The Dap Project for Statistics and Graphics


Table of contents


Introduction to Dap   [Back to Table of Contents]

Dap is a small statistics and graphics package based on C. Version 3.0 and later of Dap can read SBS programs (based on the utterly famous, industry standard statistics system with similar initials - you know the one I mean)! The user wishing to perform basic statistical analyses is now freed from learning and using C syntax for straightforward tasks, while retaining access to the C-style graphics and statistics features provided by the original implementation. Dap provides core methods of data management, analysis, and graphics that are commonly used in statistical consulting practice (univariate statistics, correlations and regression, ANOVA, categorical data analysis, logistic regression, and nonparametric analyses).

Anyone familiar with the basic syntax of C programs can learn to use the C-style features of Dap quickly and easily from the manual and the examples contained in it; advanced features of C are not necessary, although they are available. (The manual contains a brief introduction to the C syntax needed for Dap.) Because Dap processes files one line at a time, rather than reading entire files into memory, it can be, and has been, used on data sets that have very many lines and/or very many variables.

I wrote Dap to use in my statistical consulting practice because the aforementioned utterly famous, industry standard statistics system is (or at least was) not available on GNU/Linux and costs a bundle every year under a lease arrangement. And now you can run programs written for that system directly on Dap! I was generally happy with that system, except for the graphics, which are all but impossible to use,  but there were a number of clumsy constructs left over from its ancient origins. Thus, I decided to mimic the core of the functionality of that system in the context of the C language, which allows much more programming flexibility.

Dap is a GNU program and is free software distributed under a GNU-style copyleft.

Downloading Dap [Back to Table of Contents]

Dap source code can be found as a gzipped tar file in http://ftp.gnu.org/gnu/dap. Dap builds successfully on a variety of GNU/Linux and Unix platforms. Dap comes with a manual in info form, which can rendered into dvi form using texi2dvi.

The following instructions tell you how to install Dap.

GENERALITIES

This document concerns building and installing Dap from sources.

Dap will configure and build under a number of common Unix-like platforms.The directions here are for GNU/Linux; the configure and build for other
platforms are similar.

There are two mailing lists regarding Dap, one for bugs and one for comments, which can be accessed through http://mail.gnu.org/archive/html/bug-dap and http://mail.gnu.org/archive/html/dap-users.

Dap is a GNU program and is free software distributed under a GNU-style copyleft. See the file COPYING for details.

GETTING AND UNPACKING THE SOURCES

The simplest way is to download the most recent `dap-x.y.tar.gz' package into a directory that we'll call `DAP_HOME' and untar it with:

        gunzip -c dap-x.y.tar.gz | tar -xvf -

This should create directories `src', `doc', and `examples'.

COMPILATION

If you want the executables, includes, library, and info files installed in subdirectories `bin', `include', `lib', and `info', respectively, of `/usr/local', then simply issue the following commands:

        ./configure
        make install

Otherwise, if you want to install dap in subdirectories of another directory, say "home/dap", after the `./configure' command, instead type type:

        make prefix=home/dap install

Note: when DAP_HOME/src/dap.c compiles, you will get a warning:

        implicit declaration of function `strcat'

and when DAP_HOME/src/dap0.c compiles, you will get a warning:

        implicit declaration of function `dap_main'

Ignore these warnings.  Now rehash.

ENVIRONMENT

The following environment variables are used by Dap:

DAPEDITOR            path name for Emacs
DAPEDOPTS           options for the Emacs front-end
DAPPAGER            for viewing tabular output from Dap
DAPPAGEOPTS    options for that pager
DAPCOMPILER    for compiling programs to run under Dap
DAPCOMPOPTS   options for that compiler
DAPVIEWER        for viewing graphical output from Dap
DAPVIEWOPTS   options for that viewer
DAPPP                   path name for the Dap preprocessor
              (default: /usr/local/bin/dappp)
DAPRUNS             path name for the Dap process that runs the
                                preprocessor and complier
              (default: /usr/local/bin/dapruns)
INCDIR                 directory for compiler to find <dap.h>
              (default: /usr/local/include)
LIBDIR                 directory for compiler to find libdap.a
              (default: /usr/local/lib)

All but the last four are further documented in the manual.

READING THE MANUAL

To read the manual in info, you will need to have `/usr/local/info' (or whatever directory you installed the info file in) in your `INFOPATH'. The
following command (which you will probably want to put in yourshell's `rc' file) will do that if your shell is `csh':

        setenv INFOPATH ".:/usr/info:/usr/local/info"

Then issue the command:

        info dap

If you prefer dvi or html manuals, they can be made from the file:

        DAP_HOME/doc/dap.texi

(See the documentation for texi2dvi, dvips, and texinfo.)

The manual will tell you how to run and use dap.  The program and data files for the examples in the manual are in the directory DAP_HOME/doc/examples.

MACHINE DEPENDENCY

Dap assumes that you have a machine with 64-bit double precision floating point numbers conforming to the IEEE floating point standard.  If that is not the case, then you may have to modify `machdep.c'; good luck.

BUG REPORTS AND COMMENTS

Send bug reports to <bug-dap@gnu.org>.

If you use dap, please let me know about your experience using it, and suggestions, by mailing
to <dap-users@gnu.org>. Thanks.

Sample output   [Back to Table of Contents]

The following are samples of tabular output from Dap. They, the programs that produced them, and graphical output (not shown here) are all provided with the distribution.  These examples are from:

[AMD] Milliken, G.A. and Johnson, D.E. 1984.  Analysis of Messy Data.  Van Nostrand Reinhold: New York. 473pp.
[ED] Cochran, W.G. and Cox, G.M. 1957.  Experimental Designs.  John Wiley & Sons: New York. 611pp.
[MS] Bickel, P.J. and Doksum, K.A. 1977. Mathematical Statistics: Basic Ideas and Selected Topics. Holden-Day: Oakland. 493 pp.
[LM] Rao, C.R. and Toutenberg, H. 1995. Linear Models: Least Squares and Alternatives. Springer-Verlag: New York. 352 pp.
[CDA] Agresti, A.  1990.  Categorical Data Analysis.  John Wiley & Sons: New York.  558pp.

  •  Unbalanced ANOVA
  •  Crossed, nested ANOVA
  •  Random model, unbalanced
  •  Mixed model, balanced
  •  Mixed model, unbalanced
  •  Split plot
  •  Latin square
  •  Missing treatment combinations
  •  Linear regression
  •  Linear regression, model building
  •  Ordinal cross-classification
  •  Stratified 2x2 tables
  •  Loglinear models
  •  Logit  model for linear-by-linear association
  •  Logistic regression

  • Unbalanced ANOVA  [Back to Sample output]

    AMD: pp. 128 - 134
    =================================
    Dap   1. Mon Jan 12 03:20:03 2004
     

    Response variable: y

    Treatment       Levels
    --------        ------
    treat           treat1 treat2
    block           block1 block2 block3
     

    =================================
    Dap   2. Mon Jan 12 03:20:03 2004
     

    Testing Ho: treat block treat*block
    Number of observations = 16
    H0 SS = 238.937, df = 5, MS = 47.7875
    Error SS = 20, df = 10, MS = 2
    R-sq = 0.922761
    F0 = 23.8937
    Prob[F > F0] = 0.00003

    =================================
    Dap   3. Mon Jan 12 03:20:03 2004
     

    Testing Ho: treat
    Number of observations = 16
    H0 SS = 61.7143, df = 1, MS = 61.7143
    Error SS = 20, df = 10, MS = 2
    F0 = 30.8571
    Prob[F > F0] = 0.00025

