Scribd Logo
Upload

Welcome to Scribd!

  • 57 views

    The SYSLIN Procedure Two-Stage Least Squares Estimation

    Uploaded by

    Candy Suaybaguio
    - The document discusses using SAS to analyze a dataset on import levels using two-stage least squares and full information maximum likelihood estimation. - It provides output on model fitting including parameter estimates, standard errors, fit indices, and equations for the two models. - The best fitting model was the full information maximum likelihood model with a non-significant likelihood ratio chi-square test indicating good model fit.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as RTF, PDF, TXT or read online from Scribd

    The SYSLIN Procedure Two-Stage Least Squares Estimation

    Uploaded by

    Candy Suaybaguio
    57 views13 pages
    - The document discusses using SAS to analyze a dataset on import levels using two-stage least squares and full information maximum likelihood estimation. - It provides output on model fitting including parameter estimates, standard errors, fit indices, and equations for the two models. - The best fitting model was the full information maximum likelihood model with a non-significant likelihood ratio chi-square test indicating good model fit.

    Original Title

    USA Output 2

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    RTF, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    - The document discusses using SAS to analyze a dataset on import levels using two-stage least squares and full information maximum likelihood estimation. - It provides output on model fitting including parameter estimates, standard errors, fit indices, and equations for the two models. - The best fitting model was the full information maximum likelihood model with a non-significant likelihood ratio chi-square test indicating good model fit.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as RTF, PDF, TXT or read online from Scribd
    Download as rtf, pdf, or txt
    57 views13 pages

    The SYSLIN Procedure Two-Stage Least Squares Estimation

    Uploaded by

    Candy Suaybaguio
    - The document discusses using SAS to analyze a dataset on import levels using two-stage least squares and full information maximum likelihood estimation. - It provides output on model fitting including parameter estimates, standard errors, fit indices, and equations for the two models. - The best fitting model was the full information maximum likelihood model with a non-significant likelihood ratio chi-square test indicating good model fit.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as RTF, PDF, TXT or read online from Scribd
    Download as rtf, pdf, or txt
    You are on page 1of 13

    The SAS System Two-Stage Least Squares

    The SYSLIN Procedure Two-Stage Least Squares Estimation


    Model Dependent Variable Label
    logimport logimport Logarithm of Import

    Analysis of Variance Source Model Error Corrected Total Sum of DF Squares


    3 17 20

    Mean Square F Value Pr > F


    18.74 <.0001

    1.239224 0.413075 0.374701 0.022041 1.506187

    Root MSE Dependent Mean Coeff Var

    0.14846 R-Square 12.36868 Adj R-Sq 1.20031

    0.76783 0.72686

    Parameter Estimates Variable Intercept logprice_pjc logpop inf DF


    1 1 1 1

    Parameter Standard Variable Estimate Error t Value Pr > |t| Label


    12.13109 -0.56786 0.662118 0.035086 0.088486 0.277094 0.407303 0.033417 137.10 -2.05 1.63 1.05 <.0001 Intercept 0.0562 Logarithm of PJC Price 0.1224 Logarithm of Population 0.3084 Inflation

    The SAS System Full Information Maximum Likelihood


    The SYSLIN Procedure Full-Information Maximum Likelihood Estimation
    NOTE: Convergence criterion met at iteration 0.

    Model Dependent Variable Label

    IMPORT logimport Logarithm of Import

    Parameter Estimates Variable Intercept logprice_pjc logpop inf DF


    1 1 1 1

    Parameter Standard Variable Estimate Error t Value Pr > |t| Label


    12.13109 -0.56786 0.662118 0.035086 0.079614 0.249312 0.366465 0.030066 152.37 -2.28 1.81 1.17 <.0001 Intercept 0.0359 Logarithm of PJC Price 0.0885 Logarithm of Population 0.2593 Inflation

    Model Dependent Variable Label

    PRICE logprice_pjc Logarithm of PJC Price

    Parameter Estimates Variable Intercept logpop inf logexported_top10_pjc DF


    1 1 1 1

    Parameter Standard Variable Estimate Error t Value Pr > |t| Label


    -3.91261 0.307802 -0.03355 0.355189 0.889770 0.390974 0.025657 0.080154 -4.40 0.79 -1.31 4.43 0.0004 Intercept 0.4420 Logarithm of Population 0.2084 Inflation 0.0004 Exported Top10 PJC

    The SAS System Least Squares Estimation


    The REG Procedure Model: MODEL1 Dependent Variable: logimport Logarithm of Import
    Number of Observations Read Number of Observations Used
    21 21

    Analysis of Variance Source Model Error Corrected Total Sum of Mean DF Squares Square F Value Pr > F
    3 17 20 1.18726 0.31893 1.50619 0.39575 0.01876 21.10 <.0001

