Maximum likelihhod estimator sspace showing the result of Probability, z statistic, and standard error as NA

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

sundar749
Posts: 1
Joined: Wed Apr 10, 2024 2:37 pm

Maximum likelihhod estimator sspace showing the result of Probability, z statistic, and standard error as NA

Postby sundar749 » Tue Apr 16, 2024 2:31 pm

In the below code C(1) refers to mean of the real interest rate c(2) refers to Auto correlation obtained from correlogram C(3) and c(4) refer to SD/2.
I am using a real interest rate as a single latent variable to find natural rate. Whatever the data, either monthly, quarterly or early I get exactly the same result which is NA. Please guide me how to fix such problem.



@signal real_interest_rate=c(1)+s+[var=c(3)^2]
@state s=c(2)*s(-1)+[var=c(4)^2]
@param c(1)0.010207 c(2)0.849 c(3)0.019285 c(4)0.019285


Sspace: UNTITLED
Method: Maximum likelihood (BFGS / Marquardt steps)
Date: 04/16/24 Time: 16:05
Sample: 1977 2022
Included observations: 46
Convergence achieved after 29 iterations
Coefficient covariance computed using outer product of gradients
WARNING: Singular covariance - coefficients are not unique

Coefficient Std. Error z-Statistic Prob.

C(1) 0.010080 NA NA NA
C(2) 0.296205 NA NA NA
C(3) 2.80E-13 NA NA NA
C(4) 0.032614 NA N A NA

Final State Root MSE z-Statistic Prob.

S -0.004415 0.032614 -0.135367 0.8923

Log likelihood 92.14142 Akaike info criterion -3.832236
Parameters 4 Schwarz criterion -3.673223
Diffuse priors 0 Hannan-Quinn criter. -3.772669



Return to “Estimation”

Who is online

Users browsing this forum: Google [Bot] and 2 guests