How to compare regression coefficients from two models

[Akif Alig]

So, let us suppose I am analyzing the association between BMI and age
But I think the association between BMI and age differs with respect to sex.
So went for subgroup analyses; i.e. I run the model separately for males and females. see below

*First model for males

reg bmi age if sex == 1

      Source |       SS           df       MS      Number of obs   =     4,915
-------------+----------------------------------   F(1, 4913)      =     56.49
       Model |  904.472098         1  904.472098   Prob > F        =    0.0000
    Residual |  78656.2733     4,913  16.0098256   R-squared       =    0.0114
-------------+----------------------------------   Adj R-squared   =    0.0112
       Total |  79560.7454     4,914  16.1906279   Root MSE        =    4.0012

------------------------------------------------------------------------------
         bmi |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0249892   .0033247     7.52   0.000     .0184714    .0315071
       _cons |   24.32491   .1676803   145.07   0.000     23.99618    24.65364
------------------------------------------------------------------------------

Second model for females

 reg bmi age if sex == 2

      Source |       SS           df       MS      Number of obs   =     5,436
-------------+----------------------------------   F(1, 5434)      =    267.03
       Model |  7984.12044         1  7984.12044   Prob > F        =    0.0000
    Residual |  162472.165     5,434  29.8991838   R-squared       =    0.0468
-------------+----------------------------------   Adj R-squared   =    0.0467
       Total |  170456.285     5,435   31.362702   Root MSE        =     5.468

------------------------------------------------------------------------------
         bmi |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0702335   .0042979    16.34   0.000     .0618078    .0786592
       _cons |   22.21097   .2180971   101.84   0.000     21.78342    22.63853
------------------------------------------------------------------------------

Now as you can see the coefficient for males is 0.025 and for females, it is 0.07.

How can I test that the two coefficients are significantly different?

Note: This is not my actual model it is just an example so that I can get a solution. Another thing is that I don't want to do interaction analyses

Thanks and regards

[Carlo Lazzaro]

Akif:
your choice to stay away from interaction is obscure to me.
Anyway, you may want to take a look at: https://stats.oarc.ucla.edu/stata/co...s-using-suest/.