    Root MSE Dependent Mean Coeff Var

    0.13697 R-Square 12.36868 Adj R-Sq 1.10738

    0.7883 0.7509

    Parameter Estimates Variable Intercept Label


    Intercept

    DF
    1 1 1 1

    Parameter Standard Estimate Error t Value Pr > |t|


    12.12578 -0.26145 1.03358 0.04761 0.08157 0.17771 0.30260 0.02990 148.65 -1.47 3.42 1.59 <.0001 0.1595 0.0033 0.1297

    logprice_pjc Logarithm of PJC Price logpop inf


    Logarithm of Population Inflation

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Model and Initial Values
    Modeling Information Data Set N Records Read N Complete Records
    WORK.PJCDEMAND 21 21

    N Incomplete Records 0 N Complete Obs N Incomplete Obs Model Type Analysis


    21 0 LINEQS Means and Covariances

    Variables in the Model Endogenous Manifest Latent Exogenous Manifest Latent Error
    E1 E2 inf logexported_top10_pjc logpop logimport logprice_pjc

    Number of Endogenous Variables = 2 Number of Exogenous Variables = 5

    Initial Estimates for Linear Equations


    logimport = . * Intercept + . * logprice_pjc betanull logprice_pjc = alphanull betalogprice_pjc alphalogpop . * Intercept + . * logpop + . * logpop betalogpop + . * inf alphainf + . * inf betainf + . * logexported_top10_pjc + 1.0000 alphatop10 E2 + 1.0000 E1

    Initial Estimates for Variances of Exogenous Variables Variable Type Error Variable E1 E2 Observed logpop Parameter
    eps1 eps2 _Add1

    Estimate
    . . .

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Model and Initial Values
    inf
    _Add2 . .

    logexported_top10_pjc _Add3 NOTE: Parameters with prefix '_Add' are added by PROC CALIS.

    Initial Estimates for Covariances Among Exogenous Variables Var1 E1 inf Var2 E2 Parameter
    eps3

    Estimate
    . . . .

    logpop _Add4

    logexported_top10_pjc logpop _Add5 logexported_top10_pjc inf


    _Add6

    NOTE: Parameters with prefix '_Add' are added by PROC CALIS.

    Initial Estimates for Mean Parameters Variable Type Variable Parameter


    _Add7 _Add8

    Estimate
    . . .

    Observed logpop inf

    logexported_top10_pjc _Add9 NOTE: Parameters with prefix '_Add' are added by PROC CALIS.

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Descriptive Statistics
    Simple Statistics Variable inf logimport logpop
    Inflation Logarithm of Import Logarithm of Population

    Mean Std Dev


    2.74457 12.36868 0.06473 10.73071 -0.17334 1.10175 0.26781 0.15038 0.73035 0.26337

    logexported_top10_pjc Exported Top10 PJC logprice_pjc


    Logarithm of PJC Price

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Optimization
    Initial Estimation Methods
    1 2 3 Observed Moments of Variables McDonald Method Two-Stage Least Squares

    Optimization Start Parameter Estimates N Parameter 1 betanull 2 betalogprice_pjc 3 betalogpop 4 betainf 5 alphanull 6 alphalogpop 7 alphainf 8 alphatop10 9 eps1 10 eps2 11 _Add1 12 _Add2 13 _Add3 14 eps3 15 _Add4 16 _Add5 17 _Add6 18 _Add7 19 _Add8 20 _Add9 Estimate Gradient Lower Bound Upper Bound
    . . . . . . . . 0 0 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

    12.13109 1.2051E-15 -0.56786 2.4971E-16 0.66212 1.054E-16

    0.03509 3.2526E-15 -3.91261 0.30780 -0.03355 0.35519 0.01784 0.01462 0.02261 1.21386 0.53341 0.00867 -4.248E-14 -3.716E-15 -1.147E-13 -4.585E-13 -1.44E-14 -8.866E-16 -2.31E-28 -1.561E-31 -5.352E-30 -5.842E-14

    0.05862 4.0337E-30 -0.09799 -8.244E-29

    -0.27589 1.1209E-30 0.06473 -7.154E-29

    2.74457 9.2811E-31 10.73071 -1.226E-29

    Value of Objective Function = 0

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Optimization Levenberg-Marquardt Optimization Scaling Update of More (1978)
    Parameter Estimates Functions (Observations) Lower Bounds Upper Bounds Optimization Start Active Constraints Max Abs Gradient Element
    0 Objective Function 4.584738E-13 Radius 0 1 20 20 2 0

    Optimization Results Iterations Jacobian Calls Objective Function Lambda Radius


    0 Function Calls 1 Active Constraints 0 Max Abs Gradient Element 0 Actual Over Pred Change 1 Convergence criterion (ABSGCONV=0.00001) satisfied. 4 0 4.584738E-13 0

