Debian Codegraph @

texmf-dist/source/latex/linearregression/linearregression.dtx

raw
1 %\iffalse
2 % file: linearregression.dtx
3 % author: Battista Benciolini
4 % contact: benciolinibattista at gmail dot com
5 %
6 % process this file with pdflatex to obtain:
7 %
8 % - linearregression.pfd (full documentation, three pass needed)
9 % - mainlinearregression.tex (interactive main-program document)
10 % - linearregression.sty (package)
11 % - sampledata.txt (as the name says)
12 %
13 % The author would strongly appreciate to receive
14 % any comment, criticism and just usage report
15 %
16 %\fi
17 %\iffalse
18 %<*ins>
19 \begingroup
20 \input docstrip.tex
21 \keepsilent
22 \preamble
23 ------------------------------------------------------------------------
24 [2025-11-08]
25 This file is part of the (expanded) distribution of linearregression
26 The author of linearregression is Battista Benciolini
27 <benciolinibattista at gmail dot com >
28 ------------------------------------------------------------------------
29 The author would strongly appreciate to receive
30 any comment, criticism and just usage report
31 ------------------------------------------------------------------------
32 This program may be used, distributed and modified under
33 the conditions of the LaTeX Project Public License.
34 (see: http://www.latex-project.org/lppl.txt)
35 ------------------------------------------------------------------------
36 \endpreamble
37 \askforoverwritefalse
38 \generate{\file{linearregression.sty}{\from{linearregression.dtx}{package}}}
39 \generate{\file{mainlinearregression.tex}{\from{linearregression.dtx}{main}}}
40 \nopreamble\nopostamble
41 \generate{\file{sampledata.txt}{\from{linearregression.dtx}{data}}}
42 \endgroup
43 %</ins>
44 %\fi
45 %\iffalse
46 %<*driver>
47 \documentclass[a4paper,10pt]{ltxdoc}
48 \usepackage[T1]{fontenc}
49 \usepackage{lmodern}
50 \usepackage[lite,nobysame,non-compressed-cites]{amsrefs}
51 \usepackage{amsmath,amssymb,amsfonts}
52 \usepackage{multicol}
53 \usepackage{linearregression}
54 \usepackage{graphics}
55 \DeclareRobustCommand*{\Ars}{\textsf{%
56 \lower -.48ex\hbox{\rotatebox{-20}{A}}\kern -.3em{rs}}%
57 \discretionary{-}{}{\kern -.05em}\TeX\discretionary{-}{}{%
58 \kern -.17em}\lower -.357ex\hbox{nica}}% excerpt from some GUIT sty file
59 %%\NewDocumentCommand\vect{m}{\underline{#1}} % vector
60 %%\NewDocumentCommand\matr{m}{{#1}} % matrix
61 \NewDocumentCommand\vect{m}{\mathbf{#1}} % vector
62 \NewDocumentCommand\matr{m}{\mathbf{#1}} % matrix
63 \NewDocumentCommand\barycenter{m}{\overline{#1}} % barycenter
64 \NewDocumentCommand\point{}{\vect{y}} % point
65 \NewDocumentCommand\coeff{}{\vect{x}} % direction
66 \NewDocumentCommand\dx{}{\vect\delta} % direction variation
67 \NewDocumentCommand\vv{}{\vect{v}} % barycentric coordinates
68 \NewDocumentCommand\trasp{}{^{\mathsf{T}}} % traspose
69 \NewDocumentCommand\Renne{}{\mathbb{R}^n} % vector space
70 \NewDocumentCommand\dor{}{f} % distance from origin
71 \NewDocumentCommand\ipoint{}{i} % index for points
72 \NewDocumentCommand\pointsum{}{\sum_{\ipoint=1}^m} % sum over points
73 \NewDocumentCommand\reff{m}{(\ref{#1})} % ref in ( )
74 \NewDocumentCommand\mC{}{\matr{C}} % matrix C
75 \NewDocumentCommand\mc{}{k} % elements of matrix C
76 \NewDocumentCommand\mL{}{\matr{\Lambda}} % matrix lambda
77 \NewDocumentCommand\mX{}{\matr{X}} % matrix X
78 \NewDocumentCommand\spm{}{\phantom{-}} % space for the sign
79 \NewDocumentCommand\ctext{}{caption} % caption (a variable !)
80 \NewDocumentCommand\matrixtwotwo{mmmm}{ % | 2 x 2
81 \begin{pmatrix} #1 & #2 \\ #3 & #4 \end{pmatrix}} % | matrix
82 \DeclareMathOperator\tr{tr} % trace
83 \DeclareMathOperator\sgn{sgn} % signum
84 \title{Linear regression with \LaTeX}
85 \author{Battista Benciolini}
86 \NewDocumentCommand\titleauthorfootnote{}{\begingroup% Not an elegant solution
87 \let\thefootnote\relax % but it is ok at the moment
88 \footnote{Linear regression with LaTeX - available in CTAN}%
89 \footnote{Battista Benciolini - contact: benciolinibattista at gmail dot com}%
90 \endgroup\setcounter{footnote}{0}}%
91 \parindent=0pt
92 \begin{document}
93 \hypersetup{hidelinks}
94 \maketitle
95 \titleauthorfootnote
96 \tableofcontents
97 \vfill
98 \DocInput{linearregression.dtx}
99 \end{document}
100 %</driver>
101 %\fi
102 %
103 % \section{Introduction: first description of the problem\label{intro}}
104 % I start with a quote from \Ars\ (April 2021, number 31, page 73):
105 % \begin{quotation}
106 % The physicist Mario Rossi is investigating a phenomenon,
107 % presumably linear, and he performs measurements in his laboratory
108 % to verify his hypothesis; he measures the quantity $x$ which generates
109 % the phenomenon and he measures also one of the characteristics
110 % $y$ showed by the phenomenon under the effect of the stimulation $x$.
111 % \\ ... \par
112 % Subsequently Mario graphs the data of the table to judge if the points
113 % reasonably follow a linear trend or not; in this regard he computes the
114 % parameters of the regression line and he draws this line on the graph
115 % in order to judge the quality of the obtained results.
116 % \\ ... \par
117 % Being a \LaTeX\ user, he thinks to kill two birds with one stone:
118 % using \LaTeX\ to draw the graph with the experimental data consisting
119 % in the $x$, $y$ points and, at the same time, to compute the
120 % parameter $a$ e $b$ of the regression line $y = ax+b$,
121 % and finally to draw also this line on the same graph.
122 % \end{quotation}
123 % A summary description of the problem is therefore the following.
124 % A set of data pairs is available and each pair is represented as a point
125 % in the plane. A straight line is searched that optimally approximates
126 % the points. The first step is therefore the choice of an optimality criterion.
127 % This choice is the topic of the next section. \par
128 % From the text we also know that the possible deviation of $y$
129 % with respect to the model is quite larger than the deviation of $x$.
130 % \par
131 % After reading the description of the problem
132 % of Mario Rossi I tried to produce a solution.
133 % In this work I will use $y_1$ and $y_2$
134 % instead of $x$ and $y$ for the two measured quantities that
135 % will become the first and second coordinate, or abscissa and ordinate,
136 % in the Cartesian plane.
137 % \par
138 % The problem can be treated as a mere problem of approximation or
139 % alternatively as an estimation problem in the frame of a
140 % probabilistic description of the uncertainty. The two treatments are
141 % conceptually different. The probabilistic treatment produces some more
142 % results, but the estimation of the parameters is the same.
143 % On the other hand the treatment as an approximation problem is in some sense
144 % more immediate and requires a less extended theoretical background.
145 % For this reason it will be preferred here.
146 % I consider the original problem and also a variation
147 % of it based on the assumption that the two variables are known with
148 % the same uncertainty. The two considered situations will prove
149 % to be quite different.
150 %
151 % \section{Geometric definition of three optimality criteria}
152 % \begin{figure}
153 % \setlength\unitlength{4cm}
154 % \begin{picture}(1, 0.7)(0.,0.)
155 % \multiput(0.,0.)(1.1,0){3}{\line(1,0){1}}
156 % \multiput(0.,0.)(1.1,0){3}{\line(0,1){1}}
157 % \multiput(1,1)(1.1,0){3}{\line(-1,0){1}}
158 % \multiput(1,1)(1.1,0){3}{\line(0,-1){1}}
159 % \thicklines
160 % \multiput(0.08,0.06)(1.1,0){3}{\line(4,3){0.88}}
161 % \multiput(0.26,0.09)(1.1,0){3}{\circle{0.03}}
162 % \multiput(0.45,0.65)(1.1,0){3}{\circle{0.03}}
163 % \multiput(0.92,0.44)(1.1,0){3}{\circle{0.03}}
164 % \put(0.26,0.09){\line(0,1){0.1050}}
165 % \put(0.45,0.65){\line(0,-1){0.3125}}
166 % \put(0.92,0.44){\line(0,1){0.2500}}
167 % \put(1.36,0.09){\line(-1,0){0.14}}
168 % \put(1.55,0.65){\line( 1,0){0.4167}}
169 % \put(2.02,0.44){\line(-1,0){0.3333}}
170 % \put(2.46,0.09){\line(-3,4){0.05}}
171 % \put(2.65,0.65){\line(3,-4){0.15}}
172 % \put(3.12,0.44){\line(-3,4){0.12}}
173 % \end{picture}
174 % \caption{The three kinds of segments
175 % used in the definition of the objective function}
176 % \label{fig:criteria}
177 % \end{figure}
178 % For each point given in the plane we can consider the corresponding point
179 % with the same abscissa and belonging to the line.
