Question No 1

Fit the “pooled” model using health outcome (COMP) as a dependent variable and
education (EDUC), health expenditure (HLTHEXP) as independent variables.

Question No 2
Report your results.
No you see that the f value is 701.19 and it is significant and the R-square value is 0.6680 and it
is fit model. On the other table you see that if education level increase the health outcome
increase and it is according to theory the value is 2.449954 and it is significant. On the other
hand if health expenditure increase the health outcome decease and it is against the theory
-0071716 but it is significant.

Question No 2
Using the Panel data analysis approach, determine which model, fixed or random effects is
preferred.
Fixed Effect:
. xtreg comp educ hlthexp, fe

Fixed-effects (within) regression Number of obs = 700

Group variable: id Number of groups = 140

R-sq: within = 0.0193 Obs per group: min = 5

between = 0.6927 avg = 5.0
overall = 0.6518 max = 5

F(2,558) = 5.50
corr(u_i, Xb) = 0.1452 Prob > F = 0.0043

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

educ 2.693282 1.157575 2.33 0.020 .4195439 4.96702

hlthexp .0037855 .0026195 1.45 0.149 -.0013598 .0089308
_cons 56.06792 6.723484 8.34 0.000 42.86149 69.27435

sigma_u 6.7413141
sigma_e 3.3804231
rho .79907258 (fraction of variance due to u_i)

F test that all u_i=0: F(139, 558) = 18.37 Prob > F = 0.0000

In this total observation is 700 and the value is 0.0042.

Random effect:
. xtreg comp educ hlthexp, re

Random-effects GLS regression Number of obs = 700

Group variable: id Number of groups = 140

R-sq: within = 0.0184 Obs per group: min = 5

between = 0.7098 avg = 5.0
overall = 0.6677 max = 5

Wald chi2(2) = 345.35

corr(u_i, X) = 0 (assumed) Prob > chi2 = 0.0000

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

educ 2.505574 .2409721 10.40 0.000 2.033277 2.977871

hlthexp .00671 .0009916 6.77 0.000 .0047664 .0086536
_cons 55.80166 1.372749 40.65 0.000 53.11112 58.4922

sigma_u 6.3470199
sigma_e 3.3804231
rho .77902078 (fraction of variance due to u_i)

You see that wald test 345.35 and it is significant and the value is 0.0000.

Hausman Test:
. hausman fixed .

Coefficients
(b) (B) (b-B) sqrt(diag(V_b-V_B))
fixed random Difference S.E.

educ 2.693282 2.505574 .1877079 1.132216

hlthexp .0037855 .00671 -.0029245 .0024246

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(2) = (b-B)'[(V_b-V_B)^(-1)](b-B)
= 1.51
Prob>chi2 = 0.4700

Now you see that p value is 0.47 and it is greater than .05 and it is significant due to which we
accept fixed test due to random effect result is good.

Question No 14
Analyze these data using EFA and varimax rotation procedure.

Descriptive Statistics

Mean Std. Deviation Analysis N

v1 4.3200 1.86458 25
v2 4.0400 1.85921 25
v3 3.9600 1.79072 25
v4 3.9200 1.80093 25
v5 3.8400 1.92959 25
v6 4.1600 1.84120 25
v7 4.2000 1.89297 25

Now you see that the S.D value must be 1 that means respondent answer the question without
biasness. If S.D is zero that remove that question.
 Correlation Matrixa

v1 v2 v3 v4 v5 v6 v7

v1 1.000 -.004 .628 .082 .675 -.100 -.338

v2 -.004 1.000 .151 -.248 .048 .582 -.251

v3 .628 .151 1.000 -.182 .480 .090 -.588

Correlation v4 .082 -.248 -.182 1.000 .272 .017 .469

v5 .675 .048 .480 .272 1.000 -.110 -.082

v6 -.100 .582 .090 .017 -.110 1.000 .014

v7 -.338 -.251 -.588 .469 -.082 .014 1.000

a. Determinant = .062

KMO and Bartlett's Test

Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .550

Approx. Chi-Square 57.994

Bartlett's Test of Sphericity df 21

Sig. .000

Anti-image Matrices

v1 v2 v3 v4 v5 v6 v7

v1 .404 .044 -.124 -.037 -.202 .014 .071

v2 .044 .514 .078 .155 -.139 -.340 .126

v3 -.124 .078 .378 .077 -.126 -.135 .204

Anti-image Covariance v4 -.037 .155 .077 .618 -.156 -.137 -.154

v5 -.202 -.139 -.126 -.156 .412 .136 -.109

v6 .014 -.340 -.135 -.137 .136 .536 -.114

v7 .071 .126 .204 -.154 -.109 -.114 .463

a
v1 .716 .097 -.318 -.075 -.495 .029 .165

v2 .097 .414a .176 .274 -.301 -.648 .259

v3 -.318 .176 .638a .159 -.319 -.299 .489

Anti-image Correlation v4 -.075 .274 .159 .537a -.308 -.238 -.288

v5 -.495 -.301 -.319 -.308 .535a .290 -.249

v6 .029 -.648 -.299 -.238 .290 .345a -.229

v7 .165 .259 .489 -.288 -.249 -.229 .586a

a. Measures of Sampling Adequacy(MSA)

Total Variance Explained

Component Initial Eigenvalues Extraction Sums of Squared Rotation Sums of Squared

Loadings Loadings

Total % of Cumulative Total % of Cumulative Total % of Cumulative

Variance % Variance % Variance %

1 2.485 35.505 35.505 2.485 35.505 35.505 2.315 33.076 33.076

2 1.821 26.013 61.518 1.821 26.013 61.518 1.731 24.729 57.805
3 1.339 19.131 80.649 1.339 19.131 80.649 1.599 22.844 80.649
4 .508 7.258 87.907
5 .376 5.373 93.280
6 .279 3.990 97.270
7 .191 2.730 100.000

Extraction Method: Principal Component Analysis.

 Rotated Component Matrixa

Component

1 2 3

v1 .897
v5 .868
v3 .762 -.440
v4 .867
v7 -.351 .817
v6 .911
v2 .860
Extraction Method: Principal Component
Analysis.
Rotation Method: Varimax with Kaiser
Normalization.
a. Rotation converged in 4 iterations.