boxcox  price  s1 s2 dj dl wd1 wd2 bz yj yj ls lable wl tc yf1 yf2 sh1 sh2  pj dz,lrtest
note: yj dropped because of collinearity
Fitting comparison model

Iteration 0:   log likelihood = -1282.9176  
Iteration 1:   log likelihood =  -1193.974  
Iteration 2:   log likelihood = -1193.9265  
Iteration 3:   log likelihood = -1193.9265  

Fitting full model

Iteration 0:   log likelihood = -1250.9672  
Iteration 1:   log likelihood = -1139.5853  
Iteration 2:   log likelihood = -1138.8727  
Iteration 3:   log likelihood = -1138.8724  
Iteration 4:   log likelihood = -1138.8724  

Fitting comparison models for LR tests

Iteration 0:   log likelihood = -1251.0143  
Iteration 1:   log likelihood = -1139.7452  
Iteration 2:   log likelihood = -1139.0025  
Iteration 3:   log likelihood = -1139.0022  
Iteration 4:   log likelihood = -1139.0022  

Iteration 0:   log likelihood = -1251.0193  
Iteration 1:   log likelihood = -1139.6247  
Iteration 2:   log likelihood =  -1138.895  
Iteration 3:   log likelihood = -1138.8947  
Iteration 4:   log likelihood = -1138.8947  

Iteration 0:   log likelihood = -1251.0205  
Iteration 1:   log likelihood =  -1139.662  
Iteration 2:   log likelihood = -1138.9803  
Iteration 3:   log likelihood =   -1138.98  
Iteration 4:   log likelihood =   -1138.98  

Iteration 0:   log likelihood = -1260.6813  
Iteration 1:   log likelihood = -1161.3836  
Iteration 2:   log likelihood =  -1160.991  
Iteration 3:   log likelihood = -1160.9909  
Iteration 4:   log likelihood = -1160.9909  

Iteration 0:   log likelihood = -1251.3219  
Iteration 1:   log likelihood = -1140.1492  
Iteration 2:   log likelihood = -1139.4457  
Iteration 3:   log likelihood = -1139.4454  
Iteration 4:   log likelihood = -1139.4454  

Iteration 0:   log likelihood = -1251.1722  
Iteration 1:   log likelihood = -1140.1672  
Iteration 2:   log likelihood = -1139.4447  
Iteration 3:   log likelihood = -1139.4443  
Iteration 4:   log likelihood = -1139.4443  

Iteration 0:   log likelihood = -1253.9474  
Iteration 1:   log likelihood = -1144.8984  
Iteration 2:   log likelihood = -1144.1239  
Iteration 3:   log likelihood = -1144.1235  
Iteration 4:   log likelihood = -1144.1235  

Iteration 0:   log likelihood = -1251.0128  
Iteration 1:   log likelihood = -1139.7619  
Iteration 2:   log likelihood = -1139.0596  
Iteration 3:   log likelihood = -1139.0593  
Iteration 4:   log likelihood = -1139.0593  

Iteration 0:   log likelihood = -1251.0126  
Iteration 1:   log likelihood =  -1139.589  
Iteration 2:   log likelihood = -1138.8994  
Iteration 3:   log likelihood = -1138.8991  
Iteration 4:   log likelihood = -1138.8991  

Iteration 0:   log likelihood = -1254.4156  
Iteration 1:   log likelihood = -1143.1787  
Iteration 2:   log likelihood = -1142.3763  
Iteration 3:   log likelihood = -1142.3759  
Iteration 4:   log likelihood = -1142.3759  

                                                  Number of obs   =        305
                                                  LR chi2(18)     =     110.11
Log likelihood = -1138.8724                       Prob > chi2     =      0.000

------------------------------------------------------------------------------
       price |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
      /theta |  -.2239895   .0896193    -2.50   0.012      -.39964   -.0483389
------------------------------------------------------------------------------

Estimates of scale-variant parameters
-------------------------------------------------------------
             |      Coef.  chi2(df)  P>chi2(df)    df of chi2
-------------+-----------------------------------------------
Notrans      |
          s1 |  -.0235302     0.260    0.610          1
          s2 |  -.0051872     0.045    0.833          1
          dj |   .0143059     0.215    0.643          1
          dl |   .1938586    44.237    0.000          1
         wd1 |   .0563133     1.146    0.284          1
         wd2 |   .0585799     1.144    0.285          1
          bz |   .0935278    10.502    0.001          1
          yj |  -.0090733     0.078    0.780          1
          ls |  -.0283363     1.028    0.311          1
       lable |   -.048456     2.111    0.146          1
          wl |  -.0183611     0.403    0.526          1
          tc |   .0466054     3.493    0.062          1
         yf1 |  -.1577191     6.161    0.013          1
         yf2 |  -.1266088     4.195    0.041          1
         sh1 |   .0644183     1.246    0.264          1
         sh2 |   .0273976     0.374    0.541          1
          pj |   .0033248     0.053    0.817          1
          dz |  -.0117198     7.007    0.008          1
       _cons |   2.267277
-------------+-----------------------------------------------
      /sigma |   .1862849
-------------------------------------------------------------

---------------------------------------------------------
   Test         Restricted     LR statistic      P-value
    H0:       log likelihood       chi2       Prob > chi2
---------------------------------------------------------
theta = -1      -1173.1427        68.54           0.000
theta =  0      -1142.0913         6.44           0.011
theta =  1      -1250.9672       224.19           0.000
---------------------------------------------------------
想了解一下这样做对不对，二分虚拟变量可否放进去转换？还有以下几个问题：
1.我的lamdb等于-0.22是否意味着我可以采用对数形还是非对数形式？解释变量是否需要进行boxcox转换？如何转换，程序如何写？
2.在下一部回归是不是这样写:gen lnp=log（price）
                                                  reg lnp s1  s2 ......即可？