o'LP'
|
|
120 . ds ae ae
|
|
121 . ds Ae AE
|
|
122 .\}
|
|
123 .rm #[ #] #H #V #F C
|
|
124 .\" ========================================================================
|
|
125 .\"
|
|
126 .IX Title "STATISTICSUTIL 1"
|
|
127 .TH STATISTICSUTIL 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
129 .\" way too many mistakes in technical documents.
|
|
130 .if n .ad l
|
|
131 .nh
|
|
132 .SH "NAME"
|
|
133 StatisticsUtil
|
|
134 .SH "SYNOPSIS"
|
|
135 .IX Header "SYNOPSIS"
|
|
136 use StatisticsUtil;
|
|
137 .PP
|
|
138 use Statistics qw(:all);
|
|
139 .SH "DESCRIPTION"
|
|
140 .IX Header "DESCRIPTION"
|
|
141 \&\fBStatisticsUtil\fR module provides the following functions:
|
|
142 .PP
|
|
143 Average, AverageDeviation, Correlation, Covariance, Euclidean, Factorial,
|
|
144 FactorialDivison, Frequency, GeometricMean, HarmonicMean, KLargest, KSmallest,
|
|
145 Kurtosis, Maximum, Mean, Median, Minimum, Mode, PearsonCorrelation, Permutations,
|
|
146 Product, RSquare, Range, Skewness, StandardDeviation, StandardDeviationN,
|
|
147 StandardError, StandardScores, StandardScoresN, Standardize, Sum, SumOfSquares,
|
|
148 TrimMean, Variance, VarianceN
|
|
149 .SS "\s-1METHODS\s0"
|
|
150 .IX Subsection "METHODS"
|
|
151 .IP "\fBAverage\fR" 4
|
|
152 .IX Item "Average"
|
|
153 .Vb 1
|
|
154 \& $Value = Average(\e@DataArray);
|
|
155 .Ve
|
|
156 .Sp
|
|
157 Computes the mean of an array of numbers: \s-1SUM\s0( x[i] ) / n
|
|
158 .IP "\fBAverageDeviation\fR" 4
|
|
159 .IX Item "AverageDeviation"
|
|
160 .Vb 1
|
|
161 \& $Value = AverageDeviation(\e@DataArray);
|
|
162 .Ve
|
|
163 .Sp
|
|
164 Computes the average of the absolute deviation of an array of numbers: \s-1SUM\s0( \s-1ABS\s0(x[i] \- Xmean) ) / n
|
|
165 .IP "\fBCorrelation\fR" 4
|
|
166 .IX Item "Correlation"
|
|
167 .Vb 1
|
|
168 \& $Value = Correlation(\e@XDataArray, \e@YDataArray);
|
|
169 .Ve
|
|
170 .Sp
|
|
171 Computes the Pearson correlation coefficient between two arrays of numbers:
|
|
172 \&\s-1SUM\s0( (x[i] \- Xmean)(y[i] \- Ymean) ) / \s-1SQRT\s0( \s-1SUM\s0( (x[i] \- Xmean)^2 )(\s-1SUM\s0( (y[i] \- Ymean)^2 )) )
|
|
173 .IP "\fBEuclidean\fR" 4
|
|
174 .IX Item "Euclidean"
|
|
175 .Vb 1
|
|
176 \& $Return = Euclidean(\e@DataArray);
|
|
177 .Ve
|
|
178 .Sp
|
|
179 Computes the euclidean distance of an array of numbers: \s-1SQRT\s0( \s-1SUM\s0( x[i] ** 2) )
|
|
180 .IP "\fBCovariance\fR" 4
|
|
181 .IX Item "Covariance"
|
|
182 .Vb 1
|
|
183 \& $Value = Covariance(\e@XDataArray, \e@YDataArray);
|
|
184 .Ve
|
|
185 .Sp
|
|
186 Computes the covariance between two arrays of numbers: \s-1SUM\s0( (x[i] \- Xmean) (y[i] \- Ymean) ) / n
|
|
187 .IP "\fBFactorial\fR" 4
|
|
188 .IX Item "Factorial"
|
|
189 .Vb 1
|
|
190 \& $Value = Factorial($Num);