    =================================
    Dap   4. Mon Jan 12 03:20:03 2004
     

    Least-squares means for: treat

    LSD  method
    Minimum significant differences are for level 0.05000

    =================================
    Dap   5. Mon Jan 12 03:20:04 2004
     

                                _stat_ for _lsm_ / treat
    ======================================================
    |                          |23          |27          |
    |--------+--------+--------|------------+------------|
    |_type_  |_LSMEAN_|_treat  |treat1      |treat2      |
    |========|========|========|============|============|
    |EFFN    |0       |        |     7.71429|     7.71429|
    |--------+--------+--------|------------+------------|
    |LSMDIFF |23      |treat1  |            |           4|
    |        |--------+--------|------------+------------|
    |        |27      |treat2  |          -4|            |
    |--------+--------+--------|------------+------------|
    |MINDIFF |23      |treat1  |            |     1.60445|
    |        |--------+--------|------------+------------|
    |        |27      |treat2  |     1.60445|            |
    |--------+--------+--------|------------+------------|
    |PROB    |23      |treat1  |            | 0.000242431|
    |        |--------+--------|------------+------------|
    |        |27      |treat2  | 0.000242431|            |
    ------------------------------------------------------

    =================================
    Dap   6. Mon Jan 12 03:20:04 2004
     

    Testing Ho: block
    Number of observations = 16
    H0 SS = 77.1692, df = 2, MS = 38.5846
    Error SS = 20, df = 10, MS = 2
    F0 = 19.2923
    Prob[F > F0] = 0.00037

    =================================
    Dap   7. Mon Jan 12 03:20:04 2004
     

    Least-squares means for: block

    LSD  method
    Minimum significant differences are for level 0.05000

    =================================
    Dap   8. Mon Jan 12 03:20:04 2004
     

                                _stat_ for _lsm_ / block
    ===================================================================
    |                          |23          |24          |28          |
    |--------+--------+--------|------------+------------+------------|
    |_type_  |_LSMEAN_|_block  |block1      |block2      |block3      |
    |========|========|========|============|============|============|
    |EFFN    |0       |        |         4.8|         4.8|           6|
    |--------+--------+--------|------------+------------+------------|
    |LSMDIFF |23      |block1  |            |           1|           5|
    |        |--------+--------|------------+------------+------------|
    |        |24      |block2  |          -1|            |           4|
    |        |--------+--------|------------+------------+------------|
    |        |28      |block3  |          -5|          -4|            |
    |--------+--------+--------|------------+------------+------------|
    |MINDIFF |23      |block1  |            |     2.03401|     1.92963|
    |        |--------+--------|------------+------------+------------|
    |        |24      |block2  |     2.03401|            |     1.92963|
    |        |--------+--------|------------+------------+------------|
    |        |28      |block3  |     1.92963|     1.92963|            |
    |--------+--------+--------|------------+------------+------------|
    |PROB    |23      |block1  |            |    0.299003| 0.000179317|
    |        |--------+--------|------------+------------+------------|
    |        |24      |block2  |    0.299003|            | 0.000952328|
    |        |--------+--------|------------+------------+------------|
    |        |28      |block3  | 0.000179317| 0.000952328|            |
    -------------------------------------------------------------------

    =================================
    Dap   9. Mon Jan 12 03:20:04 2004
     

    Testing Ho: treat*block
    Number of observations = 16
    H0 SS = 71.6308, df = 2, MS = 35.8154
    Error SS = 20, df = 10, MS = 2
    F0 = 17.9077
    Prob[F > F0] = 0.00050

    Crossed, nested ANOVA [Back to Sample output]

    AMD: pp. 249 - 251
    =================================
    Dap   1. Mon Jan 12 03:20:11 2004
     

    Response variable: y

    Treatment       Levels
    --------        ------
    a               1 2
    b               1 2
    c               1 2
     

    =================================
    Dap   2. Mon Jan 12 03:20:11 2004
     

    Testing Ho: a b a*b b*c a*b*c
    Number of observations = 16
    H0 SS = 845.438, df = 7, MS = 120.777
    Error SS = 6.5, df = 8, MS = 0.8125
    R-sq = 0.99237
    F0 = 148.648
    Prob[F > F0] = 0.00001

    =================================
    Dap   3. Mon Jan 12 03:20:11 2004
     

    Testing Ho: a
    Number of observations = 16
    H0 SS = 39.0625, df = 1, MS = 39.0625
    Error SS = 6.5, df = 8, MS = 0.8125
    F0 = 48.0769
    Prob[F > F0] = 0.00013

    =================================
    Dap   4. Mon Jan 12 03:20:11 2004
     

    Testing Ho: b
    Number of observations = 16
    H0 SS = 770.062, df = 1, MS = 770.062
    Error SS = 6.5, df = 8, MS = 0.8125
    F0 = 947.769
    Prob[F > F0] = 0.00001

    =================================
    Dap   5. Mon Jan 12 03:20:11 2004
     

    Testing Ho: a*b
    Number of observations = 16
    H0 SS = 10.5625, df = 1, MS = 10.5625
    Error SS = 6.5, df = 8, MS = 0.8125
    F0 = 13
    Prob[F > F0] = 0.00693

    =================================
    Dap   6. Mon Jan 12 03:20:11 2004
     

    Testing Ho: c*b
    Number of observations = 16
    H0 SS = 24.125, df = 2, MS = 12.0625
    Error SS = 6.5, df = 8, MS = 0.8125
    F0 = 14.8462
    Prob[F > F0] = 0.00203

    =================================
    Dap   7. Mon Jan 12 03:20:11 2004
     

    Testing Ho: a*c*b
    Number of observations = 16
    H0 SS = 1.625, df = 2, MS = 0.8125
    Error SS = 6.5, df = 8, MS = 0.8125
    F0 = 1
    Prob[F > F0] = 0.40960

    =================================
    Dap   8. Mon Jan 12 03:20:11 2004
     

    Testing Ho: a
    Denominator: a * b
    EMS(a*b) =
        4 Var(a*b)
        1 Var(Error)
    EMS(a) =
        8 Var(a)
        4 Var(a*b)
        1 Var(Error)
    Error for a =
        1 MS(a*b)
    Number of observations = 16
    H0 SS = 39.0625, df = 1, MS = 39.0625
    Residual df = 1, MS = 10.5625
    F0 = 3.69822
    Prob[F > F0] = 0.30528

    =================================
    Dap   9. Mon Jan 12 03:20:11 2004
     

    Testing Ho: b
    Denominator: a * b b * c a * b * c
    EMS(a*b) =
        4 Var(a*b)
        2 Var(a*b*c)
        1 Var(Error)
    EMS(b*c) =
        4 Var(b*c)
        2 Var(a*b*c)
        1 Var(Error)
    EMS(a*b*c) =
        2 Var(a*b*c)
        1 Var(Error)
    EMS(b) =
        8 Var(b)
        4 Var(a*b)
        4 Var(b*c)
        2 Var(a*b*c)
        1 Var(Error)
    Error for b =
        1 MS(a*b)
        1 MS(b*c)
        -1 MS(a*b*c)
    Number of observations = 16
    H0 SS = 770.062, df = 1, MS = 770.062
    Residual df = 2.57671, MS = 21.8125
    F0 = 35.3037
    Prob[F > F0] = 0.01701

    =================================
    Dap  10. Mon Jan 12 03:20:11 2004
     

    Testing Ho: a * b
    Denominator: a * b * c
    EMS(a*b*c) =
        2 Var(a*b*c)
        1 Var(Error)
    EMS(a*b) =
        4 Var(a*b)
        2 Var(a*b*c)
        1 Var(Error)
    Error for a*b =
        1 MS(a*b*c)
    Number of observations = 16
    H0 SS = 10.5625, df = 1, MS = 10.5625
    Residual df = 2, MS = 0.8125
    F0 = 13
    Prob[F > F0] = 0.06906

    =================================
    Dap  11. Mon Jan 12 03:20:11 2004
     

    Testing Ho: c * b
    Denominator: a * c * b
    EMS(a*b*c) =
        2 Var(a*b*c)
        1 Var(Error)
    EMS(b*c) =
        4 Var(b*c)
        2 Var(a*b*c)
        1 Var(Error)
    Error for b*c =
        1 MS(a*b*c)
    Number of observations = 16
    H0 SS = 24.125, df = 2, MS = 12.0625
    Residual df = 2, MS = 0.8125
    F0 = 14.8462
    Prob[F > F0] = 0.06311