180 % Remember that the line is exactly what has to be determined.
181 % The distance between the given point and the just defined point on the line
182 % is a reasonable measure of the discrepancy between the empirical data and the
183 % corresponding theoretical model.
184 % The distances we are speaking about are the lengths of the segments shown
185 % in the leftmost scheme of figure (\ref{fig:criteria}).
186 % To obtain a global discrepancy measure that considers all the points
187 % at once we perform the sum of the squares of the lengths
188 % of the mentioned segments. It is now clear that the two coordinates
189 % of the points are treated quite differently and play a different role in
190 % the definition of the optimality criterion. This choice is reasonable when
191 % the measuring errors only (or mainly) affect the second coordinate.
192 % The optimal line is the line that minimize the just defined
193 % global discrepancy. The procedure for the determination of the optimal line
194 % is named linear regression.
195 % In this work it is named \textit{classical linear regression}.
196 % We can easily exchange the role of the two quantities, i.e.\ we can
197 % imagine that the first quantity is affected by errors.
198 % The problem is not conceptually different. The segments plotted in the
199 % central picture
200 % of figure (\ref{fig:criteria}) represent the discrepancy between
201 % the empirical data and the model.
202 % This other procedure is named \textit{classical linear regression
203 % with inverted role of the coordinates}.\par
204 % The situation is really different if the two coordinates have to be treated
205 % symmetrically.
206 % In this case the discrepancy between
207 % the empirical data and the model must be defined in a purely geometrical way.
208 % Just the line and the points enter in the definition without any special role
209 % for any predefined direction. With these requirements it is quite natural
210 % to use the distance of each point from the line.
211 % Remember that the distance of a point
212 % from a line is intended along the shortest path, i.e.\ measured in the
213 % direction orthogonal to the line itself. The rightmost scheme of
214 % figure (\ref{fig:criteria}) shows the segments that are considered.
215 % The global measure of discrepancy is again obtained as the sum
216 % of the squares of the lengts of the mentioned orthogonal segments.
217 % The procedure that obtain the optimal line that
218 % minimize the just defined global discrepancy is named
219 % \textit{symmetrical linear regression}.\par
220 % Some arguments of the present section will be repeated in section
221 % \ref{package} from the algebraic and computational point of view.
222 %
223 % \section{Information on the realised solution, including limitations}
224 % The code that implements the solution is recorded in two files, that are
225 % a package (sty) file and a main interactive document.
226 % The file |linearregression.sty| provides several commands
227 % that can be used in any document. The file |mainlinearregression.tex|
228 % provides a simple interactive user interface.
229 % The package described in the sections \ref{manual} and
230 % \ref{package} (user manual and implementation) provides the
231 % functions that execute the various needed operations, i.e.\
232 % data input, computations, printing the numerical results and
233 % generating a graphic representation of data and results.
234 % Some auxiliary functions complete the package.
235 % The design of the output (tables and plots) includes some arbitrary choices.
236 % The style of the graphic output is quite minimalist
237 % (e.g.:\ no colors, no variations of line styles).\par
238 %
239 % \section{Some comments about the programming of the package}
240 % Large part of the code is written using the |expl3| language.
241 % I have tried to be compliant with the various recommendations and
242 % prescriptions for a correct use of the language,
243 % but I probably only partly succeeded.\par
244 % Different more elegant and more coherent solutions probably exist
245 % both for the general structure of the package and for some specific part
246 % of the code, but this is what I have been able to do.
247 % Some perhaps problematic aspects are mentioned here after.\par
248 % Several used variables are global and they are accessed by various functions.
249 % This makes the various parts of the package
250 % quite connected to each other and creates strong dependencies. \par
251 % The layered programming style is only partially applied.
252 % The partition between document command and lower level functions is present,
253 % but part of the low level code is directly in the document commands.
254 % Variants are not used.
255 %
256 % \section{A ready to use simple user interface\label{main}}
257 % The main file asks the user for the name of a
258 % file containing the data and generates a one page output.
259 %\iffalse
260 %<*main>
261 %\fi
262 % \begin{macrocode}
263 \documentclass[a4paper]{article}
264 \usepackage{lmodern}
265 \usepackage{linearregression}
266 \begin{document}
267 \pagestyle{empty}
268 \lraskfilename
269 \lrcomputation
270 \lrplotparameters{0.16}{11.0}
271 \lrplot{11.0}{+}{+}{-}{-}
272 \lrprint
273 \end{document}
274 % \end{macrocode}
275 %\iffalse
276 %</main>
277 %\fi
278 % The plot just includes the points and the line obtained with the classical
279 % linear regression. Lines 8 and 9 of the code must be modified if a different
280 % result is desired. See the next section for details.
281 %
282 % \section{A user manual for the package\label{manual}}
283 % The various analysis of a data set and the representation of the data
284 % and of the results is obtained with a sequence of several commands.
285 % The main operations are:
286 % (i) selection of the data file, (ii) data imput and computation,
287 % (iii) printing of a table,
288 % (iv) printing of a picture (that can be repeated with different parameters).
289 % It is generally convenient to put the table and the picture(s)
290 % in a proper floating environment.
291 % The commands for the four mentioned operations are described here after.
292 % The first needed operation is to set the name of the data file.
293 % This is done with the command \DescribeMacro{\lrfilename}
294 % \cs{lrfilename}\marg{file} that has a mandatory argument.
295 % The argument is the name of the data file. As an alternative the
296 % command \DescribeMacro{\lraskfilename} \cs{lraskfilename} can be used.
297 % It asks the user to type the name of the data file in the terminal.
298 % \par
299 % The macro \DescribeMacro{\lrcomputation}
300 % \cs{lrcomputation} reads the data
301 % and performs all the computations.
302 % The results of the computations remain available in internal
303 % variables and are then used by the macro that print them
304 % or generates a plot.
305 %\par
306 % The macro \DescribeMacro{\lrprint}
307 % \cs{lrprint} generates a table with all the estimated
308 % parameters and some information about the data.
309 % The computed numbers are printed with four decimal digit maximum by default,
310 % but this number can be set to any desired value with the command
311 % \DescribeMacro{\lrnumdigit} \cs{lrnumdigit}\marg{number}.
312 % The mandatory argument is the desired maximum number of digits.
313 % \par
314 % The macro \DescribeMacro{\lrplot}
315 % \cs{lrplot}\marg{imagewidth}\marg{key1}\marg{key2}\marg{key3}\marg{key4}
316 % really generates the plot. The first argument is the
317 % width of the plot in centimetrs, while the height is computed according
318 % to the distribution of the points or it is recorded with the command
319 % \cs{lrplotparameters} (see below).
320 % The other four arguments are referred
321 % to the data points, to the lines determined with classical regression,
322 % with classical regression with inverted role of the coordinates and
323 % with symmetric regression.
324 % The four items, i.e.\ the set of points and the three lines, are drawn
325 % or not according to the corresponding string found in |key|$i$.
326 % Each item is not plotted if the string is the character |-|, it is plotted
327 % in any other case. Furthermore the lines are accompanied by a label made
328 % by the corresponding |key|, unless it is just a |+| or a |-|.
329 % \par
330 % The command \DescribeMacro{\lrplotparameters}
331 % \cs{lrplotparameters}\marg{diameter}\marg{imageheight}
332 % is used to record some more parameters that are related to the generation
333 % of the plot.
334 % The first argument \marg{diameter} is the diameter in centimeters of the discs
335 % that represent the points. It must be a real positive number.
336 % The default value is 0.2.
337 % The second argument \marg{imageheight} is the height of the plot
338 % in centimeters.
339 % It must be a real number with a special meaning of any non positive value.
340 % If the number is positive it is really used as the height and the variables are
341 % independently scaled to fill the width and the height of the plot.
342 % If the value is not positive or if the command is not used the
343 % two variables are scaled with the same factor and the height is computed
344 % accordingly. This can generate reasonable results only if the ranges
345 % of the two variables are not too much different.
346 % All the arguments are mandatory.
347 % \par
348 % The use of \cs{lrnumdigit} and \cs{lrplotparameters} is a convenient solution
349 % to introduce some flexibility in the output and to completely preserve
350 % compatibility with the previous version of the package.
351 % Some more elegant solution could be realized with the use of optional
352 % arguments and perhaps of key-value pairs, but the implemented solution
353 % is preferred because it is extremely simple.
354 % \par
355 % Few words are necessary about the format of the data file.
356 % Each record of the file hold the two values related to a point.
357 % The two values must be separated by any number (one is needed as a minimum) of
358 % space and comma characters. No character different from space
359 % can be accepted before the first value and after the second value.
360 %
361 % \section{An example\label{example}}
362 % The data reported here after will be available in |sampledata.txt|
363 % and will be used in the examples presented in this section .
