Scribd
Upload
46 views2 pages

Result (Annual Report)

The document presents the results of two random-effects GLS regressions with ROA as the dependent variable. The first regression includes RD, BC, and BS as independent variables. The second adds BM as a fourth independent variable. Neither model finds all coefficients to be statistically significant, though BS is significant in both and BM is not significant in the second model.

Uploaded by

Ling YN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
46 views2 pages

Result (Annual Report)

The document presents the results of two random-effects GLS regressions with ROA as the dependent variable. The first regression includes RD, BC, and BS as independent variables. The second adds BM as a fourth independent variable. Neither model finds all coefficients to be statistically significant, though BS is significant in both and BM is not significant in the second model.

Uploaded by

Ling YN
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

ROA i,t = α0 + ß1 RD i,t + ß2 BC i,t + ß3 BS i,t + 𝜺 i,t

Random-effects GLS regression Number of obs = 160


Group variable: Companynum Number of groups = 32

R-sq: Obs per group:


within = 0.0088 min = 5
between = 0.1762 avg = 5.0
overall = 0.1013 max = 5

Wald chi2(3) = 7.19


corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0661

ROA Coef. Std. Err. z P>|z| [95% Conf. Interval]

RD -3.869688 3.377054 -1.15 0.252 -10.48859 2.749216


BC .0317641 .0330708 0.96 0.337 -.0330535 .0965817
BS .7431351 .2993277 2.48 0.013 .1564636 1.329807
_cons -2.382368 3.319241 -0.72 0.473 -8.887961 4.123226

sigma_u 2.9124467
sigma_e 3.43871
rho .41770402 (fraction of variance due to u_i)

ROA i,t = ß0 + ß1RD i,t + ß2 BC i,t + ß3 BS i,t + ß4 BM i,t + 𝜺 i,t

Random-effects GLS regression Number of obs = 160


Group variable: Companynum Number of groups = 32

R-sq: Obs per group:


within = 0.0132 min = 5
between = 0.1633 avg = 5.0
overall = 0.0964 max = 5

Wald chi2(4) = 7.19


corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.1260

ROA Coef. Std. Err. z P>|z| [95% Conf. Interval]

RD -3.813602 3.436547 -1.11 0.267 -10.54911 2.921906


BC .0307794 .03373 0.91 0.361 -.0353302 .096889
BS .7132576 .3095407 2.30 0.021 .1065691 1.319946
BM .0884987 .1952949 0.45 0.650 -.2942724 .4712697
_cons -2.592695 3.380612 -0.77 0.443 -9.218572 4.033182

sigma_u 2.9733299
sigma_e 3.4334311
rho .42855354 (fraction of variance due to u_i)
NORMALITY TEST

. regress ROA RD BC BS BM

Source SS df MS Number of obs = 160


F(4, 155) = 4.88
Model 386.832217 4 96.7080543 Prob > F = 0.0010
Residual 3072.94857 155 19.8254747 R-squared = 0.1118
Adj R-squared = 0.0889
Total 3459.78079 159 21.7596276 Root MSE = 4.4526

ROA Coef. Std. Err. t P>|t| [95% Conf. Interval]

RD -3.906532 2.029605 -1.92 0.056 -7.915788 .1027244


BC .0068765 .0228208 0.30 0.764 -.0382035 .0519565
BS .7822591 .2108846 3.71 0.000 .3656805 1.198838
BM -.0339322 .1471792 -0.23 0.818 -.3246681 .2568037
_cons -1.244476 2.256704 -0.55 0.582 -5.70234 3.213389

Serial Correlation Test (Wooldridge Test)

. xtserial ROA RD BC BS BM

Wooldridge test for autocorrelation in panel data


H0: no first-order autocorrelation
F( 1, 31) = 4.745
Prob > F = 0.0371

You might also like