    Random model, unbalanced [Back to Sample output]

    AMD: pp. 265 - 273
    =================================
    Dap   1. Mon Jan 12 03:20:12 2004
     

    Response variable: efficiency

    Treatment       Levels
    --------        ------
    plant           1 2 3
    site            1 2 3 4
    worker          1 2 3
     

    =================================
    Dap   2. Mon Jan 12 03:20:13 2004
     

    Testing Ho: plant plant*site plant*worker plant*site*worker
    Number of observations = 118
    H0 SS = 10046.9, df = 35, MS = 287.054
    Error SS = 408.617, df = 82, MS = 4.98313
    R-sq = 0.960919
    F0 = 57.6052
    Prob[F > F0] = 0.00001

    =================================
    Dap   3. Mon Jan 12 03:20:13 2004
     

    Testing Ho: plant
    Number of observations = 118
    H0 SS = 3866.33, df = 2, MS = 1933.16
    Error SS = 408.617, df = 82, MS = 4.98313
    F0 = 387.942
    Prob[F > F0] = 0.00001

    =================================
    Dap   4. Mon Jan 12 03:20:13 2004
     

    Testing Ho: plant*worker
    Number of observations = 118
    H0 SS = 1949.66, df = 6, MS = 324.943
    Error SS = 408.617, df = 82, MS = 4.98313
    F0 = 65.2085
    Prob[F > F0] = 0.00001

    =================================
    Dap   5. Mon Jan 12 03:20:13 2004
     

    Testing Ho: plant*site
    Number of observations = 118
    H0 SS = 610.302, df = 9, MS = 67.8114
    Error SS = 408.617, df = 82, MS = 4.98313
    F0 = 13.6082
    Prob[F > F0] = 0.00001

    =================================
    Dap   6. Mon Jan 12 03:20:13 2004
     

    Testing Ho: plant*site*worker
    Number of observations = 118
    H0 SS = 1921.29, df = 18, MS = 106.738
    Error SS = 408.617, df = 82, MS = 4.98313
    F0 = 21.4199
    Prob[F > F0] = 0.00001

    =================================
    Dap   7. Mon Jan 12 03:20:13 2004
     

    Testing Ho: site * plant
    Denominator: site * worker * plant
    EMS(plant*site*worker) =
        2.85695 Var(plant*site*worker)
        1 Var(Error)
    EMS(plant*site) =
        8.0468 Var(plant*site)
        2.68227 Var(plant*site*worker)
        1 Var(Error)
    Error for plant*site =
        0.0611422 MS(Error)
        0.938858 MS(plant*site*worker)
    Number of observations = 118
    H0 SS = 610.302, df = 9, MS = 67.8114
    Residual df = 18.1096, MS = 100.517
    F0 = 0.674628
    Prob[F > F0] = 0.72173

    =================================
    Dap   8. Mon Jan 12 03:20:13 2004
     

    Response variable: efficiency

    Treatment       Levels
    --------        ------
    plant           1 2 3
    site            1 2 3 4
    worker          1 2 3
     

    =================================
    Dap   9. Mon Jan 12 03:20:13 2004
     

    Testing Ho: plant plant*worker plant*site*worker
    Number of observations = 118
    H0 SS = 10046.9, df = 35, MS = 287.054
    Error SS = 408.617, df = 82, MS = 4.98313
    R-sq = 0.960919
    F0 = 57.6052
    Prob[F > F0] = 0.00001

    =================================
    Dap  10. Mon Jan 12 03:20:14 2004
     

    Testing Ho: plant
    Number of observations = 118
    H0 SS = 3866.33, df = 2, MS = 1933.16
    Error SS = 408.617, df = 82, MS = 4.98313
    F0 = 387.942
    Prob[F > F0] = 0.00001

    =================================
    Dap  11. Mon Jan 12 03:20:14 2004
     

    Testing Ho: plant*worker
    Number of observations = 118
    H0 SS = 1949.66, df = 6, MS = 324.943
    Error SS = 408.617, df = 82, MS = 4.98313
    F0 = 65.2085
    Prob[F > F0] = 0.00001

    =================================
    Dap  12. Mon Jan 12 03:20:14 2004
     

    Testing Ho: site*worker*plant
    Number of observations = 118
    H0 SS = 2677.73, df = 27, MS = 99.1752
    Error SS = 408.617, df = 82, MS = 4.98313
    F0 = 19.9022
    Prob[F > F0] = 0.00001

    =================================
    Dap  13. Mon Jan 12 03:20:14 2004
     

    Testing Ho: worker * plant
    Denominator: site * worker * plant
    EMS(plant*site*worker) =
        3.06428 Var(plant*site*worker)
        1 Var(Error)
    EMS(plant*worker) =
        9.45329 Var(plant*worker)
        2.36332 Var(plant*site*worker)
        1 Var(Error)
    Error for plant*worker =
        0.22875 MS(Error)
        0.77125 MS(plant*site*worker)
    Number of observations = 118
    H0 SS = 1949.66, df = 6, MS = 324.943
    Residual df = 27.8087, MS = 77.6288
    F0 = 4.18585
    Prob[F > F0] = 0.00403

    =================================
    Dap  14. Mon Jan 12 03:20:14 2004
     

    Testing Ho: plant
    Denominator: worker * plant site * worker * plant
    EMS(plant*worker) =
        9.45329 Var(plant*worker)
        2.36332 Var(plant*site*worker)
        1 Var(Error)
    EMS(plant*site*worker) =
        3.06428 Var(plant*site*worker)
        1 Var(Error)
    EMS(plant) =
        27.598 Var(plant)
        9.19933 Var(plant*worker)
        2.29983 Var(plant*site*worker)
        1 Var(Error)
    Error for plant =
        0.0268648 MS(Error)
        0.973135 MS(plant*worker)
    Number of observations = 118
    H0 SS = 3866.33, df = 2, MS = 1933.16
    Residual df = 6.00508, MS = 316.347
    F0 = 6.1109
    Prob[F > F0] = 0.03567

    Mixed model, balanced [Back to Sample output]

    AMD:  pp. 285-289
    =================================
    Dap   1. Mon Jan 12 03:20:16 2004
     

    Response variable: productivity

    Treatment       Levels
    --------        ------
    machine         1 2 3
    person          1 2 3 4 5 6
     

    =================================
    Dap   2. Mon Jan 12 03:20:16 2004
     

    Testing Ho: machine person machine*person
    Number of observations = 54
    H0 SS = 3423.69, df = 17, MS = 201.393
    Error SS = 33.2867, df = 36, MS = 0.92463
    R-sq = 0.990371
    F0 = 217.81
    Prob[F > F0] = 0.00001

    =================================
    Dap   3. Mon Jan 12 03:20:16 2004
     

    Testing Ho: machine
    Number of observations = 54
    H0 SS = 1755.26, df = 2, MS = 877.632
    Error SS = 33.2867, df = 36, MS = 0.92463
    F0 = 949.171
    Prob[F > F0] = 0.00001

    =================================
    Dap   4. Mon Jan 12 03:20:16 2004
     

    Testing Ho: person
    Number of observations = 54
    H0 SS = 1241.89, df = 5, MS = 248.379
    Error SS = 33.2867, df = 36, MS = 0.92463
    F0 = 268.625
    Prob[F > F0] = 0.00001

    =================================
    Dap   5. Mon Jan 12 03:20:16 2004
     

    Testing Ho: machine*person
    Number of observations = 54
    H0 SS = 426.53, df = 10, MS = 42.653
    Error SS = 33.2867, df = 36, MS = 0.92463
    F0 = 46.1298
    Prob[F > F0] = 0.00001

