> log

  log type:  text

 opened on:  28 Sep 2005, 11:05:09

 

. edit

(3 vars, 4 obs pasted into editor)

- preserve

 

. set linesize 79

 

. desmat: poisson count color live

-------------------------------------------------------------------------------- 

 Poisson regression

--------------------------------------------------------------------------------

   Dependent variable                                                               count

   Optimization:                                                                       ml

   Number of observations:                                                              4

   Initial log likelihood:                                                        -14.328

   Log likelihood:                                                                 -9.540

   LR chi square:                                                                   9.578

   Model degrees of freedom:                                                            2

   Pseudo R-squared:                                                                0.334

   Prob:                                                                            0.008

------------------------------------------------------------------------------------------

nr Effect                                                               Coeff        s.e.

------------------------------------------------------------------------------------------

   count

     color

1      Green                                                           -0.693**     0.245

     live

2      Water                                                            0.241       0.233

3    _cons                                                              3.091**     0.192

------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. predict independenc

(option n assumed; predicted number of events)

 

. rename independenc independence

 

. tabulate live color [fweight=count]

 

           |         Color

      live |      Blue      Green |     Total

-----------+----------------------+----------

     Lilly |        23         10 |        33

     Water |        27         15 |        42

-----------+----------------------+----------

     Total |        50         25 |        75

 

 

. *This is our actual dataset.

. tabulate live color [fweight= independence]

 

           |         Color

      live |      Blue      Green |     Total

-----------+----------------------+----------

     Lilly |        22         11 |        33

     Water |        28         14 |        42

-----------+----------------------+----------

     Total |        50         25 |        75

 

 

. *This second table is the predicted values under independence.

. *The independence model uses up 3 degrees of freedom

. *The dataset has 4 degrees of freedom

. desmat: poisson count color*live

------------------------------------------------------------------------------------------

   Poisson regression

------------------------------------------------------------------------------------------

   Dependent variable                                                               count

   Optimization:                                                                       ml

   Number of observations:                                                              4

   Initial log likelihood:                                                        -14.328

   Log likelihood:                                                                 -9.417

   LR chi square:                                                                   9.822

   Model degrees of freedom:                                                            3

   Pseudo R-squared:                                                                0.343

   Prob:                                                                            0.020

------------------------------------------------------------------------------------------

nr Effect                                                               Coeff        s.e.

------------------------------------------------------------------------------------------

   count

     color

1      Green                                                           -0.833*      0.379

     live

2      Water                                                            0.160       0.284

     color.live

3      Green.Water                                                      0.245       0.497

4    _cons                                                              3.135**     0.209

------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. *This is the saturated model.

. *Notice that the interaction term, the only interesting term here is actually the

log odds ratio that we calculated by hand in class one.

. *And also notice that the SE of the log odds ratio is the same as we calculated by hand

. poisgof

 

         Goodness-of-fit chi2  =  7.95e-06

         Prob > chi2(0)        =         .

 

. *What this means is that the model fits the data exactly, to within the limit

of the software to maximize the likelihood exactly

. *That was a silly experiment, actually, because the saturated model fits the data exactly,

 and chisquare tests on zero degrees of freedom don't really make sense.

. *However, goodness of fit does mean something for the independence model.

. desmat: poisson count live

------------------------------------------------------------------------------------------

   Poisson regression

------------------------------------------------------------------------------------------

   Dependent variable                                                               count

   Optimization:                                                                       ml

   Number of observations:                                                              4

   Initial log likelihood:                                                        -14.328

   Log likelihood:                                                                -13.787

   LR chi square:                                                                   1.083

   Model degrees of freedom:                                                            1

   Pseudo R-squared:                                                                0.038

   Prob:                                                                            0.298

------------------------------------------------------------------------------------------

nr Effect                                                               Coeff        s.e.

------------------------------------------------------------------------------------------

   count

     live

1      Water                                                            0.241       0.233

2    _cons                                                              2.803**     0.174

------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. desmat: poisson count live color

------------------------------------------------------------------------------------------

   Poisson regression

------------------------------------------------------------------------------------------

   Dependent variable                                                               count

   Optimization:                                                                       ml

   Number of observations:                                                              4

   Initial log likelihood:                                                        -14.328

   Log likelihood:                                                                 -9.540

   LR chi square:                                                                   9.578

   Model degrees of freedom:                                                            2

   Pseudo R-squared:                                                                0.334

   Prob:                                                                            0.008

------------------------------------------------------------------------------------------

nr Effect                                                               Coeff        s.e.

------------------------------------------------------------------------------------------

   count

     live

1      Water                                                            0.241       0.233

     color

2      Green                                                           -0.693**     0.245

3    _cons                                                              3.091**     0.192

------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  .2445188

         Prob > chi2(1)        =    0.6210

 

. poisgof, pearson

 

         Goodness-of-fit chi2  =  .2435065

         Prob > chi2(1)        =    0.6217

 

. *In fact, the way one usually encounters the chisquare test for independence is not

 through loglinear models, of course, but just tacked on the bottom of a table with not much

in the way of explanation.

. tabulate live color [fweight=count], chi2 lrchi2

 

           |         Color

      live |      Blue      Green |     Total

-----------+----------------------+----------

     Lilly |        23         10 |        33

     Water |        27         15 |        42

-----------+----------------------+----------

     Total |        50         25 |        75

 

          Pearson chi2(1) =   0.2435   Pr = 0.622

 likelihood-ratio chi2(1) =   0.2445   Pr = 0.621

 

. exit, clear