|
|
191 .Ve
|
|
192 .Sp
|
|
193 Computes the factorial of a positive integer.
|
|
194 .IP "\fBFactorialDivison\fR" 4
|
|
195 .IX Item "FactorialDivison"
|
|
196 .Vb 1
|
|
197 \& $Value = FactorialDivision($Numerator, $Denominator);
|
|
198 .Ve
|
|
199 .Sp
|
|
200 Compute the factorial divison of two positive integers.
|
|
201 .IP "\fBFrequency\fR" 4
|
|
202 .IX Item "Frequency"
|
|
203 .Vb 2
|
|
204 \& %FrequencyValues = Frequency(\e@DataArray, [$NumOfBins]);
|
|
205 \& %FrequencyValues = Frequency(\e@DataArray, [\e@BinRange]);
|
|
206 .Ve
|
|
207 .Sp
|
|
208 A hash array is returned with keys and values representing range and frequency values, respectively.
|
|
209 The frequency value for a specific key corresponds to all the values which are greater than
|
|
210 the previous key and less than or equal to the current key. A key value representing maximum value is
|
|
211 added for generating frequency distribution for specific number of bins, and whenever the maximum
|
|
212 array value is greater than the maximum specified in bin range, it is also added to bin range.
|
|
213 .IP "\fBGeometricMean\fR" 4
|
|
214 .IX Item "GeometricMean"
|
|
215 .Vb 1
|
|
216 \& $Value = GeometricMean(\e@DataArray);
|
|
217 .Ve
|
|
218 .Sp
|
|
219 Computes the geometric mean of an array of numbers: NthROOT( \s-1PRODUCT\s0(x[i]) )
|
|
220 .IP "\fBHarmonicMean\fR" 4
|
|
221 .IX Item "HarmonicMean"
|
|
222 .Vb 1
|
|
223 \& $Value = HarmonicMean(\e@DataArray);
|
|
224 .Ve
|
|
225 .Sp
|
|
226 Computes the harmonic mean of an array of numbers: 1 / ( \s-1SUM\s0(1/x[i]) / n )
|
|
227 .IP "\fBKLargest\fR" 4
|
|
228 .IX Item "KLargest"
|
|
229 .Vb 1
|
|
230 \& $Value = KLargest(\e@DataArray, $KthNumber);
|
|
231 .Ve
|
|
232 .Sp
|
|
233 Returns the k\-largest value from an array of numbers.
|
|
234 .IP "\fBKSmallest\fR" 4
|
|
235 .IX Item "KSmallest"
|
|
236 .Vb 1
|
|
237 \& $Value = KSmallest(\e@DataArray, $KthNumber);
|
|
238 .Ve
|
|
239 .Sp
|
|
240 Returns the k\-smallest value from an array of numbers.
|
|
241 .IP "\fBKurtosis\fR" 4
|
|
242 .IX Item "Kurtosis"
|
|
243 .Vb 1
|
|
244 \& $Value = Kurtosis(\e@DataArray);
|
|
245 .Ve
|
|
246 .Sp
|
|
247 Computes the kurtosis of an array of numbers:
|
|
248 [ {n(n + 1)/(n \- 1)(n \- 2)(n \- 3)} SUM{ ((x[i] \- Xmean)/STDDEV)^4 } ] \- {3((n \- 1)^2)}/{(n \- 2)(n\-3)}
|
|
249 .IP "\fBMaximum\fR" 4
|
|
250 .IX Item "Maximum"
|
|
251 .Vb 1
|
|
252 \& $Value = Maximum(\e@DataArray);
|
|
253 .Ve
|
|
254 .Sp
|
|
255 Returns the largest value from an array of numbers.
|
|
256 .IP "\fBMinimum\fR" 4
|
|
257 .IX Item "Minimum"
|
|
258 .Vb 1
|
|
259 \& $Value = Minimum(\e@DataArray);
|
|
260 .Ve
|
|
261 .Sp
|
|
262 Returns the smallest value from an array of numbers.
|
|
263 .IP "\fBMean\fR" 4
|
|
264 .IX Item "Mean"
|
|
265 .Vb 1
|
|
266 \& $Value = Mean(\e@DataArray);
|
|
267 .Ve
|
|
268 .Sp
|
|
269 Computes the mean of an array of numbers: \s-1SUM\s0( x[i] ) / n
|
|
270 .IP "\fBMedian\fR" 4
|
|
271 .IX Item "Median"
|
|
272 .Vb 1
|
|
273 \& $Value = Median(\e@DataArray);
|
|
274 .Ve
|
|
275 .Sp
|
|
276 Computes the median value of an array of numbers. For an even number array, it's
|
|
277 the average of two middle values.