    =================================
    Dap   6. Mon Jan 12 03:20:16 2004
     

    Testing Ho: person
    Denominator: machine * person
    EMS(machine*person) =
        3 Var(machine*person)
        1 Var(Error)
    EMS(person) =
        9 Var(person)
        3 Var(machine*person)
        1 Var(Error)
    Error for person =
        1 MS(machine*person)
    Number of observations = 54
    H0 SS = 1241.89, df = 5, MS = 248.379
    Residual df = 10, MS = 42.653
    F0 = 5.82325
    Prob[F > F0] = 0.00895

    =================================
    Dap   7. Mon Jan 12 03:20:16 2004
     

    Testing Ho: machine
    Denominator: machine * person
    EMS(machine*person) =
        3 Var(machine*person)
        1 Var(Error)
    EMS(machine) =
        18 Var(machine)
        3 Var(machine*person)
        1 Var(Error)
    Error for machine =
        1 MS(machine*person)
    Number of observations = 54
    H0 SS = 1755.26, df = 2, MS = 877.632
    Residual df = 10, MS = 42.653
    F0 = 20.5761
    Prob[F > F0] = 0.00029

    =================================
    Dap   8. Mon Jan 12 03:20:16 2004
     

    Least-squares means for: machine

    LSD  method
    Minimum significant differences are for level 0.05000

    =================================
    Dap   9. Mon Jan 12 03:20:17 2004
     

                                _stat_ for _lsm_ / machine
    ===================================================================
    |                          |52.3556     |60.3222     |66.2722     |
    |--------+--------+--------|------------+------------+------------|
    |_type_  |_LSMEAN_|_machine|1           |2           |3           |
    |========|========|========|============|============|============|
    |EFFN    |0       |        |          18|          18|          18|
    |--------+--------+--------|------------+------------+------------|
    |LSMDIFF |52.3556 |1       |            |     7.96667|     13.9167|
    |        |--------+--------|------------+------------+------------|
    |        |60.3222 |2       |    -7.96667|            |        5.95|
    |        |--------+--------|------------+------------+------------|
    |        |66.2722 |3       |    -13.9167|       -5.95|            |
    |--------+--------+--------|------------+------------+------------|
    |MINDIFF |52.3556 |1       |            |     4.85062|     4.85062|
    |        |--------+--------|------------+------------+------------|
    |        |60.3222 |2       |     4.85062|            |     4.85062|
    |        |--------+--------|------------+------------+------------|
    |        |66.2722 |3       |     4.85062|     4.85062|            |
    |--------+--------+--------|------------+------------+------------|
    |PROB    |52.3556 |1       |            |  0.00439263| 7.90648e-05|
    |        |--------+--------|------------+------------+------------|
    |        |60.3222 |2       |  0.00439263|            |   0.0210791|
    |        |--------+--------|------------+------------+------------|
    |        |66.2722 |3       | 7.90648e-05|   0.0210791|            |
    -------------------------------------------------------------------
     

    Mixed model, unbalanced [Back to Sample output]

    AMD:  pp. 290 - 295
    =================================
    Dap   1. Mon Jan 12 03:20:18 2004
     

    Response variable: productivity

    Treatment       Levels
    --------        ------
    machine         1 2 3
    person          1 2 3 4 5 6
     

    =================================
    Dap   2. Mon Jan 12 03:20:18 2004
     

    Testing Ho: machine person machine*person
    Number of observations = 44
    H0 SS = 3061.74, df = 17, MS = 180.103
    Error SS = 22.6867, df = 26, MS = 0.872564
    R-sq = 0.992645
    F0 = 206.406
    Prob[F > F0] = 0.00001

    =================================
    Dap   3. Mon Jan 12 03:20:18 2004
     

    Testing Ho: machine
    Number of observations = 44
    H0 SS = 1238.2, df = 2, MS = 619.099
    Error SS = 22.6867, df = 26, MS = 0.872564
    F0 = 709.517
    Prob[F > F0] = 0.00001

    =================================
    Dap   4. Mon Jan 12 03:20:18 2004
     

    Testing Ho: person
    Number of observations = 44
    H0 SS = 1011.05, df = 5, MS = 202.211
    Error SS = 22.6867, df = 26, MS = 0.872564
    F0 = 231.743
    Prob[F > F0] = 0.00001

    =================================
    Dap   5. Mon Jan 12 03:20:18 2004
     

    Testing Ho: machine*person
    Number of observations = 44
    H0 SS = 404.315, df = 10, MS = 40.4315
    Error SS = 22.6867, df = 26, MS = 0.872564
    F0 = 46.3364
    Prob[F > F0] = 0.00001

    =================================
    Dap   6. Mon Jan 12 03:20:19 2004
     

    Testing Ho: person
    Denominator: machine * person
    EMS(machine*person) =
        2.31622 Var(machine*person)
        1 Var(Error)
    EMS(person) =
        6.72245 Var(person)
        2.24082 Var(machine*person)
        1 Var(Error)
    Error for person =
        0.0325538 MS(Error)
        0.967446 MS(machine*person)
    Number of observations = 44
    H0 SS = 1011.05, df = 5, MS = 202.211
    Residual df = 10.0145, MS = 39.1437
    F0 = 5.16586
    Prob[F > F0] = 0.01334

    =================================
    Dap   7. Mon Jan 12 03:20:19 2004
     

    Testing Ho: machine
    Denominator: machine * person
    EMS(machine*person) =
        2.31622 Var(machine*person)
        1 Var(Error)
    EMS(machine) =
        12.8219 Var(machine)
        2.13699 Var(machine*person)
        1 Var(Error)
    Error for machine =
        0.0773812 MS(Error)
        0.922619 MS(machine*person)
    Number of observations = 44
    H0 SS = 1238.2, df = 2, MS = 619.099
    Residual df = 10.0362, MS = 37.3704
    F0 = 16.5666
    Prob[F > F0] = 0.00067

    =================================
    Dap   8. Mon Jan 12 03:20:19 2004
     

    Least-squares means for: machine

    LSD  method
    Minimum significant differences are for level 0.05000

    =================================
    Dap   9. Mon Jan 12 03:20:19 2004
     

                                _stat_ for _lsm_ / machine
    ===================================================================
    |                          |52.3136     |60.022      |66.2722     |
    |--------+--------+--------|------------+------------+------------|
    |_type_  |_LSMEAN_|_machine|1           |2           |3           |
    |========|========|========|============|============|============|
    |EFFN    |0       |        |     11.4088|     12.8061|          18|
    |--------+--------+--------|------------+------------+------------|
    |LSMDIFF |52.3136 |1       |            |      7.7084|     13.9586|
    |        |--------+--------|------------+------------+------------|
    |        |60.022  |2       |     -7.7084|            |     6.25021|
    |        |--------+--------|------------+------------+------------|
    |        |66.2722 |3       |    -13.9586|    -6.25021|            |
    |--------+--------+--------|------------+------------+------------|
    |MINDIFF |52.3136 |1       |            |     5.54278|     5.15225|
    |        |--------+--------|------------+------------+------------|
    |        |60.022  |2       |     5.54278|            |     4.97724|
    |        |--------+--------|------------+------------+------------|
    |        |66.2722 |3       |     5.15225|     4.97724|            |
    |--------+--------+--------|------------+------------+------------|
    |PROB    |52.3136 |1       |            |   0.0112602| 0.000124789|
    |        |--------+--------|------------+------------+------------|
    |        |60.022  |2       |   0.0112602|            |   0.0188437|
    |        |--------+--------|------------+------------+------------|
    |        |66.2722 |3       | 0.000124789|   0.0188437|            |
    -------------------------------------------------------------------
     

    Split plot   [Back to Sample output]

    AMD:  pp. 297 - 308
    =================================
    Dap   1. Mon Jan 12 02:33:16 2004

    Whole plot (block, fertilizer) analysis

    Response variable: yield

    Treatment       Levels
    --------        ------
    fertilizer      1 2 3 4
    block           1 2
    variety         1 2
     