364 %\iffalse
365 %<*data>
366 %\fi
367 % \begin{multicols}{4}
368 % \begin{macrocode}
369 -0.546 0.107
370 1.093 -0.510
371 1.440 1.995
372 1.414 0.991
373 0.735 1.585
374 -1.848 -0.235
375 -0.203 -0.292
376 1.517 0.779
377 0.559 -1.341
378 -0.462 -0.437
379 -0.785 -0.661
380 -0.558 0.397
381 0.181 -2.616
382 0.619 1.859
383 -0.223 -1.915
384 0.629 -0.534
385 -1.989 -2.300
386 -0.241 1.098
387 -0.931 -1.613
388 -1.070 0.592
389 2.341 0.413
390 1.993 -0.111
391 -2.357 -0.312
392 -1.975 0.140
393 % \end{macrocode}
394 % \end{multicols}
395 %\iffalse
396 %</data>
397 %\fi
398 %
399 % The analysis of the sample data and the generation of a numeric table
400 % is operated by a code similar to the following
401 % (see table \ref{tab:sampledata}). \\
402 % |\lrfilename{sampledata.txt}| \\ |\lrcomputation| \\
403 % |\lrnumdigit{5}| \\ |\begin{table}| \\
404 % | \lrprint| \\
405 % | \caption{Analysis of ... }| \\ |\label{tab:sampledata}\end{table}|
406 % \par
407 % The generation of some different graphical representation of the data and of
408 % the results is operated by a code similar to the following
409 % (see figures \ref{fig:sampledataB} ).\\
410 % \RenewDocumentCommand\ctext{}{LEFT The three lines are obtained with the three
411 % optimality criteria. (AA) classical linear regression; (BB) classical linear
412 % regression with inverted role of the coordinates; (S) symmetric linear
413 % regression. RIGHT Data points and line estimated with
414 % symmetric linear regression.}
415 % |\begin{figure}|\\|\lrplot{10.}{-}{AA}{BB}{S}| \\
416 % |\lrplot{10.}{+}{-}{-}{+}|
417 % \\ |\caption{|\ctext|}|\\ | \label{fig:sampledataB} \end{figure}|
418 %
419 % \lrfilename{sampledata.txt} \lrcomputation \lrnumdigit{5}
420 % \begin{table} \lrprint \caption{Analysis of the sample data}
421 % \label{tab:sampledata} \end{table}
422 % \begin{figure} \lrplot{6.}{-}{AA}{BB}{S} \hfill \lrplot{6.}{+}{-}{-}{+}
423 % \caption{\ctext} \label{fig:sampledataB} \end{figure}
424 % The same data are used to show the effect of the command
425 % \cs{lrplotparameters}.
426 % \begin{figure}
427 % \lrplotparameters{0.12}{5.} \lrplot{4.}{+}{-}{-}{+} \hfill
428 % \lrplotparameters{0.10}{3.} \lrplot{4.}{+}{-}{-}{+} \hfill
429 % \lrplotparameters{0.11}{-1.} \lrplot{4.}{+}{-}{-}{+}
430 % \caption{Three different version of a plot to demonstrate the use of
431 % the command \cs{lrplotparameters}} \label{fig:sampledataC} \end{figure}
432 % The commands:\\ |...| \\
433 % |\lrplotparameters{0.12}{5.} \lrplot{4.}{+}{-}{-}{+} \hfill | \\
434 % |\lrplotparameters{0.10}{3.} \lrplot{4.}{+}{-}{-}{+} \hfill | \\
435 % |\lrplotparameters{0.11}{-1.} \lrplot{4.}{+}{-}{-}{+} | \\ |...| \\
436 % generate the figure (\ref{fig:sampledataC}).
437 %
438 % \section{A package for linear regression
439 % and the theory behind it\label{package}}
440 %\iffalse
441 %<*package>
442 %\fi
443 %
444 % \subsection{Math preliminaries and notation \label{prelim}}
445 % The coordinates of a set of $m$ points on the plane are available.
446 % A straight line is searched that optimally approximates the points.\par
447 % The coordinates of a generic point are $y_1$ and $y_2$
448 % and they are collected in the vector $\point$.
449 % Any given point is identified with the index $\ipoint$.
450 % Explicit indices $(\dots)_1$ or $(\dots)_2$ always refer to the first
451 % or second coordinate of a point or to the first or second component
452 % of a vector in the plane.
453 % Symbolic index $(\dots)\ipoint$ always refers to the different points. Few
454 % formulas require both indices $(\dots)_{1\ipoint}$, $(\dots)_{2\ipoint}$.\par
455 % With more then two points a criterion of best approximation
456 % is needed to select the optimal line that describes the data. \par
457 % Lower case symbols are used for scalars. Lower case bold
458 % symbols are used for vectors in the plane. Upper case bold symbols
459 % are used for matrices.
460 % \par
461 % It is possible that certain data generate an ambiguity or a singularity
462 % in the computation.
463 % The following mathematical treatment of the problem
464 % do not mention these situations and the code does not deal with them.
465 %
466 % \subsection{Package declaration, required package and definition of variables}
467 % The various macro will be provided in a package file
468 % that is introduced as usual. Most of the macros require
469 % the \LaTeX3 syntax.
470 % \begin{macrocode}
471 \ProvidesPackage{linearregression}[2025-11-08]
472 \RequirePackage{pict2e}
473 \ExplSyntaxOn
474 % \end{macrocode}
475 % The variables used in the package are defined hereafter.
476 % \begin{macrocode}
477 \ior_new:N \g_BBLR_file_ior
478 \tl_new:N \g_BBLR_file_name_tl
479 \int_new:N \g_BBLR_number_of_points_int
480 \fp_new:N \g_BBLR_abscissa_fp
481 \fp_new:N \g_BBLR_ordinate_fp
482 \fp_new:N \g_BBLR_mean_abscissa_fp
483 \fp_new:N \g_BBLR_mean_ordinate_fp
484 \fp_new:N \g_BBLR_abscissa_SecOrdMoment_fp
485 \fp_new:N \g_BBLR_ordinate_SecOrdMoment_fp
486 \fp_new:N \g_BBLR_mixed_SecOrdMoment_fp
487 \fp_new:N \g_BBLR_slope_A_fp
488 \fp_new:N \g_BBLR_slope_B_fp
489 \fp_new:N \g_BBLR_slope_S_fp
490 \fp_new:N \g_BBLR_intercept_A_fp
491 \fp_new:N \g_BBLR_intercept_B_fp
492 \fp_new:N \g_BBLR_intercept_S_fp
493 \fp_new:N \g_BBLR_cos_fp
494 \fp_new:N \g_BBLR_sin_fp
495 \fp_new:N \g_BBLR_sig_sin_fp
496 \fp_new:N \g_BBLR_eig_diff_fp
497 \fp_new:N \g_BBLR_diag_diff_fp
498 \tl_new:N \g_BBLR_file_line_tl
499 \fp_new:N \g_BBLR_min_abscissa_fp
500 \fp_new:N \g_BBLR_min_ordinate_fp
501 \fp_new:N \g_BBLR_max_abscissa_fp
502 \fp_new:N \g_BBLR_max_ordinate_fp
503 \fp_new:N \g_BBLR_min_draw_abscissa_fp
504 \fp_new:N \g_BBLR_max_draw_abscissa_fp
505 \bool_new:N \g_BBLR_data_eof_bool
506 \int_new:N \g_BBLR_record_length_int
507 \int_new:N \g_BBLR_rec_count_int
508 \int_new:N \g_BBLR_first_separator_int
509 \int_new:N \g_BBLR_last_separator_int
510 \str_const:Nn \c_BBLR_space_str {~}
511 \str_const:Nn \c_BBLR_comma_str {,}
512 \str_const:Nn \c_BBLR_plus_str {+}
513 \str_const:Nn \c_BBLR_minus_str {-}
514 \bool_new:N \g_BBLR_plot_points_bool
515 \bool_new:N \g_BBLR_plot_lineA_bool
516 \bool_new:N \g_BBLR_plot_lineB_bool
517 \bool_new:N \g_BBLR_plot_lineS_bool
518 \bool_new:N \g_BBLR_two_scale_bool
519 \bool_gset_false:N \g_BBLR_two_scale_bool
520 \fp_new:N \g_BBLR_base_fp
521 \fp_new:N \g_BBLR_height_fp
522 \fp_new:N \g_BBLR_Xbase_fp
523 \fp_new:N \g_BBLR_Xheight_fp
524 \fp_new:N \g_BBLR_XXheight_fp
525 \fp_new:N \g_BBLR_Dabscissa_fp
526 \fp_new:N \g_BBLR_Dordinate_fp
527 \fp_new:N \g_BBLR_diameter_fp
528 \fp_gset:Nn \g_BBLR_diameter_fp{0.2}
529 \fp_new:N \g_BBLR_line_base_length_fp
530 \fp_new:N \g_BBLR_scale_factor_fp
531 \fp_new:N \g_BBLR_scale_factor_H_fp
532 \str_new:N \g_BBLR_point_code_str
533 \str_new:N \g_BBLR_labelA_str
534 \str_new:N \g_BBLR_labelB_str
535 \str_new:N \g_BBLR_labelS_str
536 \int_new:N \g_BBLR_num_dec_dig_int
537 \int_gset:Nn \g_BBLR_num_dec_dig_int{4}
538 % \end{macrocode}
539 %
540 % \subsection{Preparing data input}
541 % \begin{macro}{\lrfilename}
542 % The command \cs{lrfilename} records the file name passed as argument.
543 % \begin{macrocode}
544 \NewDocumentCommand{\lrfilename}{m}{
545 \tl_gset:Nn \g_BBLR_file_name_tl {#1}
546 }
547 % \end{macrocode}
548 % \end{macro}
549 % \begin{macro}{\lraskfilename}
550 % The command \cs{lraskfilename} asks for the data file name from the terminal.
551 % \begin{macrocode}
552 \NewDocumentCommand{\lraskfilename}{}{
553 \ior_get_term:nN {filename ? } \g_BBLR_file_name_tl
554 \tl_trim_spaces:N \g_BBLR_file_name_tl
555 }
556 % \end{macrocode}
557 % \end{macro}
558 %
559 % \subsection{Computation}
560 % \begin{macro}{\lrcomputation}
561 % The command \cs{lrcomputation} reads the data file and
562 % performs all the relevant computations to solve the
563 % proposed problem.