|
|
278 .Sp
|
|
279 For even values of n: Xsorted[(n \- 1)/2 + 1]
|
|
280 For odd values of n: (Xsorted[n/2] + Xsorted[n/2 + 1])/2
|
|
281 .IP "\fBMode\fR" 4
|
|
282 .IX Item "Mode"
|
|
283 .Vb 1
|
|
284 \& $Value = Mode(\e@DataArray);
|
|
285 .Ve
|
|
286 .Sp
|
|
287 Returns the most frequently occuring value in an array of numbers.
|
|
288 .IP "\fBPearsonCorrelation\fR" 4
|
|
289 .IX Item "PearsonCorrelation"
|
|
290 .Vb 1
|
|
291 \& $Value = Correlation(\e@XDataArray, \e@YDataArray);
|
|
292 .Ve
|
|
293 .Sp
|
|
294 Computes the Pearson correlation coefficient between two arrays of numbers:
|
|
295 \&\s-1SUM\s0( (x[i] \- Xmean)(y[i] \- Ymean) ) / \s-1SQRT\s0( \s-1SUM\s0( (x[i] \- Xmean)^2 )(\s-1SUM\s0( (y[i] \- Ymean)^2 )) )
|
|
296 .IP "\fBPermutations\fR" 4
|
|
297 .IX Item "Permutations"
|
|
298 .Vb 1
|
|
299 \& $PermutationsRef = Permutations(@DataToPermute);
|
|
300 .Ve
|
|
301 .Sp
|
|
302 Generate all possible permuations or a specific permutations of items in an array
|
|
303 and return a reference to an array containing array references to generated permuations.
|
|
304 .Sp
|
|
305 This alogrithm is based on the example provided by Mark Jason-Dominus, and is available
|
|
306 at \s-1CPAN\s0 as mjd_permute standalone script.
|
|
307 .IP "\fBProduct\fR" 4
|
|
308 .IX Item "Product"
|
|
309 .Vb 1
|
|
310 \& $Value = Product(\e@DataArray);
|
|
311 .Ve
|
|
312 .Sp
|
|
313 Compute the product of an array of numbers.
|
|
314 .IP "\fBRange\fR" 4
|
|
315 .IX Item "Range"
|
|
316 .Vb 1
|
|
317 \& ($Smallest, $Largest) = Range(\e@DataArray);
|
|
318 .Ve
|
|
319 .Sp
|
|
320 Return the smallest and largest values from an array of numbers.
|
|
321 .IP "\fBRSquare\fR" 4
|
|
322 .IX Item "RSquare"
|
|
323 .Vb 1
|
|
324 \& $Value = RSquare(\e@XDataArray, \e@YDataArray);
|
|
325 .Ve
|
|
326 .Sp
|
|
327 Computes square of the Pearson correlation coefficient between two arrays of numbers.
|
|
328 .IP "\fBSkewness\fR" 4
|
|
329 .IX Item "Skewness"
|
|
330 .Vb 1
|
|
331 \& $Value = Skewness(\e@DataArray);
|
|
332 .Ve
|
|
333 .Sp
|
|
334 Computes the skewness of an array of numbers:
|
|
335 {n/(n \- 1)(n \- 2)} SUM{ ((x[i] \- Xmean)/STDDEV)^3 }
|
|
336 .IP "\fBStandardDeviation\fR" 4
|
|
337 .IX Item "StandardDeviation"
|
|
338 .Vb 1
|
|
339 \& $Value = StandardDeviation(\e@DataArray);