    =================================
    Dap   2. Mon Jan 12 02:33:16 2004

    Whole plot (block, fertilizer) analysis

    Testing Ho: fertilizer block
    Denominator: fertilizer*block variety fertilizer*variety block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 171.293, df = 4, MS = 42.8231
    Residual SS = 19.1575, df = 11, MS = 1.74159
    R-sq = 0.899409
    F0 = 24.5885
    Prob[F > F0] = 0.00002

    =================================
    Dap   3. Mon Jan 12 02:33:16 2004

    Whole plot (block, fertilizer) analysis

    Testing Ho: fertilizer
    Denominator: fertilizer*block variety fertilizer*variety block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 40.19, df = 3, MS = 13.3967
    Residual SS = 19.1575, df = 11, MS = 1.74159
    F0 = 7.6922
    Prob[F > F0] = 0.00479

    =================================
    Dap   4. Mon Jan 12 02:33:17 2004

    Whole plot (block, fertilizer) analysis

    Testing Ho: block
    Denominator: fertilizer*block variety fertilizer*variety block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 131.103, df = 1, MS = 131.103
    Residual SS = 19.1575, df = 11, MS = 1.74159
    F0 = 75.2774
    Prob[F > F0] = 0.00001

    =================================
    Dap   5. Mon Jan 12 02:33:17 2004

    Whole plot (block, fertilizer) analysis

    Testing Ho: fertilizer
    Denominator: fertilizer * block
    EMS(fertilizer*block) =
        2 Var(fertilizer*block)
        1 Var(Error)
    EMS(fertilizer) =
        4 Var(fertilizer)
        2 Var(fertilizer*block)
        1 Var(Error)
    Error for fertilizer =
        1 MS(fertilizer*block)
    Number of observations = 16
    H0 SS = 40.19, df = 3, MS = 13.3967
    Residual df = 3, MS = 2.30917
    F0 = 5.80152
    Prob[F > F0] = 0.09137

    =================================
    Dap   6. Mon Jan 12 02:33:17 2004

    Whole plot (block, fertilizer) analysis

    Least-squares means for: fertilizer

    LSD  method
    Minimum significant differences are for level 0.05000

    =================================
    Dap   7. Mon Jan 12 02:33:18 2004

    Whole plot (block, fertilizer) analysis

                                _stat_ for _lsm_ / fertilizer
    ================================================================================
    |                          |38.8        |39.4        |39.8        |42.9        |
    |--------+--------+--------|------------+------------+------------+------------|
    |_type_  |_LSMEAN_|_fertili|1           |3           |2           |4           |
    |========|========|========|============|============|============|============|
    |EFFN    |0       |        |           4|           4|           4|           4|
    |--------+--------+--------|------------+------------+------------+------------|
    |LSMDIFF |38.8    |1       |            |         0.6|           1|         4.1|
    |        |--------+--------|------------+------------+------------+------------|
    |        |39.4    |3       |        -0.6|            |         0.4|         3.5|
    |        |--------+--------|------------+------------+------------+------------|
    |        |39.8    |2       |          -1|        -0.4|            |         3.1|
    |        |--------+--------|------------+------------+------------+------------|
    |        |42.9    |4       |        -4.1|        -3.5|        -3.1|            |
    |--------+--------+--------|------------+------------+------------+------------|
    |MINDIFF |38.8    |1       |            |     3.41955|     3.41955|     3.41955|
    |        |--------+--------|------------+------------+------------+------------|
    |        |39.4    |3       |     3.41955|            |     3.41955|     3.41955|
    |        |--------+--------|------------+------------+------------+------------|
    |        |39.8    |2       |     3.41955|     3.41955|            |     3.41955|
    |        |--------+--------|------------+------------+------------+------------|
    |        |42.9    |4       |     3.41955|     3.41955|     3.41955|            |
    |--------+--------+--------|------------+------------+------------+------------|
    |PROB    |38.8    |1       |            |    0.615544|    0.420682|    0.031666|
    |        |--------+--------|------------+------------+------------+------------|
    |        |39.4    |3       |    0.615544|            |    0.734441|   0.0472285|
    |        |--------+--------|------------+------------+------------+------------|
    |        |39.8    |2       |    0.420682|    0.734441|            |   0.0632693|
    |        |--------+--------|------------+------------+------------+------------|
    |        |42.9    |4       |    0.031666|   0.0472285|   0.0632693|            |
    --------------------------------------------------------------------------------

    =================================
    Dap   8. Mon Jan 12 02:33:18 2004

    Subplot (variety) analysis

    Response variable: yield

    Treatment       Levels
    --------        ------
    fertilizer      1 2 3 4
    block           1 2
    variety         1 2
     

    =================================
    Dap   9. Mon Jan 12 02:33:18 2004

    Subplot (variety) analysis

    Testing Ho: fertilizer block fertilizer*block variety fertilizer*variety
    Denominator: block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 182.02, df = 11, MS = 16.5473
    Residual SS = 8.43, df = 4, MS = 2.1075
    R-sq = 0.955736
    F0 = 7.85161
    Prob[F > F0] = 0.03064

    =================================
    Dap  10. Mon Jan 12 02:33:18 2004

    Subplot (variety) analysis

    Testing Ho: fertilizer
    Denominator: block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 40.19, df = 3, MS = 13.3967
    Residual SS = 8.43, df = 4, MS = 2.1075
    F0 = 6.35666
    Prob[F > F0] = 0.05300

    =================================
    Dap  11. Mon Jan 12 02:33:18 2004

    Subplot (variety) analysis

    Testing Ho: block
    Denominator: block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 131.103, df = 1, MS = 131.103
    Residual SS = 8.43, df = 4, MS = 2.1075
    F0 = 62.2076
    Prob[F > F0] = 0.00140

    =================================
    Dap  12. Mon Jan 12 02:33:18 2004

    Subplot (variety) analysis

    Testing Ho: variety
    Denominator: block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 2.25, df = 1, MS = 2.25
    Residual SS = 8.43, df = 4, MS = 2.1075
    F0 = 1.06762
    Prob[F > F0] = 0.35987

    =================================
    Dap  13. Mon Jan 12 02:33:18 2004

    Subplot (variety) analysis

    Testing Ho: fertilizer*block
    Denominator: block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 6.9275, df = 3, MS = 2.30917
    Residual SS = 8.43, df = 4, MS = 2.1075
    F0 = 1.09569
    Prob[F > F0] = 0.44760

    =================================
    Dap  14. Mon Jan 12 02:33:18 2004

    Subplot (variety) analysis

    Testing Ho: fertilizer*variety
    Denominator: block*variety fertilizer*block*variety
    Number of observations = 16
    H0 SS = 1.55, df = 3, MS = 0.516667
    Residual SS = 8.43, df = 4, MS = 2.1075
    F0 = 0.245156
    Prob[F > F0] = 0.86125

    Latin square   [Back to Sample output]

    ED: pp. 122 - 125
    =================================
    Dap   1. Mon Jan 12 03:20:29 2004
     

    Response variable: error

    Treatment       Levels
    --------        ------
    sampler         A B C D E F
    area            1 2 3 4 5 6
    order           6 5 1 2 4 3
     

    =================================
    Dap   2. Mon Jan 12 03:20:34 2004
     

    Testing Ho: sampler area order
    Denominator: sampler*area*order
    Number of observations = 36
    H0 SS = 263.064, df = 15, MS = 17.5376
    Residual SS = 66.5633, df = 20, MS = 3.32817
    R-sq = 0.798065
    F0 = 5.26945
    Prob[F > F0] = 0.00039

    =================================
    Dap   3. Mon Jan 12 03:20:34 2004
     

    Testing Ho: sampler
    Denominator: sampler*area*order
    Number of observations = 36
    H0 SS = 155.596, df = 5, MS = 31.1192
    Residual SS = 66.5633, df = 20, MS = 3.32817
    F0 = 9.35024
    Prob[F > F0] = 0.00011

