I am writing my master thesis on the effect of implementing GSCM practices on financial performance. I am using a balanced panel data set across 9 year periods with 464 annual observations (i.e. firms). By performing a Hausman test, it shows that using a fixed effect model is more suitable in my case. However, I would like to know how I can examine whether to use a one way (i.e. only including either firm or year) or two way (both time and year)? And if a one-way model would be better, how do I determine to use firm or year in my case?
Besides, is it preferred to use LSDV with xi: regress i.(dummy) or xtreg, fe?
Would help me a lot!
Below my output:
Code:
sort ID year . xtset ID year, yearly panel variable: ID (strongly balanced) time variable: year, 2006 to 2014 delta: 1 year xtreg TobinsQ laggedGSCMP Firmrisk Firmsize Industry, fe note: Industry omitted because of collinearity Fixed-effects (within) regression Number of obs = 3712 Group variable: ID Number of groups = 464 R-sq: within = 0.0050 Obs per group: min = 8 between = 0.0356 avg = 8.0 overall = 0.0247 max = 8 F(3,3245) = 5.49 corr(u_i, Xb) = -0.0538 Prob > F = 0.0009 ------------------------------------------------------------------------------ TobinsQ | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- laggedGSCMP | -.1490492 .108578 -1.37 0.170 -.3619376 .0638393 Firmrisk | -.2108832 .1473064 -1.43 0.152 -.4997062 .0779398 Firmsize | -.1545399 .0489047 -3.16 0.002 -.2504271 -.0586528 Industry | 0 (omitted) _cons | 3.295451 .3674794 8.97 0.000 2.574936 4.015967 -------------+---------------------------------------------------------------- sigma_u | 1.0374074 sigma_e | .83317079 rho | .60789743 (fraction of variance due to u_i) ------------------------------------------------------------------------------ F test that all u_i=0: F(463, 3245) = 12.22 Prob > F = 0.0000 . estimates store fixed . xtreg ROA laggedGSCMP Firmrisk Firmsize Industry, fe note: Industry omitted because of collinearity Fixed-effects (within) regression Number of obs = 3712 Group variable: ID Number of groups = 464 R-sq: within = 0.0266 Obs per group: min = 8 between = 0.1170 avg = 8.0 overall = 0.0679 max = 8 F(3,3245) = 29.56 corr(u_i, Xb) = -0.3840 Prob > F = 0.0000 ------------------------------------------------------------------------------ ROA | Coef. Std. Err. t P>|t| [95% Conf. Interval] -------------+---------------------------------------------------------------- laggedGSCMP | -.0186391 .0138594 -1.34 0.179 -.0458132 .008535 Firmrisk | -.0918953 .0188029 -4.89 0.000 -.1287621 -.0550286 Firmsize | .053131 .0062424 8.51 0.000 .0408915 .0653705 Industry | 0 (omitted) _cons | -.3451898 .0469069 -7.36 0.000 -.4371598 -.2532197 -------------+---------------------------------------------------------------- sigma_u | .10264246 sigma_e | .10634995 rho | .48226573 (fraction of variance due to u_i) ------------------------------------------------------------------------------ F test that all u_i=0: F(463, 3245) = 6.17 Prob > F = 0.0000 . estimates store random . hausman fixed random ---- Coefficients ---- | (b) (B) (b-B) sqrt(diag(V_b-V_B)) | fixed random Difference S.E. -------------+---------------------------------------------------------------- laggedGSCMP | -.1490492 -.0186391 -.1304101 .1076899 Firmrisk | -.2108832 -.0918953 -.1189879 .1461015 Firmsize | -.1545399 .053131 -.2076709 .0485046 ------------------------------------------------------------------------------ b = consistent under Ho and Ha; obtained from xtreg B = inconsistent under Ha, efficient under Ho; obtained from xtreg Test: Ho: difference in coefficients not systematic chi2(3) = (b-B)'[(V_b-V_B)^(-1)](b-B) = 23.12 Prob>chi2 = 0.0000
0 Response to two way or one way fixed effect model
Post a Comment