564 % \begin{macrocode}
565 \NewDocumentCommand{\lrcomputation}{}{%
566 % \end{macrocode}
567 %
568 % \subsubsection{Computation of first and second order moments}
569 % In the sequel it will results that the first and second order moments
570 % of the data provide everything needed to solve the problem.
571 % The barycenter of the data is defined as
572 % \begin{equation}
573 % \barycenter{\point}=\frac{1}{m}\pointsum \point_\ipoint.
574 % \label{barycenter} \end{equation}
575 % It is convenient to scan the data to accumulate the sum
576 % that appears in \reff{barycenter}.
577 % The coordinates of each point are read from the file
578 % and they are immediately used. The data are not globally recorded.
579 % \begin{macrocode}
580 \bool_gset_false:N \g_BBLR_data_eof_bool
581 \int_zero:N \g_BBLR_number_of_points_int
582 \fp_zero:N \g_BBLR_mean_abscissa_fp
583 \fp_zero:N \g_BBLR_mean_ordinate_fp
584 \ior_open:Nn \g_BBLR_file_ior \g_BBLR_file_name_tl
585 \bool_until_do:Nn \g_BBLR_data_eof_bool {
586 \ior_str_get:NN \g_BBLR_file_ior \g_BBLR_file_line_tl
587 \if_eof:w \g_BBLR_file_ior
588 \bool_gset_true:N \g_BBLR_data_eof_bool
589 \else:
590 \int_incr:N \g_BBLR_number_of_points_int
591 \BBLR_decode_data:
592 \fp_gset:Nn \g_BBLR_mean_abscissa_fp
593 {\g_BBLR_mean_abscissa_fp + \g_BBLR_abscissa_fp}
594 \fp_gset:Nn \g_BBLR_mean_ordinate_fp
595 {\g_BBLR_mean_ordinate_fp + \g_BBLR_ordinate_fp}
596 \fi:
597 }
598 % \end{macrocode}
599 % Loop ended. Now close the file,
600 % globally set the value of the number of points
601 % and divide the accumulated sums by the number of points.
602 % \begin{macrocode}
603 \int_gset:Nn \g_BBLR_number_of_points_int {\g_BBLR_number_of_points_int}
604 \ior_close:N \g_BBLR_file_ior
605 \fp_gset:Nn \g_BBLR_mean_abscissa_fp
606 {\g_BBLR_mean_abscissa_fp / \g_BBLR_number_of_points_int}
607 \fp_gset:Nn \g_BBLR_mean_ordinate_fp
608 {\g_BBLR_mean_ordinate_fp / \g_BBLR_number_of_points_int}
609 % \end{macrocode}
610 %
611 % The barycentric coordinates are defined for each point
612 % \begin{equation} \vv_\ipoint= \point_\ipoint - \barycenter{\point}
613 % \label{residual} \end{equation}
614 % and the empirical dispersion matrix is defined as:
615 % \begin{equation} \mC=\frac{1}{m}\pointsum \vv_\ipoint\vv_\ipoint\trasp .
616 % \label{matrixC} \end{equation}
617 % Superscript as in $()\trasp$ means transpose. The elements of $\mC$ are the
618 % second order central moments and they are denoted as:
619 % \begin{equation} \mC=\matrixtwotwo{\mc_{11}}{\mc_{12}}{\mc_{12}}{\mc_{22}}.
620 % \label{matrixCc} \end{equation}
621 % A second scan of the data is performed to compute the
622 % sums that appears in \reff{matrixC} and to determine the
623 % extremal values of the coordinates. Record scan can be regulated
624 % by a record counter, because the number of points is now known.
625 % \begin{macrocode}
626 \fp_zero:N \g_BBLR_abscissa_SecOrdMoment_fp
627 \fp_zero:N \g_BBLR_ordinate_SecOrdMoment_fp
628 \fp_zero:N \g_BBLR_mixed_SecOrdMoment_fp
629 \fp_gset_eq:NN \g_BBLR_min_abscissa_fp \g_BBLR_mean_abscissa_fp
630 \fp_gset_eq:NN \g_BBLR_min_ordinate_fp \g_BBLR_mean_ordinate_fp
631 \fp_gset_eq:NN \g_BBLR_max_abscissa_fp \g_BBLR_mean_abscissa_fp
632 \fp_gset_eq:NN \g_BBLR_max_ordinate_fp \g_BBLR_mean_ordinate_fp
633 \ior_open:Nn \g_BBLR_file_ior \g_BBLR_file_name_tl
634 \int_zero:N \g_BBLR_rec_count_int
635 \int_do_until:nn
636 {\g_BBLR_rec_count_int = \g_BBLR_number_of_points_int}
637 {
638 \ior_str_get:NN \g_BBLR_file_ior \g_BBLR_file_line_tl
639 \int_incr:N \g_BBLR_rec_count_int
640 \BBLR_decode_data:
641 \fp_gset:Nn \g_tmpa_fp
642 {\g_BBLR_abscissa_fp - \g_BBLR_mean_abscissa_fp}
643 \fp_gset:Nn \g_tmpb_fp
644 {\g_BBLR_ordinate_fp - \g_BBLR_mean_ordinate_fp}
645 \fp_gset:Nn \g_BBLR_abscissa_SecOrdMoment_fp
646 {\g_BBLR_abscissa_SecOrdMoment_fp + \g_tmpa_fp * \g_tmpa_fp}
647 \fp_gset:Nn \g_BBLR_mixed_SecOrdMoment_fp
648 {\g_BBLR_mixed_SecOrdMoment_fp + \g_tmpa_fp * \g_tmpb_fp}
649 \fp_gset:Nn \g_BBLR_ordinate_SecOrdMoment_fp
650 {\g_BBLR_ordinate_SecOrdMoment_fp + \g_tmpb_fp * \g_tmpb_fp}
651 \fp_gset:Nn \g_BBLR_min_abscissa_fp
652 {min(\g_BBLR_min_abscissa_fp, \g_BBLR_abscissa_fp)}
653 \fp_gset:Nn \g_BBLR_min_ordinate_fp
654 {min(\g_BBLR_min_ordinate_fp, \g_BBLR_ordinate_fp)}
655 \fp_gset:Nn \g_BBLR_max_abscissa_fp
656 {max(\g_BBLR_max_abscissa_fp, \g_BBLR_abscissa_fp)}
657 \fp_gset:Nn \g_BBLR_max_ordinate_fp
658 {max(\g_BBLR_max_ordinate_fp, \g_BBLR_ordinate_fp)}
659 }
660 \ior_close:N \g_BBLR_file_ior
661 \fp_gset:Nn \g_BBLR_abscissa_SecOrdMoment_fp
662 {\g_BBLR_abscissa_SecOrdMoment_fp / \g_BBLR_number_of_points_int}
663 \fp_gset:Nn \g_BBLR_mixed_SecOrdMoment_fp
664 {\g_BBLR_mixed_SecOrdMoment_fp / \g_BBLR_number_of_points_int}
665 \fp_gset:Nn \g_BBLR_ordinate_SecOrdMoment_fp
666 {\g_BBLR_ordinate_SecOrdMoment_fp / \g_BBLR_number_of_points_int}
667 \fp_gset:Nn \g_BBLR_Dabscissa_fp
668 {\g_BBLR_max_abscissa_fp - \g_BBLR_min_abscissa_fp }
669 \fp_gset:Nn \g_BBLR_Dordinate_fp
670 {\g_BBLR_max_ordinate_fp - \g_BBLR_min_ordinate_fp }
671 % \end{macrocode}
672 % A single pass algorithm exists, but it is numerically less stable.
673 %
674 % \subsubsection{Classical linear regression \label{classical}}
675 % A line in the plane is described by the equation
676 % \begin{equation} y_2=ay_1+b \label{eqab} \end{equation}
677 % that contains the parameters $a$ and $b$.
678 % For each point it is possible to define a distance or a discrepancy
679 % of the experimental data with respect to the model.
680 % In the given problem the second coordinate is much more affected by
681 % errors than the first coordinate. It is therefore reasonable
682 % to define the approximation error of each point as
683 % \begin{equation} e_\ipoint=y_{2\ipoint}-ay_{1\ipoint}-b
684 % \label{e}\end{equation}
685 % i.e.\ the difference between the empirical value $y_{2\ipoint}$
686 % and its model counterpart $ay_{1\ipoint}+b$.
687 % This leads to the already mentioned classical linear regression. In fact the
688 % absolute value of $e_\ipoint$ expressed in (\ref{e}) is the lenght
689 % of the segments shown in the leftmost scheeme of figure (\ref{fig:criteria}).
690 % The global discrepancy between the data and the model is measured by the
691 % least square objective function defined by:
692 % \begin{equation} \psi=\pointsum e_\ipoint^2 \label{psiab} \end{equation}
693 % and the parameters $a$ and $b$ will be determined
694 % just by the minimization of the function $\psi$ defined in \reff{psiab}.
695 % \par
696 % In the present treatment of the regression problem as a pure
697 % approximation problem the definition of $\psi$ in \reff{psiab}
698 % seams quite arbitrary. It is anyway a convenient choice.
699 % \par
700 % Expression \reff{e} can be rewritten in the different form
701 % \begin{equation}
702 % e_\ipoint=v_{2\ipoint}-av_{1\ipoint}+\barycenter{y}_2-a\barycenter{y}_1-b
703 % \label{e2}\end{equation}
704 % so that the function to be minimized can be expressed
705 % as the sum of two quadratic functions:
706 % \begin{equation}
707 % \psi=
708 % \pointsum (v_{2\ipoint}-av_{1\ipoint})^2+
709 % m(\barycenter{y}_2-a\barycenter{y}_1-b)^2
710 % \label{psiab2} \end{equation}
711 % and the minimum can be attained considering
712 % the two terms one at a time.