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Full Information Maximum Likelihood Estimation
    Fit Summary Modeling Info N Complete Observations N Incomplete Observations N Variables N Moments N Parameters N Active Constraints Saturated Model Estimation Saturated Model Function Value Saturated Model -2 Log-Likelihood Baseline Model Estimation Baseline Model Function Value Baseline Model -2 Log-Likelihood Baseline Model Chi-Square Baseline Model Chi-Square DF Pr > Baseline Model Chi-Square Absolute Index Fit Function -2 Log-Likelihood Chi-Square Chi-Square DF Pr > Chi-Square Z-Test of Wilson & Hilferty Hoelter Critical N Root Mean Square Residual (RMSR) Standardized RMSR (SRMSR) Goodness of Fit Index (GFI) Parsimony Index Adjusted GFI (AGFI) Parsimonious GFI RMSEA Estimate Probability of Close Fit
    21 0 5 20 20 0 FIML 0.0000 0.0000 Converged 4.6622 97.9054 97.9054 10 <.0001 0.0000 0.0000 0.0000 0 . . . 0.0000 0.0000 1.0000 . 0.0000 . .

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Full Information Maximum Likelihood Estimation
    Akaike Information Criterion Bozdogan CAIC Schwarz Bayesian Criterion McDonald Centrality Incremental Index Bentler Comparative Fit Index Bentler-Bonett NFI Bentler-Bonett Non-normed Index Bollen Normed Index Rho1 Bollen Non-normed Index Delta2 James et al. Parsimonious NFI
    40.0000 80.8904 60.8904 1.0000 1.0000 1.0000 . . 1.0000 0.0000

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Full Information Maximum Likelihood Estimation
    Linear Equations
    logimport Std Err t Value logprice_pjc = Std Err t Value = 12.1311 * Intercept + -0.5679 * logprice_pjc 0.0796 152.4 0.8898 -4.3973 + 0.0351 * inf 0.0301 1.1670 + 0.3552 * logexported_top10_pjc + 1.0000 0.0802 4.4313 alphatop10 E2 betainf alphanull betanull 0.2493 -2.2777 0.3910 0.7873 + 1.0000 alphalogpop betalogprice_pjc + 0.6621 * logpop 0.3665 1.8068 + -0.0336 * inf 0.0257 -1.3078 E1 alphainf betalogpop

    -3.9126 * Intercept + 0.3078 * logpop

    Estimates for Variances of Exogenous Variables Variable Type Error Variable E1 E2 Observed logpop inf Parameter Estimate
    eps1 eps2 _Add1 _Add2 0.01784 0.01462 0.02261 1.21386 0.53341

    Standard Error t Value


    0.00700 2.54895 0.00451 3.24037 0.00698 3.24037 0.37461 3.24037 0.16461 3.24037

    logexported_top10_pjc _Add3

    Covariances Among Exogenous Variables Var1 E1 inf Var2 E2 Parameter Estimate


    eps3 0.00867 0.05862 -0.09799 -0.27589

    Standard Error
    0.00541 0.03835

    t Value
    1.60183 1.52842

    logpop _Add4

    logexported_top10_pjc logpop _Add5 logexported_top10_pjc inf


    _Add6

    0.03212 -3.05081 0.18563 -1.48629

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Full Information Maximum Likelihood Estimation
    Mean Parameters Variable Type Variable Parameter Estimate
    _Add7 _Add8 0.06473 2.74457 10.73071

    Standard Error
    0.03282

    t Value
    1.97268

    Observed logpop inf

    0.24042 11.41562 0.15937 67.33015

    logexported_top10_pjc _Add9

    Squared Multiple Correlations Variable logimport logprice_pjc Error Total Variance Variance R-Square
    0.01784 0.01462 0.07172 0.06936 0.7512 0.7892

    The SAS System Generalized Least Squares


    The CALIS Procedure Mean and Covariance Structures: Full Information Maximum Likelihood Estimation
    Standardized Results for Linear Equations
    logimport Std Err t Value logprice_pjc = Std Err t Value = -0.5584 * logprice_pjc 0.2327 -2.3999 0.1758 * logpop 0.2233 0.7871 alphalogpop betalogprice_pjc + 0.3718 * logpop 0.2046 1.8169 + -0.1404 * inf 0.1091 -1.2867 alphainf betalogpop + 0.1443 * inf 0.1252 1.1528 + 0.9850 * logexported_top10_pjc + 1.0000 0.2016 4.8851 alphatop10 E2 betainf + 1.0000 E1

    Standardized Results for Variances of Exogenous Variables Variable Type Error Variable E1 E2 Observed logpop inf Parameter Estimate
    eps1 eps2 _Add1 _Add2 0.24877 0.21076 1.00000 1.00000 1.00000

    Standard Error t Value


    0.11274 2.20663 0.08172 2.57915

    logexported_top10_pjc _Add3

    Standardized Results for Covariances Among Exogenous Variables Var1 E1 inf Var2 E2 Parameter Estimate
    eps3 0.12289 0.35379 -0.89220 -0.34287

    Standard Error
    0.08233 0.19090 0.04451 0.19256

    t Value
    1.49266 1.85322 -20.04374 -1.78054

    logpop _Add4

    logexported_top10_pjc logpop _Add5 logexported_top10_pjc inf


    _Add6

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy