Answer

a.

genr:

lnoutput= log(output) dependent variable= total production, output

Independent be those input, to produce the product
lncapital= log(capital)

lnlabor= log(labor)

ln(Output) = 0 + 1ln(labor) + 2ln(capital) +

b. Genr all variables > Select lnoutput first, then lnlabor & lncapital > Open Equation >
Rearrange to (lnoutput c lnlabor lncapital)
Dependent Variable: INOUTPUT
Method: Least Squares
Date: 07/13/17 Time: 14:24
Sample: 1989 2012
Included observations: 24

Variable Coefficient Std. Error t-Statistic Prob.

C (C1) -0.177310 0.434293 -0.408272 0.6872

INLABOR (C2) 0.807278 0.145076 5.564513 0.0000
INCAPITAL (C3) 0.233053 0.063530 3.668415 0.0014

R-squared 0.957425 Mean dependent var 5.077336

Adjusted R-squared 0.953370 S.D. dependent var 0.269234
S.E. of regression 0.058138 Akaike info criterion -2.735511
Sum squared resid 0.070982 Schwarz criterion -2.588254
Log likelihood 35.82613 Hannan-Quinn criter. -2.696444
F-statistic 236.1219 Durbin-Watson stat 1.523452
Prob(F-statistic) 0.000000

Inoutput = -0.1773 + 0.8072 Inlabor + 0.2331 Incapital +

(b)

H0 : 1 = 0
H1 : 1 0 (no need to report in your lab test, this is the notes for you)

Prob. for lnlabor = 0.0000 (notes : if P-value < 0.10, statistically significant, reject H0).
Since p-value for lnlabor is < 0.10, lnlabor is statistically significant at 10% significant level.
Reject H0. Therefore, 1 0.

H0 : 2 = 0
H1 : 2 0

Prob. for lncapital = 0.0014 (notes : if P-value < 0.10, statistically significant, reject H0).
Since p-value for lncapital is < 0.10, lncapital is statistically significant at 10% significant
level. Reject H0. Therefore, 2 0.

(c)

H0 : 1 = 2 = 0
H1 : at least one i 0

Prob. (F-statistic) = 0.0000 (notes : if P-value < 0.10, statistically significant, reject H0).
Since p-value for F-statistic is < 0.10, it is statistically significant at 1% significant level,
reject H0. Therefore, Bi 0.

(d) Capital have effect on output or not* (if =0, no effect, if not equal 0, have effect)

H0 : 2 = 0
H1 : 2 0

Prob. for Incapital = 0.0014 (notes : if P-value < 0.05, reject H0; if P-value statistically
significant, reject H0). Since p-value for lncapital is < 0.05, lncapital is statistically significant
at 5% significant level. Reject H0. Therefore, 2 0.

* 2 0, so have effect.
(e) Select Inoutput first then Inlabor and Incapital > Open Equation > inoutput c inlabor
incapital > View > Coefficient Diagnostics > Wald Test- Coefficient Restriction >
C(2)+C(3)=0
Wald Test:
Equation: Untitled

Test Statistic Value df Probability

t-statistic 11.40753 21 0.0000

F-statistic 130.1317 (1, 21) 0.0000
Chi-square 130.1317 1 0.0000

Null Hypothesis: C(2)+C(3)=0

Null Hypothesis Summary:

Normalized Restriction (= 0) Value Std. Err.

C(2) + C(3) 1.040332 0.091197

Restrictions are linear in coefficients.

H0 : 1 + 2 = 0
H1 : 1 + 2 0

Prob = 0.0000 (notes : if P-value < 0.01, reject H0; if P-value > 0.01, do not reject H0)

Since p-value (0.0000) < 0.01, it is statistically significant at 1% significance level, reject H0.
Therefore, 1 + 2 0

(f)

Adjusted R-squared = 0.9534

95.34% estimated regression line fits the data

95.34% of all variables x (Inlabor and Incapital) explain y (lnoutput).