713 % The second term in the right-hand side of \reff{psiab2}
714 % vanishes if the choice of $b$ is:
715 % \begin{equation} b=\barycenter{y}_2-a\barycenter{y}_1.
716 % \label{estb} \end{equation}
717 % The first term in the right-hand side of \reff{psiab2} becomes:
718 % \begin{equation} \psi_{(a)}=m\left(\mc_{22}-2a\mc_{12}+a^2\mc_{11}\right).
719 % \label{parabola} \end{equation}
720 % Searching the minimum of $\psi$ w.r.t.\ $a$ is therefore the search
721 % of the abscissa of the vertex of a parabola
722 % with axis parallel to the second coordinated axis.
723 % The result is:
724 % \begin{equation} a=\mc_{12}/\mc_{11}
725 % \label{esta} \end{equation}
726 % Now the slope $a$ and the intercept $b$ can be actually computed.
727 % \begin{macrocode}
728 \fp_gset:Nn \g_BBLR_slope_A_fp
729 {\g_BBLR_mixed_SecOrdMoment_fp / \g_BBLR_abscissa_SecOrdMoment_fp }
730 \fp_gset:Nn \g_BBLR_intercept_A_fp
731 {\g_BBLR_mean_ordinate_fp - \g_BBLR_slope_A_fp * \g_BBLR_mean_abscissa_fp}
732 % \end{macrocode}
733 % \par
734 % The empirical data and the estimated values of $a$ and $b$
735 % can be used to compute
736 % the value actually attained by the residuals $e_\ipoint$ and
737 % by the function $\psi$. Then the index
738 % \begin{equation} \hat\sigma_0^2=\psi/(m-2)\end{equation}
739 % can be used to evaluate the general quality of the data and of the model.
740 % This claim is clearly quite generic. A complete understanding
741 % of this evaluation would require to treat the linear regression
742 % problem in the framework of the probabilistic estimation theory.
743 % The used notation is derived from that theory.\par
744 % If the role of the two coordinates is exchanged the result
745 % for $a$ becomes (still with reference to \reff{eqab})
746 % \begin{equation} a=\mc_{22}/\mc_{12}.\end{equation}
747 % The slope and the intercept can be computed accordingly.
748 % \begin{macrocode}
749 \fp_gset:Nn \g_BBLR_slope_B_fp
750 {\g_BBLR_ordinate_SecOrdMoment_fp / \g_BBLR_mixed_SecOrdMoment_fp}
751 \fp_gset:Nn \g_BBLR_intercept_B_fp
752 {\g_BBLR_mean_ordinate_fp - \g_BBLR_slope_B_fp * \g_BBLR_mean_abscissa_fp}
753 % \end{macrocode}
754 %
755 % \subsubsection{Symmetric linear regression \label{symmetric}}
756 % If both the coordinates of the experimental points are affected
757 % by the same uncertainty it is advisable to use a more symmetric
758 % optimality criterion and it is convenient to use a different model equation.
759 % \par
760 % The same line can be described by a different equation, i.e.\
761 % \begin{equation} x_1y_1+x_2y_2=\dor \end{equation}
762 % or in vector form:
763 % \begin{equation} \coeff\trasp\point=\dor. \label{eqvx} \end{equation}
764 % The parameters in \reff{eqvx}
765 % are the scalar $\dor$ and the elements
766 % of the vector $\coeff$, i.e.\ $x_1$ and $x_2$.
767 % The line described by \reff{eqvx} is obviously
768 % invariant when the three parameters are simultaneously
769 % scaled by a constant. The normalization condition
770 % \begin{equation} \coeff\trasp\coeff=1, \label{norm} \end{equation}
771 % supplemented by $\dor\ge 0$,
772 % is quite convenient because the parameters will assume
773 % a significant geometrical meaning:
774 % $\coeff$ is a unit vector orthogonal to the line and $\dor$
775 % is the distance of the line from the origin.
776 % The expression
777 % \begin{equation} d=\dor-\coeff\trasp\point \label{distance} \end{equation}
778 % is the distance of the generic point $\point$ from the line
779 % with a sign that is positive for points on the same side of the origin.
780 % \par
781 % The distance of each given point from the desired optimal line
782 % is denoted by $d_\ipoint$.
783 % It has a clear intrinsic geometrical meaning and it does not
784 % privileges one coordinate w.r.t.\ the other.
785 % The function to be minimized by the optimal line is
786 % \begin{equation}
787 % \phi=\frac{1}{m}\pointsum d_\ipoint^2. \label{phi1} \end{equation}
788 % The parameters of \reff{eqvx} are determined by the minimization
789 % of the function $\phi$ that can be expressed as:
790 % \begin{equation}
791 % \phi=\frac{1}{m}\pointsum (\coeff\trasp\point_{\ipoint}-\dor)^{2}
792 % \label{phi2} \end{equation}
793 % and then, after some algebraic manipulations:
794 % \begin{equation}
795 % \phi=\coeff\trasp\mC\coeff+(\dor-\coeff\trasp\barycenter{\point})^2
796 % \label{phi3}. \end{equation}
797 % The function $\phi$ is composed (as it was the function $\psi$) by the sum
798 % of two parts. The second term in the right-hand side of \reff{phi3}
799 % vanishes if the choice of $\dor$ is:
800 % \begin{equation} \dor=\coeff\trasp\barycenter{\point}.
801 % \label{estd} \end{equation}
802 % Both (\ref{estb}) and (\ref{estd}) means that the optimal line includes
803 % the mean point.
804 % Then it is necessary to minimize the function
805 % \begin{equation} \phi_{(\coeff)} = \coeff\trasp\mC\coeff
806 % \label{quadraticfun} \end{equation}
807 % with the constrain $\coeff\trasp\coeff=1$.
808 % It can be proved that the function $\phi_{(\coeff)}$
809 % is stationary if $\coeff$ is an eigenvector of $\mC$. \par
810 % The function $\phi_{(\coeff)}$ and the constrain must be combined
811 % using a Lagrange multiplier:
812 % \begin{equation}
813 % \Phi= \coeff\trasp\mC\coeff+\lambda(1-\coeff\trasp\coeff).
814 % \label{Phi} \end{equation}
815 % Then the stationarity points of $\Phi$ must be determined.
816 % Equating to zero the derivatives of $\Phi$ gives
817 % \begin{equation}
818 % \mC\coeff=\lambda\coeff
819 % \label{auto} \end{equation}
820 % i.e.\ $\coeff$ is an eigenvector of $\mC$. \par
821 % The same result is obtained with the following argument.
822 % The function $\phi_{(\coeff)}$ is stationary if its first variation
823 % is zero. The variation of $\coeff$ is named $\dx$ .
824 % It must respect the constrain, that in linearized form becomes $\dx\trasp\coeff=0$.
825 % The first variation of $\phi_{(\coeff)}$ is $2\dx\trasp\mC\coeff$,
826 % and it is zero if and only if the following implication is valid:
827 % $\dx\trasp\coeff=0 \implies \dx\trasp\mC\coeff=0$,
828 % and the implication is valid if and only if the vector
829 % $\mC\coeff$ has the same direction of $\coeff$, i.e.\ if
830 % $\coeff$ is an eigenvector of $\mC$.
831 % \par
832 % The result on the optimal line
833 % can be described geometrically in the following way:
834 % (i) the optimal line includes the barycenter of the data;
835 % (ii) the optimal line is orthogonal to the eigenvector of
836 % $\mC$ corresponding to the minimum eigenvalue .\par
837 % The obtained result can be generalized in $\Renne$.
838 % A set of points in $\Renne$ must be approximated by an $(n-1)$-dimensional
839 % affine subspace. (Other more general situations can be considered.)
840 % \par
841 % The trace of the matrix $\mC$, denoted as $\tr(\mC)$, is a measure of the
842 % global dispersion of the set of points.
843 % The minimum eigenvalue $\lambda_{\textrm{min}}$ of $\mC$ is a measure
844 % of the dispersion of the set of points with
845 % respect to the optimal affine subspace. Therefore the index
846 % \begin{equation} \frac{n\lambda_{\textrm{min}}}{\tr(\mC)}
847 % \end{equation}
848 % can be used as an indicator of the relative residual
849 % dispersion of the data around the optimal affine subspace.
850 % The defined index is dimensionless and it is
851 % always between $0$ and $1$.
852 % \par
853 % For the actual computation of $\coeff$ it is convenient to consider
854 % the spectral factorization of the matrix $\mC$, i.e.\
855 % $\mC=\mX\mL\mX\trasp$ where $\mL$ is a diagonal matrix
856 % whose diagonal elements are the eigenvalues of $\mC$
857 % and $\mX$ is an orthonormal matrix whose columns are
858 % the eigenvectors of $\mC$. The spectral factorization exists
859 % for any symmetric matrix, but it is specially simple for
860 % a $2\times 2$ matrix.
861 % \begin{equation}
862 % \matrixtwotwo{\mc_{11}}{\mc_{12}}{\mc_{12}}{\mc_{22}}=
863 % \matrixtwotwo{c}{-s}{s}{\spm c}
864 % \matrixtwotwo{\lambda_1}{0}{0}{\lambda_2}
865 % \matrixtwotwo{\spm c}{s}{-s}{c}
866 % \label{spectral}\end{equation}
867 % The eigenvalues can be easily obtained because
868 % their sum is the trace of $\mC$
869 % \begin{equation}
870 % \lambda_1 + \lambda_2 = \mc_{11}+\mc_{22}
871 % \label{Sum}\end{equation}
872 % and their product
873 % is the determinant of the same matrix.
