I am using panel data for US companies for the period 2000-2019. My research involves studying the impact of Geographical Diversification (Ln_GSD) on firm performance (Ln_EBIT_ROA). As you can see, I have log-transformed the original variables i,e.
1. The IV Geographic Segmentation (GSD) is log-transformed as Ln_GSD
2. The DV EBIT_ROA is log-transformed as Ln_EBIT_ROA
I have pasted by regression equation and margins command below. I am wondering how I can interpret these margins given that both IV and DV are log-transformed. Any guidance would be greatly apprecaited. Thank you.
Code:
. xtreg Ln_EBIT_ROA Ln_Revenue Ln_LTD_to_Sales Ln_Intangible_Assets CoAge wGDPpc wCPI wDCF wExpg
> r wGDPgr wCons Ln_PS_RD c.l1.Ln_GSD##c.l1.Ln_GSD if CoAge>=0 & NATION=="UNITED STATES" & NATIO
> NCODE==840 & FSTS>=10 & GENERALINDUSTRYCLASSIFICATION ==1 & Year_<2020 & Year_<YearInactive & D
> iscr_GS_Rev!=1, fe cluster(n_CUSIP)
Fixed-effects (within) regression Number of obs = 1,094
Group variable: n_CUSIP Number of groups = 217
R-sq: Obs per group:
within = 0.1070 min = 1
between = 0.0010 avg = 5.0
overall = 0.0001 max = 19
F(11,216) = .
corr(u_i, Xb) = -0.9029 Prob > F = .
(Std. Err. adjusted for 217 clusters in n_CUSIP)
--------------------------------------------------------------------------------------
| Robust
Ln_EBIT_ROA | Coef. Std. Err. t P>|t| [95% Conf. Interval]
---------------------+----------------------------------------------------------------
Ln_Revenue | .5763141 .1411842 4.08 0.000 .298039 .8545892
Ln_LTD_to_Sales | -.0995823 .0380325 -2.62 0.009 -.1745447 -.0246199
Ln_Intangible_Assets | -.1271354 .0583075 -2.18 0.030 -.24206 -.0122108
CoAge | -.0258257 .0132921 -1.94 0.053 -.0520246 .0003732
wGDPpc | .0000464 .0000236 1.97 0.050 -8.48e-09 .0000928
wCPI | 4.31e-06 .0232319 0.00 1.000 -.045786 .0457947
wDCF | 1.23e-13 1.25e-13 0.99 0.323 -1.22e-13 3.69e-13
wExpgr | .0004585 .0102761 0.04 0.964 -.0197959 .0207128
wGDPgr | .0224036 .0310686 0.72 0.472 -.0388328 .08364
wCons | -1.44e-14 4.34e-14 -0.33 0.740 -1.00e-13 7.11e-14
Ln_PS_RD | -.0364973 .048478 -0.75 0.452 -.1320477 .0590531
|
Ln_GSD |
L1. | -.6849239 .2057833 -3.33 0.001 -1.090524 -.2793234
|
cL.Ln_GSD#cL.Ln_GSD | -.0891373 .0413972 -2.15 0.032 -.1707315 -.007543
|
_cons | -12.39407 2.418484 -5.12 0.000 -17.16092 -7.62722
---------------------+----------------------------------------------------------------
sigma_u | 1.4895855
sigma_e | .59440144
rho | .86264051 (fraction of variance due to u_i)
--------------------------------------------------------------------------------------
. margins, at(l1.Ln_GSD=(-4.839976 (1).2830217))
Predictive margins Number of obs = 1,094
Model VCE : Robust
Expression : Linear prediction, predict()
1._at : L.Ln_GSD = -4.839976
2._at : L.Ln_GSD = -3.839976
3._at : L.Ln_GSD = -2.839976
4._at : L.Ln_GSD = -1.839976
5._at : L.Ln_GSD = -.839976
6._at : L.Ln_GSD = .160024
------------------------------------------------------------------------------
| Delta-method
| Margin Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_at |
1 | -1.546592 .5436151 -2.85 0.004 -2.612058 -.4811256
2 | -1.457808 .3933611 -3.71 0.000 -2.228782 -.6868347
3 | -1.547299 .2963378 -5.22 0.000 -2.128111 -.9664879
4 | -1.815065 .20548 -8.83 0.000 -2.217798 -1.412332
5 | -2.261105 .0808414 -27.97 0.000 -2.419551 -2.102659
6 | -2.88542 .1023237 -28.20 0.000 -3.085971 -2.684869
------------------------------------------------------------------------------
0 Response to Interpreting margins command for log transformed IV and DV
Post a Comment