    =================================
    Dap   4. Mon Jan 12 03:20:34 2004
     

    Least-squares means for: sampler

    LSD  method
    Minimum significant differences are for level 0.05000

    =================================
    Dap   5. Mon Jan 12 03:20:35 2004
     

                                _stat_ for _lsm_ / sampler
    ==========================================================================================================
    |                          |1.2         |2.66667     |5.58333     |6.06667     |6.11667     |6.91667     |
    |--------+--------+--------|------------+------------+------------+------------+------------+------------|
    |_type_  |_LSMEAN_|_sampler|F           |E           |B           |A           |C           |D           |
    |========|========|========|============|============|============|============|============|============|
    |EFFN    |0       |        |           6|           6|           6|           6|           6|           6|
    |--------+--------+--------|------------+------------+------------+------------+------------+------------|
    |LSMDIFF |1.2     |F       |            |     1.46667|     4.38333|     4.86667|     4.91667|     5.71667|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |2.66667 |E       |    -1.46667|            |     2.91667|         3.4|        3.45|        4.25|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |5.58333 |B       |    -4.38333|    -2.91667|            |    0.483333|    0.533333|     1.33333|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.06667 |A       |    -4.86667|        -3.4|   -0.483333|            |        0.05|        0.85|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.11667 |C       |    -4.91667|       -3.45|   -0.533333|       -0.05|            |         0.8|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.91667 |D       |    -5.71667|       -4.25|    -1.33333|       -0.85|        -0.8|            |
    |--------+--------+--------|------------+------------+------------+------------+------------+------------|
    |MINDIFF |1.2     |F       |            |     2.19708|     2.19708|     2.19708|     2.19708|     2.19708|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |2.66667 |E       |     2.19708|            |     2.19708|     2.19708|     2.19708|     2.19708|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |5.58333 |B       |     2.19708|     2.19708|            |     2.19708|     2.19708|     2.19708|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.06667 |A       |     2.19708|     2.19708|     2.19708|            |     2.19708|     2.19708|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.11667 |C       |     2.19708|     2.19708|     2.19708|     2.19708|            |     2.19708|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.91667 |D       |     2.19708|     2.19708|     2.19708|     2.19708|     2.19708|            |
    |--------+--------+--------|------------+------------+------------+------------+------------+------------|
    |PROB    |1.2     |F       |            |    0.179066| 0.000482096| 0.000165276| 0.000148021| 2.59349e-05|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |2.66667 |E       |    0.179066|            |   0.0118367|   0.0042174|  0.00378313|  0.00064819|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |5.58333 |B       | 0.000482096|   0.0118367|            |    0.651264|    0.618142|    0.220099|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.06667 |A       | 0.000165276|   0.0042174|    0.651264|            |    0.962609|    0.429156|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.11667 |C       | 0.000148021|  0.00378313|    0.618142|    0.962609|            |    0.456392|
    |        |--------+--------|------------+------------+------------+------------+------------+------------|
    |        |6.91667 |D       | 2.59349e-05|  0.00064819|    0.220099|    0.429156|    0.456392|            |
    ----------------------------------------------------------------------------------------------------------

    =================================
    Dap   6. Mon Jan 12 03:20:35 2004
     

    Testing Ho: area
    Denominator: sampler*area*order
    Number of observations = 36
    H0 SS = 78.8692, df = 5, MS = 15.7738
    Residual SS = 66.5633, df = 20, MS = 3.32817
    F0 = 4.7395
    Prob[F > F0] = 0.00512

    =================================
    Dap   7. Mon Jan 12 03:20:35 2004
     

    Testing Ho: order
    Denominator: sampler*area*order
    Number of observations = 36
    H0 SS = 28.5992, df = 5, MS = 5.71983
    Residual SS = 66.5633, df = 20, MS = 3.32817
    F0 = 1.71861
    Prob[F > F0] = 0.17635

    Missing treatment combinations  [Back to Sample output]

    AMD: pp. 173 - 177
    =================================
    Dap   1. Mon Jan 12 04:25:05 2004

    Test Ho:
    u11 - u21 - (u13 - u23) = 0
    u21 - u31 - (u22 - u32) = 0

    Testing Ho: treat*block
    Number of observations = 10
    H0 SS = 18.7778, df = 2, MS = 9.38889
    Error SS = 14.5, df = 3, MS = 4.83333
    F0 = 1.94253
    Prob[F > F0] = 0.28763

    =================================
    Dap   2. Mon Jan 12 04:25:05 2004

    Test Ho:
    u11 + u13 - (u21 + u23) = 0
    u21 + u22 - (u31 + u32) = 0

    Testing Ho: treat
    Number of observations = 10
    H0 SS = 2.77778, df = 2, MS = 1.38889
    Error SS = 14.5, df = 3, MS = 4.83333
    F0 = 0.287356
    Prob[F > F0] = 0.76882

    Linear regression  [Back to Sample output]

    MS: pp. 95 - 97
    =================================
    Dap   1. Mon Jan 12 03:20:40 2004
     

    Reduced | full model regressors: _intercept_ | soilphos
    Number of observations = 9

    Response: plantphos
       F0(1, 7) = 12.8868, Prob[F > F0] = 0.00886
       R-sq = 0.648008, Adj R-sq = 0.597723

       Parameter           Estimate    Std Error   T0[     7]  Prob[|T|>|T0|]
       _intercept_          61.5804      6.24765      9.85656         0.00003
       soilphos             1.41689     0.394698      3.58982         0.00886

    Linear regression, model building   [Back to Sample output]

    LM: pp. 50 - 60
    =================================
    Dap   1. Mon Jan 12 03:20:39 2004

    Correlations

                       _corr_ for _var2_
    ====================================================================================
    |_var1_  |_type_  |x1          |x2          |x3          |x4          |y           |
    |========|========|============|============|============|============|============|
    |x1      |CORR    |           1|    0.971236|   -0.668403|    0.651995|    0.740306|
    |        |--------|------------+------------+------------+------------+------------|
    |        |N       |          10|          10|          10|          10|          10|
    |        |--------|------------+------------+------------+------------+------------|
    |        |PCORR   |           0| 2.89253e-06|    0.034618|   0.0410635|   0.0143438|
    |--------+--------|------------+------------+------------+------------+------------|
    |x2      |CORR    |    0.971236|           1|    -0.59782|    0.526844|    0.627619|
    |        |--------|------------+------------+------------+------------+------------|
    |        |N       |          10|          10|          10|          10|          10|
    |        |--------|------------+------------+------------+------------+------------|
    |        |PCORR   | 2.89253e-06|           0|   0.0679458|    0.117662|   0.0520562|
    |--------+--------|------------+------------+------------+------------+------------|
    |x3      |CORR    |   -0.668403|    -0.59782|           1|    -0.84101|   -0.780072|
    |        |--------|------------+------------+------------+------------+------------|
    |        |N       |          10|          10|          10|          10|          10|
    |        |--------|------------+------------+------------+------------+------------|
    |        |PCORR   |    0.034618|   0.0679458|           0|  0.00229667|  0.00777379|
    |--------+--------|------------+------------+------------+------------+------------|
    |x4      |CORR    |    0.651995|    0.526844|    -0.84101|           1|    0.977603|
    |        |--------|------------+------------+------------+------------+------------|
    |        |N       |          10|          10|          10|          10|          10|
    |        |--------|------------+------------+------------+------------+------------|
    |        |PCORR   |   0.0410635|    0.117662|  0.00229667|           0| 1.07154e-06|
    |--------+--------|------------+------------+------------+------------+------------|
    |y       |CORR    |    0.740306|    0.627619|   -0.780072|    0.977603|           1|
    |        |--------|------------+------------+------------+------------+------------|
    |        |N       |          10|          10|          10|          10|          10|
    |        |--------|------------+------------+------------+------------+------------|
    |        |PCORR   |   0.0143438|   0.0520562|  0.00777379| 1.07154e-06|           0|
    ------------------------------------------------------------------------------------