874 % Therefore after some manipulations it results:
875 % \begin{equation}
876 % \lambda_1 - \lambda_2 = \sqrt{(\mc_{11}-\mc_{22})^2+4\mc_{12}^2}
877 % \label{Difference}\end{equation}
878 % and the two eigenvalues are then immediately obtained. \par
879 % It is convenient to compute the difference of the two diagonal elements
880 % of the dispersion matrix and the difference of its eigenvalues.
881 % \begin{macrocode}
882 \fp_gset:Nn \g_BBLR_diag_diff_fp
883 {\g_BBLR_abscissa_SecOrdMoment_fp - \g_BBLR_ordinate_SecOrdMoment_fp}
884 \fp_gset:Nn \g_BBLR_eig_diff_fp
885 {sqrt(\g_BBLR_diag_diff_fp * \g_BBLR_diag_diff_fp +
886 4 * \g_BBLR_mixed_SecOrdMoment_fp * \g_BBLR_mixed_SecOrdMoment_fp)}
887 % \end{macrocode}
888 % The computation of $c$ and $s$ is obtained from \reff{spectral}
889 % taking into account that $c^2+s^2=1$.
890 % From \reff{spectral} it results:
891 % \begin{equation} \mc_{11}-\mc_{22}=(\lambda_1-\lambda_2)(c^2-s^2)
892 % \label{Cos2A}\end{equation}
893 % and also
894 % \begin{equation} \mc_{12}=(\lambda_1-\lambda_2)cs
895 % \label{Sin2A}\end{equation}
896 % that is only used to determine the sign of $cs$.
897 % The expression for the parameters $c$ and $s$ are:
898 % \begin{equation}
899 % c=\sqrt{\frac{1}{2}+\frac{\mc_{11}-\mc_{22}}{2(\lambda_1-\lambda_2)}}
900 % \label{cos}\end{equation}
901 % \begin{equation}
902 % s=\sgn(\mc_{12})
903 % \sqrt{\frac{1}{2}-\frac{\mc_{11}-\mc_{22}}{2(\lambda_1-\lambda_2)}}
904 % \label{sin}\end{equation}
905 % The parameters $s$ and $c$ are the sine and cosine
906 % of the angle between the axis of $y_1$ and the eigenvector
907 % corresponding to the maximum eigenvalue. \par
908 % They are computed using the already defined elements.
909 % \begin{macrocode}
910 \fp_gset:Nn \g_BBLR_cos_fp%
911 {sqrt((1 + \g_BBLR_diag_diff_fp / \g_BBLR_eig_diff_fp) / 2)}
912 \fp_gset:Nn \g_BBLR_sig_sin_fp {\fp_sign:n {\g_BBLR_mixed_SecOrdMoment_fp}}
913 \fp_gset:Nn \g_BBLR_sin_fp
914 {\g_BBLR_sig_sin_fp*sqrt((1-\g_BBLR_diag_diff_fp / \g_BBLR_eig_diff_fp) / 2)}
915 % \end{macrocode}
916 % The vector $\coeff$ is :
917 % \begin{equation}
918 % \coeff=\sgn(-s\barycenter{y}_1+c\barycenter{y}_2)
919 % \begin{pmatrix} -s \\ c\end{pmatrix}.
920 % \label{xhat}\end{equation}
921 %
922 %\par
923 % The parameter $a$ of model \reff{eqab} can be obtained as:
924 % \begin{equation}
925 % a=s/c
926 % \end{equation}
927 % Now the slope and the intercept of the optimal line corresponding to the
928 % symmetric criterion can be computed.
929 %
930 % \begin{macrocode}
931 \fp_gset:Nn \g_BBLR_slope_S_fp
932 {\g_BBLR_sin_fp / \g_BBLR_cos_fp }
933 \fp_gset:Nn \g_BBLR_intercept_S_fp
934 {\g_BBLR_mean_ordinate_fp -
935 \g_BBLR_slope_S_fp * \g_BBLR_mean_abscissa_fp}
936 }
937 % \end{macrocode}
938 %
939 % The theoretical treatment of the proposed problem and the
940 % implementation of its numerical solution end here.
941 % \end{macro}
942 %
943 % \subsection{Print of table of results}
944 % \begin{macro}{\lrprint}
945 % The command \cs{lrprint} prints some info on the data
946 % and the results of the computations in tabular form.
947 % \begin{macrocode}
948 \NewDocumentCommand{\lrprint}{}{
949 \begin{center}
950 \begin{tabular}{| l | r |} \hline
951 Data~File & \g_BBLR_file_name_tl \\
952 \hline
953 Number~of~points & \int_use:N\g_BBLR_number_of_points_int \\
954 \hline
955 Mean~values~of~the~coordinates &%
956 $\BBLR_print_fp:N \g_BBLR_mean_abscissa_fp$ \\ &
957 $\BBLR_print_fp:N \g_BBLR_mean_ordinate_fp$ \\ \hline
958 Minimum~values~of~the~coordinates &%
959 $\BBLR_print_fp:N \g_BBLR_min_abscissa_fp$ \\ &
960 $\BBLR_print_fp:N \g_BBLR_min_ordinate_fp$ \\ \hline
961 Maximum~values~of~the~coordinates &%
962 $\BBLR_print_fp:N \g_BBLR_max_abscissa_fp$ \\ &
963 $\BBLR_print_fp:N \g_BBLR_max_ordinate_fp$ \\ \hline
964 {Second~order~moments}\phantom{xxxxxxxxx}{abscissa} &%
965 $\BBLR_print_fp:N \g_BBLR_abscissa_SecOrdMoment_fp$ \\
966 \multicolumn{1}{|r|}{mixed} & %
967 $\BBLR_print_fp:N \g_BBLR_mixed_SecOrdMoment_fp$ ~ \\
968 \multicolumn{1}{|r|}{ordinate} & %
969 $\BBLR_print_fp:N \g_BBLR_ordinate_SecOrdMoment_fp$ \\ \hline
970 Slope~and~intercept~of~optimal~line & $\BBLR_print_fp:N
971 \g_BBLR_slope_A_fp$ \\
972 (estimated~with~errors~in~ordinate)&$\BBLR_print_fp:N
973 \g_BBLR_intercept_A_fp$\\ \hline
974 Slope~and~intercept~of~optimal~line & $\BBLR_print_fp:N
975 \g_BBLR_slope_B_fp$ \\
976 (estimated~with~errors~in~abscissa)&$\BBLR_print_fp:N
977 \g_BBLR_intercept_B_fp$\\ \hline
978 Unit~vector~along~the~line & $\BBLR_print_fp:N
979 \g_BBLR_cos_fp$ \\
980 & $\BBLR_print_fp:N \g_BBLR_sin_fp$ \\
981 Slope~and~intercept~of~optimal~line &$\BBLR_print_fp:N
982 \g_BBLR_slope_S_fp$ \\
983 (estimated~with~symmetric~regression) &
984 $\BBLR_print_fp:N \g_BBLR_intercept_S_fp$\\ \hline
985 \end{tabular}
986 \end{center}
987 }
988 % \end{macrocode}
989 % \end{macro}
990 %
991 % \begin{macro}{\lrnumdigit}
992 % The command \cs{lrnumdigit} records the maximum number of digits
993 % used in the table for computed numbers. The default value is $4$.
994 % \begin{macrocode}
995 \NewDocumentCommand{\lrnumdigit}{m}{
996 \int_gset:Nn \g_BBLR_num_dec_dig_int{#1}
997 }
998 % \end{macrocode}
999 % \end{macro}
1000 %
1001 % \subsection{Plot of points and lines}
1002 % \begin{macro}{\lrplot}
1003 % The command \cs{lrplot} produce a framed plot of the data
1004 % and of the regression line(s). The size of the plot and its actual
1005 % content are determined by the arguments.
1006 % \begin{macrocode}
1007 \NewDocumentCommand{\lrplot}{mmmmm}{%
1008 % \end{macrocode}
1009 % The plotting area is divided into a main plotting area for
1010 % the representation of points and line(s) and a small surrounding free space.
1011 % The height is computed taking into account the distribution of the points,
1012 % if it is not explicitelly given.
1013 % \begin{macrocode}
1014 \fp_gset:Nn \g_BBLR_base_fp {#1}
1015 \fp_gset:Nn \g_BBLR_Xbase_fp {\g_BBLR_base_fp - 0.6}
1016 \fp_gset:Nn \g_BBLR_scale_factor_fp{\g_BBLR_Xbase_fp /
1017 \g_BBLR_Dabscissa_fp}
1018 \bool_if:NTF \g_BBLR_two_scale_bool
1019 {\fp_gset:Nn \g_BBLR_height_fp {\g_BBLR_XXheight_fp}
1020 \fp_gset:Nn \g_BBLR_Xheight_fp {\g_BBLR_height_fp - 0.6}
1021 \fp_gset:Nn \g_BBLR_scale_factor_H_fp{\g_BBLR_Xheight_fp /
1022 \g_BBLR_Dordinate_fp}
1023 }
1024 {\fp_gset:Nn \g_BBLR_Xheight_fp {\g_BBLR_Dordinate_fp *
1025 \g_BBLR_scale_factor_fp}
1026 \fp_gset:Nn \g_BBLR_height_fp {\g_BBLR_Xheight_fp + 0.6}
1027 \fp_gset:Nn \g_BBLR_scale_factor_H_fp {\g_BBLR_scale_factor_fp }
1028 }
1029 % \end{macrocode}
1030 % The information about the items to be plotted is in the remaining arguments.