|
|
340 .Ve
|
|
341 .Sp
|
|
342 Computes the standard deviation of an array of numbers.
|
|
343 \&\s-1SQRT\s0 ( \s-1SUM\s0( (x[i] \- mean)^2 ) / (n \- 1) )
|
|
344 .IP "\fBStandardDeviationN\fR" 4
|
|
345 .IX Item "StandardDeviationN"
|
|
346 .Vb 1
|
|
347 \& $Value = StandardDeviationN(\e@DataArray);
|
|
348 .Ve
|
|
349 .Sp
|
|
350 Computes the standard deviation of an array of numbers representing entire population:
|
|
351 \&\s-1SQRT\s0 ( \s-1SUM\s0( (x[i] \- mean)^2 ) / n )
|
|
352 .IP "\fBStandardError\fR" 4
|
|
353 .IX Item "StandardError"
|
|
354 .Vb 1
|
|
355 \& $Value = StandardError($StandardDeviation, $Count);
|
|
356 .Ve
|
|
357 .Sp
|
|
358 Computes the standard error using standard deviation and sample size.
|
|
359 .IP "\fBStandardize\fR" 4
|
|
360 .IX Item "Standardize"
|
|
361 .Vb 1
|
|
362 \& $Value = Standardize($Value, $Mean, $StandardDeviation);
|
|
363 .Ve
|
|
364 .Sp
|
|
365 Standardizes the value using mean and standard deviation.
|
|
366 .IP "\fBStandardScores\fR" 4
|
|
367 .IX Item "StandardScores"
|
|
368 .Vb 1
|
|
369 \& @Values = StandardScores(\e@DataArray);
|
|
370 .Ve
|
|
371 .Sp
|
|
372 Computes the standard deviation above the mean for an array of numbers:
|
|
373 (x[i] \- mean) / (n \- 1)
|
|
374 .IP "\fBStandardScoresN\fR" 4
|
|
375 .IX Item "StandardScoresN"
|
|
376 .Vb 1
|
|
377 \& @Values = StandardScoresN(\e@DataArray);
|
|
378 .Ve
|
|
379 .Sp
|
|
380 Computes the standard deviation above the mean for an array of numbers representing entire population:
|
|
381 (x[i] \- mean) / n
|
|
382 .IP "\fBSum\fR" 4
|
|
383 .IX Item "Sum"
|
|
384 .Vb 1
|
|
385 \& $Value = Sum(\e@DataArray);
|
|
386 .Ve
|
|
387 .Sp
|
|
388 Compute the sum of an array of numbers.
|
|
389 .IP "\fBSumOfSquares\fR" 4
|
|
390 .IX Item "SumOfSquares"
|
|
391 .Vb 1
|
|
392 \& $Value = SumOfSquares(\e@DataArray);
|
|
393 .Ve
|
|
394 .Sp
|
|
395 Computes the sum of an array of numbers.
|
|
396 .IP "\fBTrimMean\fR" 4
|
|
397 .IX Item "TrimMean"
|
|
398 .Vb 1
|
|
399 \& $Value = TrimMean(\e@DataArray, $FractionToExclude));
|
|
400 .Ve
|
|
401 .Sp
|
|
402 Computes the mean of an array of numbers by excluding a fraction of
|
|
403 numbers from the top and bottom of the data set.
|
|
404 .IP "\fBVariance\fR" 4
|
|
405 .IX Item "Variance"
|
|
406 .Vb 1
|
|
407 \& $Value = Variance(\e@DataArray);
|
|
408 .Ve
|
|
409 .Sp
|
|
410 Computes the variance of an array of numbers: \s-1SUM\s0( (x[i] \- Xmean)^2 / (n \- 1) )
|
|
411 .IP "\fBVarianceN\fR" 4
|
|
412 .IX Item "VarianceN"
|
|
413 .Vb 1
|
|
414 \& $Value = Variance(\e@DataArray);
|
|
415 .Ve
|
|
416 .Sp
|
|
417 Compute the variance of an array of numbers representing entire population:
|
|
418 \&\s-1SUM\s0( (x[i] \- Xmean)^2 / n )
|
|
419 .SH "AUTHOR"
|
|
420 .IX Header "AUTHOR"
|
|
421 Manish Sud <msud@san.rr.com>
|
|
422 .SH "SEE ALSO"
|
|
423 .IX Header "SEE ALSO"
|
|
424 Constants.pm, ConversionsUtil.pm, MathUtil.pm
|
|
425 .SH "COPYRIGHT"
|
|
426 .IX Header "COPYRIGHT"
|
|
427 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
428 .PP
|
|
429 This file is part of MayaChemTools.
|
|
430 .PP
|
|
431 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
432 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
433 Software Foundation; either version 3 of the License, or (at your option)
|
|
434 any later version.
|