    =================================
    Dap   2. Mon Jan 12 03:20:39 2004

    Model building

    Reduced | full model regressors: _intercept_ | x4
    Number of observations = 10

    Response: y
       F0(1, 8) = 172.619, Prob[F > F0] = 0.00001
       R-sq = 0.955708, Adj R-sq = 0.950171

       Parameter           Estimate    Std Error   T0[     8]  Prob[|T|>|T0|]
       _intercept_          21.8042      2.83157      7.70041         0.00006
       x4                   1.02579    0.0780755      13.1384         0.00001

    =================================
    Dap   3. Mon Jan 12 03:20:39 2004

    Model building

    Reduced | full model regressors: _intercept_ x4 | x1
    Number of observations = 10

    Response: y
       F0(2, 7) = 131.793, Prob[F > F0] = 0.00001
       R-sq = 0.97413, Adj R-sq = 0.966739
       F-change(1, 7) = 4.98488, Prob[F > F-change] = 0.06073

       Parameter           Estimate    Std Error   T0[     7]  Prob[|T|>|T0|]
       _intercept_          12.9449      4.59315      2.81831         0.02584
       x4                  0.903324     0.084129      10.7374         0.00002
       x1                   1.88521     0.844369      2.23268         0.06073

    =================================
    Dap   4. Mon Jan 12 03:20:39 2004

    Model building

    Reduced | full model regressors: _intercept_ x4 x1 | x3
    Number of observations = 10

    Response: y
       F0(3, 6) = 183.912, Prob[F > F0] = 0.00001
       R-sq = 0.989242, Adj R-sq = 0.983863
       F-change(1, 6) = 8.42848, Prob[F > F-change] = 0.02723

       Parameter           Estimate    Std Error   T0[     6]  Prob[|T|>|T0|]
       _intercept_          2.55427      4.80051     0.532084         0.61379
       x4                   1.07907    0.0842512      12.8078         0.00002
       x1                   2.40786     0.615063      3.91482         0.00785
       x3                  0.936516     0.322582      2.90318         0.02723

    =================================
    Dap   5. Mon Jan 12 03:20:39 2004

    Model building

    Reduced | full model regressors: _intercept_ x4 x1 x3 | x2
    Number of observations = 10

    Response: y
       F0(4, 5) = 126.46, Prob[F > F0] = 0.00004
       R-sq = 0.990212, Adj R-sq = 0.982382
       F-change(1, 5) = 0.495515, Prob[F > F-change] = 0.51290

       Parameter           Estimate    Std Error   T0[     5]  Prob[|T|>|T0|]
       _intercept_          2.80985      5.02914     0.558715         0.60046
       x4                   1.12232     0.107355      10.4543         0.00014
       x1                  0.523737      2.75266     0.190266         0.85659
       x3                  0.994528     0.346992      2.86614         0.03516
       x2                  0.775412      1.10155     0.703928         0.51290

    Ordinal cross-classification [Back to Sample output]

    CDA: pp. 49 - 50
    =================================
    Dap   1. Mon Jan 12 03:20:25 2004
     

    Variable: Levels
    ----------------
    income: 00-06 06-15 15-25 25-
    jobsat: 1verydis 2littledis 3modsat 4verysat

    Chisq0[9] = 11.9886, Prob[Chisq > Chisq0] = 0.21396
    Statistic          Value   ASE
    Gamma              0.127  0.041
    Kendall's Tau-b    0.088  0.028
    Somers' D C|R      0.082  0.026
    Somers' D R|C      0.094  0.030

    =================================
    Dap   2. Mon Jan 12 03:20:25 2004
     

                       _cell_ for jobsat
    =======================================================================
    |income  |_type_  |1verydis    |2littledis  |3modsat     |4verysat    |
    |========|========|============|============|============|============|
    |00-06   |COUNT   |          20|          24|          80|          82|
    |        |--------|------------+------------+------------+------------|
    |        |EXPECTED|     14.1754|     24.6926|     72.9345|     94.1976|
    |--------+--------|------------+------------+------------+------------|
    |06-15   |COUNT   |          22|          38|         104|         125|
    |        |--------|------------+------------+------------+------------|
    |        |EXPECTED|     19.8868|     34.6415|     102.321|     132.151|
    |--------+--------|------------+------------+------------+------------|
    |15-25   |COUNT   |          13|          28|          81|         113|
    |        |--------|------------+------------+------------+------------|
    |        |EXPECTED|     16.1709|     28.1687|      83.202|     107.458|
    |--------+--------|------------+------------+------------+------------|
    |25-     |COUNT   |           7|          18|          54|          92|
    |        |--------|------------+------------+------------+------------|
    |        |EXPECTED|     11.7669|     20.4972|     60.5427|     78.1931|
    -----------------------------------------------------------------------
     

    Stratified 2x2 tables [Back to Sample output]

    CDA: pp. 232 - 233
    =================================
    Dap   1. Mon Jan 12 03:20:24 2004
     

    Cochran-Mantel-Haenszel test for delay x response, stratified by penicillin
    M0-squared = 3.92857, Prob[M-squared > M0-squared] = 0.0475

    =================================
    Dap   2. Mon Jan 12 03:20:24 2004
     

    For: penicillin = 0.125

              _cell_ for response
    ====================================
    |delay   |cured       |died        |
    |========|============|============|
    |1.5h    |           0|           5|
    |--------|------------+------------|
    |none    |           0|           6|
    ------------------------------------

    =================================
    Dap   3. Mon Jan 12 03:20:24 2004
     

    For: penicillin = 0.250

              _cell_ for response
    ====================================
    |delay   |cured       |died        |
    |========|============|============|
    |1.5h    |           0|           6|
    |--------|------------+------------|
    |none    |           3|           3|
    ------------------------------------

    =================================
    Dap   4. Mon Jan 12 03:20:24 2004
     

    For: penicillin = 0.500

              _cell_ for response
    ====================================
    |delay   |cured       |died        |
    |========|============|============|
    |1.5h    |           2|           4|
    |--------|------------+------------|
    |none    |           6|           0|
    ------------------------------------

    =================================
    Dap   5. Mon Jan 12 03:20:24 2004
     

    For: penicillin = 1.000

              _cell_ for response
    ====================================
    |delay   |cured       |died        |
    |========|============|============|
    |1.5h    |           6|           0|
    |--------|------------+------------|
    |none    |           5|           1|
    ------------------------------------

    =================================
    Dap   6. Mon Jan 12 03:20:24 2004
     

    For: penicillin = 4.000

              _cell_ for response
    ====================================
    |delay   |cured       |died        |
    |========|============|============|
    |1.5h    |           5|           0|
    |--------|------------+------------|
    |none    |           2|           0|
    ------------------------------------

    Loglinear models   [Back to Sample output]

    CDA: pp. 135 - 138, 171 - 174, 176 - 177
    =================================
    Dap   1. Mon Jan 12 03:19:54 2004

    (DV, P) vs (D, V, P)

    Loglinear model:
    numerical indexes of classification variables

    Number  defendant  victim  penalty
    ------  ---------  ------  -------
         1  black      black   no
         2  white      white   yes
     

    =================================
    Dap   2. Mon Jan 12 03:19:55 2004

    (DV, P) vs (D, V, P)

    Maximum likelihood estimation

    Cell count: n
    Class and aux variables: _defendant _victim _penalty

    Statistic              df      Prob
    G2[Model]   =   8.13    3    0.0434
    G2[Reduced] = 137.93    4    0.0001
    G2[Diff]    = 129.80    1    0.0001
    X2[Model]   =   6.98    3    0.0727

        Estimate          ASE  Model  Parameter
         2.83789     0.117031    *    _mu
         0.39084    0.0946427    *    defendant:1
       -0.582116    0.0946427    *    victim:1
        0.827863    0.0946427    ?    defendant*victim:1:1
         1.04323    0.0883545    *    penalty:1
     