1031 % \begin{macrocode}
1032 \str_gset:Nn \g_BBLR_point_code_str {#2}
1033 \str_gset:Nn \g_BBLR_labelA_str {#3}
1034 \str_gset:Nn \g_BBLR_labelB_str {#4}
1035 \str_gset:Nn \g_BBLR_labelS_str {#5}
1036 \bool_gset:Nn \g_BBLR_plot_points_bool
1037 {!(\str_if_eq_p:NN \g_BBLR_point_code_str \c_BBLR_minus_str)}
1038 \bool_gset:Nn \g_BBLR_plot_lineA_bool
1039 {!(\str_if_eq_p:NN \g_BBLR_labelA_str \c_BBLR_minus_str)}
1040 \bool_gset:Nn \g_BBLR_plot_lineB_bool
1041 {!(\str_if_eq_p:NN \g_BBLR_labelB_str \c_BBLR_minus_str)}
1042 \bool_gset:Nn \g_BBLR_plot_lineS_bool
1043 {!(\str_if_eq_p:NN \g_BBLR_labelS_str \c_BBLR_minus_str)}
1044 % \end{macrocode}
1045 % The unit of length is $1$ centimeter. The plotting area is framed.
1046 % \begin{macrocode}
1047 \setlength{\unitlength}{1.0cm}
1048 \fp_gset:Nn \g_tmpa_fp {\g_BBLR_Xbase_fp +0.2}
1049 \fp_gset:Nn \g_tmpb_fp {\g_BBLR_Xheight_fp +0.1}
1050 \begin{picture}(\fp_use:N\g_BBLR_base_fp,\fp_use:N\g_BBLR_height_fp)(-0.3,-0.3)
1051 \put(-0.1,-0.1){\line(1,0){\fp_use:N\g_tmpa_fp}}
1052 \put(-0.1,\fp_use:N\g_tmpb_fp){\line(1,0){\fp_use:N\g_tmpa_fp}}
1053 \fp_gset:Nn \g_tmpa_fp {\g_tmpa_fp -0.1}
1054 \fp_gset:Nn \g_tmpb_fp {\g_tmpb_fp +0.1}
1055 \put(-0.1,-0.1){\line(0,1){\fp_use:N\g_tmpb_fp}}
1056 \put(\fp_use:N\g_tmpa_fp,-0.1){\line(0,1){\fp_use:N\g_tmpb_fp}}
1057 % \end{macrocode}
1058 % The plot of points and line(s) is obtained using auxiliary functions.
1059 % \begin{macrocode}
1060 \thicklines
1061 \bool_if:nT {\g_BBLR_plot_points_bool}{\BBLR_plot_points:}
1062 \bool_if:nT {\g_BBLR_plot_lineA_bool}{
1063 \BBLR_draw_line:NNN \g_BBLR_slope_A_fp\g_BBLR_intercept_A_fp
1064 \g_BBLR_labelA_str}
1065 \bool_if:nT {\g_BBLR_plot_lineB_bool}{
1066 \BBLR_draw_line:NNN \g_BBLR_slope_B_fp\g_BBLR_intercept_B_fp
1067 \g_BBLR_labelB_str}
1068 \bool_if:nT {\g_BBLR_plot_lineS_bool}{
1069 \BBLR_draw_line:NNN \g_BBLR_slope_S_fp\g_BBLR_intercept_S_fp
1070 \g_BBLR_labelS_str}
1071 \end{picture}
1072 }%
1073 % \end{macrocode}
1074 % \end{macro}
1075 % \begin{macro}{\lrplotparameters}
1076 % The command \cs{lrplotparameters} records two parameters related to
1077 % the generation of the plot and sets a boolean variable.
1078 % \begin{macrocode}
1079 \NewDocumentCommand{\lrplotparameters}{mm}{
1080 \fp_gset:Nn \g_BBLR_diameter_fp{#1}
1081 \fp_gset:Nn \g_BBLR_XXheight_fp{#2}
1082 \bool_gset:Nn \g_BBLR_two_scale_bool
1083 {\fp_compare_p:nNn {\g_BBLR_XXheight_fp}>{0.}}
1084 }
1085 % \end{macrocode}
1086 % \end{macro}
1087 %
1088 % \subsection{Functions for internal use}
1089 % The functions listed here after are for internal
1090 % use and are just minimally documented. \par
1091 % The function |\BBLR_decode_data:|
1092 % \marginpar{\raggedleft\texttt{
1093 % \textbackslash{}BBLR\textunderscore{}decode\textunderscore{}data:}}
1094 % extract two numeric values from the string read from the file.
1095 % Some clever actions are necessary because
1096 % a so called csv file sometime do not contains the separating commas.
1097 % \begin{macrocode}
1098 \cs_new_protected:Nn \BBLR_decode_data: {
1099 \tl_trim_spaces:N \g_BBLR_file_line_tl
1100 \int_gzero:N \g_tmpa_int
1101 \int_gzero:N \g_BBLR_first_separator_int
1102 \int_gzero:N \g_BBLR_last_separator_int
1103 \int_gset:Nn \g_BBLR_record_length_int {
1104 \str_count:N \g_BBLR_file_line_tl}
1105 \str_map_variable:NNn \g_BBLR_file_line_tl \g_tmpa_str {
1106 \int_gincr:N \g_tmpa_int
1107 \bool_lazy_or:nnTF
1108 {\str_if_eq_p:NN \g_tmpa_str \c_BBLR_comma_str}
1109 {\str_if_eq_p:NN \g_tmpa_str \c_BBLR_space_str}
1110 {\int_gset_eq:NN \g_BBLR_last_separator_int \g_tmpa_int
1111 \int_if_zero:nTF {\g_BBLR_first_separator_int}
1112 {\int_gset_eq:NN \g_BBLR_first_separator_int \g_tmpa_int
1113 }{\prg_do_nothing:}
1114 }{\prg_do_nothing:}
1115 }
1116 \int_gincr:N \g_BBLR_last_separator_int
1117 \int_gdecr:N \g_BBLR_first_separator_int
1118 \fp_gset:Nn \g_BBLR_abscissa_fp{
1119 \str_range:Nnn \g_BBLR_file_line_tl{1}{\g_BBLR_first_separator_int}}
1120 \fp_gset:Nn \g_BBLR_ordinate_fp{
1121 \str_range:Nnn \g_BBLR_file_line_tl
1122 {\g_BBLR_last_separator_int}{\g_BBLR_record_length_int}}
1123 }
1124 % \end{macrocode}
1125 % The function |\BBLR_plot_points:| \marginpar{\raggedleft\texttt{
1126 % \textbackslash{}BBLR\textunderscore{}plot\textunderscore{}points:}}
1127 % scans the data file to read the coordinates and
1128 % it draws a circle for each point.
1129 %
1130 % \begin{macrocode}
1131 \cs_new_protected:Nn \BBLR_plot_points: {
1132 \ior_open:Nn \g_BBLR_file_ior \g_BBLR_file_name_tl
1133 \int_zero:N \g_BBLR_rec_count_int
1134 \int_do_until:nn
1135 {\g_BBLR_rec_count_int = \g_BBLR_number_of_points_int}
1136 {
1137 \ior_str_get:NN \g_BBLR_file_ior \g_BBLR_file_line_tl
1138 \int_incr:N \g_BBLR_rec_count_int
1139 \BBLR_decode_data:
1140 \fp_gset:Nn \g_tmpa_fp{(\g_BBLR_abscissa_fp-\g_BBLR_min_abscissa_fp)*
1141 \g_BBLR_scale_factor_fp}
1142 \fp_gset:Nn \g_tmpb_fp{(\g_BBLR_ordinate_fp-\g_BBLR_min_ordinate_fp)*
1143 \g_BBLR_scale_factor_H_fp}
1144 \put(\fp_use:N\g_tmpa_fp, \fp_use:N\g_tmpb_fp){
1145 {\circle*{\fp_use:N\g_BBLR_diameter_fp}}}
1146 }
1147 \ior_close:N \g_BBLR_file_ior
1148 }
1149 % \end{macrocode}
1150 % The function |\BBLR_draw_line:NNN| \marginpar{\raggedleft\texttt{
1151 % \textbackslash{}BBLR\textunderscore{}draw\textunderscore{}line:NNN}}
1152 % draws the line. The first two parameters given as arguments
1153 % are the slope and the intercept. The third parameter is a label.
1154 % \par The next code finds the intersection of the line with the plotting area.
1155 % \begin{macrocode}
1156 \cs_new_protected:Nn \BBLR_draw_line:NNN {
1157 \fp_gset:Nn \fp_tmpa_fp {#1 * \g_BBLR_min_abscissa_fp + #2 }
1158 \fp_compare:nTF{\fp_tmpa_fp > \g_BBLR_max_ordinate_fp}{
1159 \fp_gset:Nn \g_BBLR_min_draw_abscissa_fp {(\g_BBLR_max_ordinate_fp -#2) / #1}
1160 }{
1161 \fp_compare:nTF{\fp_tmpa_fp < \g_BBLR_min_ordinate_fp}{
1162 \fp_gset:Nn \g_BBLR_min_draw_abscissa_fp {(\g_BBLR_min_ordinate_fp - #2) / #1}
1163 }{
1164 \fp_gset:Nn \g_BBLR_min_draw_abscissa_fp { \g_BBLR_min_abscissa_fp }
1165 }}
1166 \fp_gset:Nn \fp_tmpa_fp {#1 * \g_BBLR_max_abscissa_fp + #2 }
1167 \fp_compare:nTF{\fp_tmpa_fp > \g_BBLR_max_ordinate_fp}{
1168 \fp_gset:Nn \g_BBLR_max_draw_abscissa_fp {(\g_BBLR_max_ordinate_fp -#2) / #1}
1169 }{
1170 \fp_compare:nTF{\fp_tmpa_fp < \g_BBLR_min_ordinate_fp}{
1171 \fp_gset:Nn \g_BBLR_max_draw_abscissa_fp { (\g_BBLR_min_ordinate_fp - #2) / #1}
1172 }{
1173 \fp_gset:Nn \g_BBLR_max_draw_abscissa_fp { \g_BBLR_max_abscissa_fp }
1174 }}
1175 % \end{macrocode}
1176 % Some parameters (coordinates of starting point, base-length, scaled slope)
1177 % are computed and the line is drawn.
