I have a two year panel with fully fleshed out dummies. The dummies indicate, for each individual, their transition between any of 4 plan types, or if they stayed in one plan type.
I expect stata to recognize one as being collinear and therefore to omit it from computations. Despite this, stata seems to estimate a coefficient for each dummy. Here is my estimation and related descriptive stats: The estimated constant is the value of the dependent variable for the first year in the data.
xtreg drgscr xt*, fe
Fixed-effects (within) regression Number of obs = 2,514,702
Group variable: enrolid Number of groups = 1,257,351
R-sq: Obs per group:
within = 0.0016 min = 2
between = 0.0001 avg = 2.0
overall = 0.0003 max = 2
F(16,1257335) = 127.35
corr(u_i, Xb) = -0.0017 Prob > F = 0.0000
------------------------------------------------------------------------------
drgscr | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
xt_trn24 | -.0072333 .0087649 -0.83 0.409 -.0244123 .0099457
xt_trn26 | -.0197679 .0020753 -9.53 0.000 -.0238353 -.0157004
xt_trn28 | -.0408163 .0416417 -0.98 0.327 -.1224327 .0408001
xt_trn42 | -.0110701 .0125207 -0.88 0.377 -.0356102 .01347
xt_trn46 | .0004178 .0026645 0.16 0.875 -.0048046 .0056401
xt_trn48 | -.0045156 .0059059 -0.76 0.445 -.016091 .0070598
xt_trn62 | .0129304 .0034007 3.80 0.000 .0062651 .0195958
xt_trn64 | -.1327324 .0030942 -42.90 0.000 -.1387968 -.1266679
xt_trn68 | -.0007097 .0038828 -0.18 0.855 -.0083198 .0069004
xt_trn82 | 0 .1190012 0.00 1.000 -.2332383 .2332383
xt_trn84 | -.0512821 .033005 -1.55 0.120 -.1159707 .0134066
xt_trn86 | -.0058824 .0223564 -0.26 0.792 -.0497002 .0379355
xt_stay2 | .0005267 .0007013 0.75 0.453 -.0008478 .0019012
xt_stay4 | .0019664 .0004547 4.32 0.000 .0010752 .0028577
xt_stay6 | .0030591 .0003726 8.21 0.000 .0023287 .0037894
xt_stay8 | .0002641 .0047367 0.06 0.956 -.0090198 .0095479
_cons | .7086693 .0001838 3855.32 0.000 .708309 .7090295
-------------+----------------------------------------------------------------
sigma_u | .4300561
sigma_e | .20611611
rho | .81320204 (fraction of variance due to u_i)
------------------------------------------------------------------------------
F test that all u_i=0: F(1257350, 1257335) = 8.68 Prob > F = 0.0000
. sum xt_trn* xt_stay* if year==2005
Variable | Obs Mean Std. Dev. Min Max
-------------+---------------------------------------------------------
xt_trn24 | 1,257,351 0 0 0 0
xt_trn26 | 1,257,351 0 0 0 0
xt_trn28 | 1,257,351 0 0 0 0
xt_trn42 | 1,257,351 0 0 0 0
xt_trn46 | 1,257,351 0 0 0 0
-------------+---------------------------------------------------------
xt_trn48 | 1,257,351 0 0 0 0
xt_trn62 | 1,257,351 0 0 0 0
xt_trn64 | 1,257,351 0 0 0 0
xt_trn68 | 1,257,351 0 0 0 0
xt_trn82 | 1,257,351 0 0 0 0
-------------+---------------------------------------------------------
xt_trn84 | 1,257,351 0 0 0 0
xt_trn86 | 1,257,351 0 0 0 0
xt_stay2 | 1,257,351 0 0 0 0
xt_stay4 | 1,257,351 0 0 0 0
xt_stay6 | 1,257,351 0 0 0 0
-------------+---------------------------------------------------------
xt_stay8 | 1,257,351 0 0 0 0
. sum xt_trn* xt_stay* if year==2006
Variable | Obs Mean Std. Dev. Min Max
-------------+---------------------------------------------------------
xt_trn24 | 1,257,351 .0008796 .0296455 0 1
xt_trn26 | 1,257,351 .0156909 .1242768 0 1
xt_trn28 | 1,257,351 .000039 .0062425 0 1
xt_trn42 | 1,257,351 .0004311 .0207576 0 1
xt_trn46 | 1,257,351 .0095184 .097097 0 1
-------------+---------------------------------------------------------
xt_trn48 | 1,257,351 .0019374 .0439733 0 1
xt_trn62 | 1,257,351 .0058432 .0762174 0 1
xt_trn64 | 1,257,351 .0070585 .0837178 0 1
xt_trn68 | 1,257,351 .0044824 .0668008 0 1
xt_trn82 | 1,257,351 4.77e-06 .0021845 0 1
-------------+---------------------------------------------------------
xt_trn84 | 1,257,351 .000062 .007876 0 1
xt_trn86 | 1,257,351 .0001352 .011627 0 1
xt_stay2 | 1,257,351 .1374111 .344281 0 1
xt_stay4 | 1,257,351 .3267942 .4690415 0 1
xt_stay6 | 1,257,351 .4867002 .4998233 0 1
-------------+---------------------------------------------------------
xt_stay8 | 1,257,351 .0030119 .054798 0 1
Related Posts with xtreg fe and collinear dummies
looping across multiple variablesHi, I have a dataset that includes several observations for one id and i need to create a sequencin…
SEM Mediation Models: How to calculate CIs for R^2?Greetings, I'm running Stata 15.1 on a Mac OS. I'm trying to determine whether a model with mediato…
Testing heteroskedasticity and autocorrelation in xtlogit without time variableHello all, I have an unbalanced panel data set. For this, STATA (14.2) wants me to define a panel I…
-oaxaca- using normalize option for categorical predictor variablesHi! I know that results from regular -oaxaca- depend on the omitted base category for categorical va…
how to cite the tempfile?I want to append all the tempfile, here is my code, however, there is somthing wrong, how to solve t…
Subscribe to:
Post Comments (Atom)
0 Response to xtreg fe and collinear dummies
Post a Comment