    =================================
    Dap   3. Mon Jan 12 03:19:55 2004

    (DV, P) vs (D, V, P)

                                   n for _type_ / penalty
    ===========================================================
    |                             |FIT          |OBS          |
    |--------------+--------------|------+------+------+------|
    |defendant     |victim        |no    |yes   |no    |yes   |
    |==============|==============|======|======|======|======|
    |black         |black         | 91.63| 11.37| 97.00|  6.00|
    |              |--------------|------+------+------+------|
    |              |white         | 56.04|  6.96| 52.00| 11.00|
    |--------------+--------------|------+------+------+------|
    |white         |black         |  8.01|  0.99|  9.00|  0.00|
    |              |--------------|------+------+------+------|
    |              |white         |134.33| 16.67|132.00| 19.00|
    -----------------------------------------------------------

    =================================
    Dap   4. Mon Jan 12 03:19:55 2004

    (DV, VP) vs (DV, P)

    Loglinear model:
    numerical indexes of classification variables

    Number  defendant  victim  penalty
    ------  ---------  ------  -------
         1  black      black   no
         2  white      white   yes
     

    =================================
    Dap   5. Mon Jan 12 03:19:55 2004

    (DV, VP) vs (DV, P)

    Maximum likelihood estimation

    Cell count: n
    Class and aux variables: _defendant _victim _penalty

    Statistic              df      Prob
    G2[Model]   =   1.88    2    0.3903
    G2[Reduced] =   8.13    3    0.0434
    G2[Diff]    =   6.25    1    0.0125
    X2[Model]   =   1.43    2    0.4889

        Estimate          ASE  Model  Parameter
         2.72369      0.13779    *    _mu
         0.39084    0.0946425    *    defendant:1
        -0.79861      0.13779    *    victim:1
        0.827913    0.0946425    *    defendant*victim:1:1
          1.1713     0.115885    *    penalty:1
        0.264535     0.115885    ?    victim*penalty:1:1
     

    =================================
    Dap   6. Mon Jan 12 03:19:55 2004

    (DV, VP) vs (DV, P)

                                   n for _type_ / penalty
    ===========================================================
    |                             |FIT          |OBS          |
    |--------------+--------------|------+------+------+------|
    |defendant     |victim        |no    |yes   |no    |yes   |
    |==============|==============|======|======|======|======|
    |black         |black         | 97.48|  5.52| 97.00|  6.00|
    |              |--------------|------+------+------+------|
    |              |white         | 54.17|  8.83| 52.00| 11.00|
    |--------------+--------------|------+------+------+------|
    |white         |black         |  8.52|  0.48|  9.00|  0.00|
    |              |--------------|------+------+------+------|
    |              |white         |129.83| 21.17|132.00| 19.00|
    -----------------------------------------------------------

    =================================
    Dap   7. Mon Jan 12 03:19:55 2004

    (DV, DP, VP) vs (DV, VP)

    Loglinear model:
    numerical indexes of classification variables

    Number  defendant  victim  penalty
    ------  ---------  ------  -------
         1  black      black   no
         2  white      white   yes
     

    =================================
    Dap   8. Mon Jan 12 03:19:55 2004

    (DV, DP, VP) vs (DV, VP)

    Maximum likelihood estimation

    Cell count: n
    Class and aux variables: _defendant _victim _penalty

    Statistic              df      Prob
    G2[Model]   =   0.70    1    0.4026
    G2[Reduced] =   1.88    2    0.3903
    G2[Diff]    =   1.18    1    0.2772
    X2[Model]   =   0.38    1    0.5401

        Estimate          ASE  Model  Parameter
         2.69211     0.142941    *    _mu
        0.479402     0.124301    *    defendant:1
       -0.854001     0.146841    *    victim:1
        0.839499    0.0954928    *    defendant*victim:1:1
         1.20005     0.119974    *    penalty:1
       -0.110105     0.100222    ?    defendant*penalty:1:1
        0.331103     0.129837    *    victim*penalty:1:1
     

    =================================
    Dap   9. Mon Jan 12 03:19:55 2004

    (DV, DP, VP) vs (DV, VP)

                                   n for _type_ / penalty
    ===========================================================
    |                             |FIT          |OBS          |
    |--------------+--------------|------+------+------+------|
    |defendant     |victim        |no    |yes   |no    |yes   |
    |==============|==============|======|======|======|======|
    |black         |black         | 97.33|  5.67| 97.00|  6.00|
    |              |--------------|------+------+------+------|
    |              |white         | 51.67| 11.33| 52.00| 11.00|
    |--------------+--------------|------+------+------+------|
    |white         |black         |  8.67|  0.33|  9.00|  0.00|
    |              |--------------|------+------+------+------|
    |              |white         |132.33| 18.67|132.00| 19.00|
    -----------------------------------------------------------

    Logit model for linear-by-linear association [Back to Sample output]

    CDA: pp.  261 -  269
    =================================
    Dap   1. Mon Jan 12 03:19:56 2004
     

    Maximum likelihood estimation

    Cell count: count
    Class and aux variables: income jobsat

    Statistic              df      Prob
    G2[Model]   =   2.39    8    0.9669
    G2[Reduced] =  12.04    9    0.2113
    G2[Diff]    =   9.65    1    0.0019
    X2[Model]   =   2.33    8    0.9693

        Estimate          ASE  Model  Parameter
         3.47292     0.102512    *    mu
        0.294928     0.132411    *    <6
        0.396336      0.06927    *    6-15
      -0.0581172     0.068397    *    15-25
       -0.805298     0.118785    *    VeryDis
       -0.385834    0.0853789    *    LittleDis
        0.548591    0.0620011    *    ModSat
         0.11199    0.0364075    ?    Inc*Sat
     

    =================================
    Dap   2. Mon Jan 12 03:19:57 2004
     

              count for _type_ / jobsat
    ==================================================================
    |        |FIT                        |OBS                        |
    |--------|------+------+------+------+------+------+------+------|
    |income  |0     |1     |2     |3     |0     |1     |2     |3     |
    |========|======|======|======|======|======|======|======|======|
    |0       | 19.35| 29.43| 74.93| 82.30| 20.00| 24.00| 80.00| 82.00|
    |--------|------+------+------+------+------+------+------+------|
    |1       | 21.41| 36.43|103.73|127.43| 22.00| 38.00|104.00|125.00|
    |--------|------+------+------+------+------+------+------+------|
    |2       | 13.59| 25.86| 82.37|113.18| 13.00| 28.00| 81.00|113.00|
    |--------|------+------+------+------+------+------+------+------|
    |3       |  7.65| 16.28| 57.98| 89.10|  7.00| 18.00| 54.00| 92.00|
    ------------------------------------------------------------------

    Logistic regression  [Back to Sample output]

    CDA: pp. 87 - 89
    =================================
    Dap   1. Mon Jan 12 03:20:27 2004
     

    Reduced | full model regressors: _intercept_ | labind
    Number of observations = 14
    Number of trials = 27
    Events / Trials: nremiss / ncases
    -2 (Lred - Lfull) = 8.2988 = ChiSq0[1]
    Prob[ChiSq > ChiSq0] = 0.00397

      Parameter           Estimate    Std Error   Wald ChiSq  Prob[ChiSq>Wald ChiSq]
      _intercept_         -3.77714      1.37863       7.5064         0.00615
      labind              0.144863    0.0593411      5.95942         0.01464


    Return to GNU's home page.

    Please send FSF & GNU inquiries & questions to gnu@gnu.org. There are also other ways to contact the FSF.

    Please send comments on these web pages to webmasters@gnu.org, send other questions to gnu@gnu.org.

    Copyright © 2001, 2002, 2003, 2004 Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA

    Verbatim copying and distribution of this entire article is permitted in any medium, provided this notice is preserved.

    Updated: $Date: 2014/01/06 21:03:37 $ $Author: sebdiaz $