1178 % \begin{macrocode}
1179 \fp_gset:Nn \fp_tmpa_fp {(\g_BBLR_min_draw_abscissa_fp -
1180 \g_BBLR_min_abscissa_fp)* \g_BBLR_scale_factor_fp}
1181 \fp_gset:Nn \fp_tmpb_fp {(#1 * \g_BBLR_min_draw_abscissa_fp + #2 -
1182 \g_BBLR_min_ordinate_fp)* \g_BBLR_scale_factor_H_fp}
1183 \fp_gset:Nn \fp_BBLR_line_base_length_fp{(\g_BBLR_max_draw_abscissa_fp -
1184 \g_BBLR_min_draw_abscissa_fp) * \g_BBLR_scale_factor_fp}
1185 \fp_gset:Nn \fp_scaled_slope_fp
1186 {(#1 * \g_BBLR_scale_factor_H_fp / \g_BBLR_scale_factor_fp)}
1187 \put(\fp_use:N\fp_tmpa_fp, \fp_use:N\fp_tmpb_fp){
1188 \line(1.,\fp_use:N\fp_scaled_slope_fp){\fp_use:N\fp_BBLR_line_base_length_fp}}
1189 % \end{macrocode}
1190 %The third parameter is used as a label, if it is not a |+|.
1191 % \begin{macrocode}
1192 \bool_if:nF {\str_if_eq_p:NN #3 \c_BBLR_plus_str}{
1193 \fp_gset:Nn \fp_tmpa_fp
1194 {0.08 * \g_BBLR_min_draw_abscissa_fp + 0.92 * \g_BBLR_max_draw_abscissa_fp}
1195 \fp_gset:Nn \fp_tmpb_fp {#1 * \fp_tmpa_fp + #2 }
1196 \fp_gset:Nn \fp_tmpa_fp
1197 {(\fp_tmpa_fp-\g_BBLR_min_abscissa_fp)*\g_BBLR_scale_factor_fp
1198 + 0.3 * #1 /sqrt(1.+#1*#1)}
1199 \fp_gset:Nn \fp_tmpb_fp
1200 {(\fp_tmpb_fp-\g_BBLR_min_ordinate_fp)* \g_BBLR_scale_factor_fp
1201 - 0.3 /sqrt(1.+#1*#1)}
1202 \put(\fp_use:N\fp_tmpa_fp, \fp_use:N\fp_tmpb_fp){#3}
1203 }
1204 }
1205 % \end{macrocode}
1206 % The function |\BBLR_print_fp:N | \marginpar{\raggedleft\texttt{
1207 % \textbackslash{}BBLR\textunderscore{}print\textunderscore{}fp:N }}
1208 % is used to print floating point numbers with a limited number
1209 % of decimal digit.
1210 %
1211 % \begin{macrocode}
1212 \cs_new_protected:Nn \BBLR_print_fp:N {%
1213 {\fp_eval:n{trunc(#1 ,\g_BBLR_num_dec_dig_int)}}
1214 }
1215 % \end{macrocode}
1216 %
1217 % \begin{macrocode}
1218 \ExplSyntaxOff
1219 % \end{macrocode}
1220 %
1221 %
1222 %\iffalse
1223 %</package>
1224 %\fi
1225 %
1226 % \section{Versions}
1227 % 2024-06-10: first post on CTAN.\par
1228 % 2024-11-23: small changes in the text,
1229 % different format of numbers in the table.\par
1230 % 2024-12-14: more flexibe output, some changes in the text.\par
1231 % 2025-11-08: different notation for vectors and matrices,
1232 % some changes and additions in the text, updated year of two references,
1233 % a significant bug corrected
1234 % (variable holding the number of points needs to be globally setted).
1235 %
1236 % \section{Acknowledgments}
1237 % The colleagues Paolo Zatelli, Alfonso Vitti and Giulia Graldi
1238 % read some preliminary version
1239 % of this text and suggested several improvements.
1240 % Claudio Beccari usefully commented about the first version
1241 % when I was preparing the second version. \par
1242 %
1243 % \section{Citations and references}
1244 % \subsection*{Mathematics}
1245 % The books by Lang \cite{Lang} and by Strang \cite{Strang} give
1246 % all the background on linear algebra.\par
1247 % The texts by Sansò \cites{Sanso1, Sanso2} (in italian) treat the
1248 % teory of probability and its application to metrology.
1249 % The paper by Pearson \cite{Pearson} is the oldest text that
1250 % I have found on the symmetric regression, or total regression.
1251 % \subsection*{Programming}
1252 % The two documents \cites{L3A, L3B} are the fountamental and official guide
1253 % for \LaTeX3 programming. The books by Donald Knuth \cites{Knuth}
1254 % and Leslie Lamport \cites{Lamport} are still essential references.
1255 % The papers by Enrico Gregorio \cites{egreg1, egreg2, egreg3, egreg4, egreg5}
1256 % explain some general and some special aspect of \LaTeX3 programming.
1257 % \subsection*{References}
1258 % \begin{biblist}[\normalsize]
1259 % \bib{egreg1}{article}{
1260 % author={Gregorio, Enrico},
1261 % journal={ArsTeXnica},
1262 % number={14},pages={41\ndash 47}, date={2012},
1263 % title={\LaTeX3: un nuovo gioco per i maghi e per diventarlo},
1264 % }
1265 % \bib{egreg2}{article}{
1266 % author={Gregorio, Enrico},
1267 % journal={ArsTeXnica},
1268 % number={22},pages={69\ndash 77}, date={2016},
1269 % title={Liste, cicli, \LaTeX3},
1270 % }
1271 % \bib{egreg3}{article}{
1272 % author={Gregorio, Enrico},
1273 % journal={ArsTeXnica},
1274 % number={24},pages={37\ndash 44}, date={2017},
1275 % title={Condizionali in \LaTeX},
1276 % }
1277 % \bib{egreg4}{article}{
1278 % author={Gregorio, Enrico},
1279 % journal={ArsTeXnica},
1280 % number={30},pages={36\ndash 45}, date={2020},
1281 % title={Funzioni e |expl3|},
1282 % }
1283 % \bib{egreg5}{article}{
1284 % author={Gregorio, Enrico},
1285 % journal={TUGboat},
1286 % volume={41},number={3},pages={299\ndash 307}, date={2020},
1287 % title={Functions and |expl3|},
1288 % }
1289 % \bib{Knuth}{book}{
1290 % author={Knuth, Donald},
1291 % title={The TeXbook},
1292 % date={1986},
1293 % publisher={American Mathematical Society and Addison-Wesley},
1294 % }
1295 % \bib{Lang}{book}{
1296 % author={Lang, Serge},
1297 % title={Linear Algebra},
1298 % date={1987},
1299 % publisher={Springer-Verlag},
1300 % place={Berlin Heidelberg},
1301 % }
1302 % \bib{Lamport}{book}{
1303 % author={Lamport, Leslie},
1304 % title={LaTeX - A document preparation system (2nd ed.\ )},
1305 % date={1994},
1306 % publisher={Addison-Wesley},
1307 % note={something interesting in the fist edition, too},
1308 % }
1309 % \bib{L3A}{article}{
1310 % title={The |expl3| package and LaTeX3 programming},
1311 % author={The LaTeX project team}, date={2025},
1312 % note={file: |expl3.pdf| available in CTAN in l3kernel},
1313 % }
1314 % \bib{L3B}{article}{
1315 % title={The \LaTeX3 interface},
1316 % author={The LaTeX project team}, date={2025},
1317 % note={file: |interface3.pdf| available in CTAN in l3kernel}
1318 % }
1319 % \bib{Pearson}{article}{
1320 % title={On lines and planes of closest fit to systems of points in space},
1321 % author={Pearson, Karl}, date={1901},
1322 % journal={Philosophical Magazine},
1323 % volume={2},number={11},pages={559\ndash 572},
1324 % }
1325 % \bib{Sanso1}{book}{
1326 % author={Sansò, Fernando},
1327 % title={Elementi di teoria della probabilità},
1328 % date={1996},
1329 % publisher={Città-Studi},
1330 % place={Milano},
1331 % note={see: http://www.geolab.polimi.it/text-books/},
1332 % }
1333 % \bib{Sanso2}{book}{
1334 % author={Sansò, Fernando},
1335 % title={La teoria della stima},
1336 % date={1996},
1337 % publisher={Città-Studi},
1338 % place={Milano},
1339 % note={see: http://www.geolab.polimi.it/text-books/},
1340 % }
1341 % \bib{Strang}{book}{
1342 % author={Strang, Gilbert},
1343 % title={Introduction to linear algebra},
1344 % date={2009},
1345 % publisher={Wellesley-Cambridge press,},
1346 % }
1347 % \end{biblist}
1348 %
1349 % \par\vfill\centerline{\small ***}\vfill
1350 % \end{document}
1351 %
1352 %\iffalse
1353 % END OF FILE linearregression.dtx
1354 %\fi