Different hazard ratio and coefficient in Cox Regression

[Anuradha Saikia]

Hello everyone. I am working on Cox regression using a panel dataset. My observation is 4029 with 255 firms. The failure variable is firm exit taking value 1 . Total no of firms that have exited are 20. The main independent variable is corruption.
My coefficient sign is coming negative for corruption and the hazard ratio is positive. Kindly help me with the same.

 stcox Informality_scaled RD ID AGE ROA Leverage1 Par_Size1 GDPPERCAPITA SIZE HHI, efron vce(robust) nohr

         failure _d:  Failure
   analysis time _t:  Time

Iteration 0:   log pseudolikelihood = -140.80912
Iteration 1:   log pseudolikelihood = -126.07835
Iteration 2:   log pseudolikelihood = -124.21411
Iteration 3:   log pseudolikelihood = -123.46315
Iteration 4:   log pseudolikelihood = -123.14804
Iteration 5:   log pseudolikelihood = -123.09893
Iteration 6:   log pseudolikelihood =  -123.0982
Iteration 7:   log pseudolikelihood =  -123.0982
Refining estimates:
Iteration 0:   log pseudolikelihood =  -123.0982

Cox regression -- Efron method for ties

No. of subjects      =        4,023             Number of obs    =       4,023
No. of failures      =           20
Time at risk         =        99038
                                                Wald chi2(10)    =       63.12
Log pseudolikelihood =    -123.0982             Prob > chi2      =      0.0000

------------------------------------------------------------------------------------
                   |               Robust
                _t |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------------+----------------------------------------------------------------
Informality_scaled |  -.0008861   .0003976    -2.23   0.026    -.0016653   -.0001068
                RD |  -.0912838   .0304677    -3.00   0.003    -.1509995   -.0315682
                ID |  -.6918332   .7620768    -0.91   0.364    -2.185476    .8018099
               AGE |   -.053758   .0448858    -1.20   0.231    -.1417326    .0342166
               ROA |  -.0001181   .0000405    -2.92   0.004    -.0001974   -.0000388
         Leverage1 |   .0402488   .0567644     0.71   0.478    -.0710075     .151505
         Par_Size1 |   .4118916   .3573877     1.15   0.249    -.2885754    1.112359
      GDPPERCAPITA |   .0034515    .000809     4.27   0.000     .0018659     .005037
              SIZE |  -.1731879   .0644932    -2.69   0.007    -.2995922   -.0467836
               HHI |   .2210428   .4264988     0.52   0.604    -.6148795    1.056965
------------------------------------------------------------------------------------

. stcox Informality_scaled RD ID AGE ROA Leverage1 Par_Size1 GDPPERCAPITA SIZE HHI, efron vce(robust)

         failure _d:  Failure
   analysis time _t:  Time

Iteration 0:   log pseudolikelihood = -140.80912
Iteration 1:   log pseudolikelihood = -126.07835
Iteration 2:   log pseudolikelihood = -124.21411
Iteration 3:   log pseudolikelihood = -123.46315
Iteration 4:   log pseudolikelihood = -123.14804
Iteration 5:   log pseudolikelihood = -123.09893
Iteration 6:   log pseudolikelihood =  -123.0982
Iteration 7:   log pseudolikelihood =  -123.0982
Refining estimates:
Iteration 0:   log pseudolikelihood =  -123.0982

Cox regression -- Efron method for ties

No. of subjects      =        4,023             Number of obs    =       4,023
No. of failures      =           20
Time at risk         =        99038
                                                Wald chi2(10)    =       63.12
Log pseudolikelihood =    -123.0982             Prob > chi2      =      0.0000

------------------------------------------------------------------------------------
                   |               Robust
                _t | Haz. Ratio   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------------+----------------------------------------------------------------
Informality_scaled |   .9991143   .0003972    -2.23   0.026     .9983361    .9998932
                RD |   .9127586   .0278097    -3.00   0.003     .8598481    .9689249
                ID |   .5006574   .3815394    -0.91   0.364     .1124242    2.229573
               AGE |   .9476614   .0425366    -1.20   0.231     .8678533    1.034809
               ROA |   .9998819   .0000405    -2.92   0.004     .9998026    .9999612
         Leverage1 |    1.04107   .0590957     0.71   0.478     .9314549    1.163584
         Par_Size1 |   1.509671   .5395378     1.15   0.249     .7493303    3.041524
      GDPPERCAPITA |   1.003457   .0008117     4.27   0.000     1.001868     1.00505
              SIZE |   .8409796   .0542374    -2.69   0.007     .7411204    .9542939
               HHI |   1.247377   .5320047     0.52   0.604      .540706    2.877624
------------------------------------------------------------------------------------

Why is the sign of the hazard ratio and coefficient different?

[Maarten Buis]

A ratio implies a multiplication rather than an addition. If you multiply something with a number less than 1, than it decreases. If you multiply something with a number larger than one than it increases. So a "negative" ratio is a ratio less than 1 not less than 0.