What is a cut point in ologit?

[Sarah Aspen]

Hello,

I am new to Stata and I have done an ologit regression. I don't understand what cut points are and how to interpret them. Could someone explain me? Thank you in advance.



Here is my ologit model:

[William Lisowski]

The Remarks and Examples section of the ologit documentation in the Stata Base Reference Manual PDF included in your Stata installation (and accessible through Stata's Help menu) discusses the interpretation of the cut points.

[Richard Williams]

You may want to read this:

https://www3.nd.edu/~rwilliam/xsoc73994/Ologit01.pdf

People usually don't say much about the cutpoints. But they are used in the calculations of things like predicted probabilities.

[Sarah Aspen]

Thank you very much for your answers! This was very helpful.

[Nahed Eddai]

Dear all,
How can we interpret negative cut points in an ordered logit?
Best regards

[Carlo Lazzaro]

Nahed:
the following toy-example may be useful:

. use "https://www.stata-press.com/data/r16/fullauto.dta"
. ologit rep78 foreign

Iteration 0:   log likelihood = -93.692061 
Iteration 1:   log likelihood = -79.696089 
Iteration 2:   log likelihood = -79.034005 
Iteration 3:   log likelihood = -79.029244 
Iteration 4:   log likelihood = -79.029243 

Ordered logistic regression                     Number of obs     =         69
                                                LR chi2(1)        =      29.33
                                                Prob > chi2       =     0.0000
Log likelihood = -79.029243                     Pseudo R2         =     0.1565

------------------------------------------------------------------------------
       rep78 |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
     foreign |    2.98155   .6203644     4.81   0.000     1.765658    4.197442
-------------+----------------------------------------------------------------
       /cut1 |  -3.158382   .7224269                     -4.574313   -1.742452
       /cut2 |  -1.362642   .3557343                     -2.059868   -.6654154
       /cut3 |   1.232161   .3431227                      .5596532     1.90467
       /cut4 |   3.246209   .5556657                      2.157124    4.335293
------------------------------------------------------------------------------

*The following probabilities calculated by hand refer to Foreign==1*
*Poor (/cut1)*
. di 1/(1+exp(2.98155+3.158382))
.00215044
*Fair (/cut2)*
. di 1/(1+exp(2.98155+1.362642))-1/(1+exp(2.98155+3.158382))
.01066519
*Average (/cut3)*
. di 1/(1+exp(2.98155-1.232161))-1/(1+exp(2.98155+1.362642))
.13530866
*Good (/cut4)*
. di 1/(1+exp(2.98155-3.246209))-1/(1+exp(2.98155-1.232161))
.41765695
*Excellent (here the probability is simply the complement to 1)
. di 1-.00215044-.01066519-.13530866-.41765695
.43421876

*..and to double check*
. list poor fair avg good exc in 4

     +------------------------------------------------------+
     |     poor       fair        avg       good        exc |
     |------------------------------------------------------|
  4. | .0021504   .0106652   .1353087   .4176569   .4342188 |
     +------------------------------------------------------+

.

[Nahed Eddai]

So cut points are used to compute predicted probabilities?

[Carlo Lazzaro]

Nahed:
short answer: yes, they are.
Take a look at -ologit- entry in Stata .pdf manual for more details.

[Nahed Eddai]

Thank you Carlo.