--------------------------------------------------------------------------- Blimp 3.2.10 Blimp was developed with funding from Institute of Education Sciences awards R305D150056 and R305D190002. Craig K. Enders, P.I. Email: cenders@psych.ucla.edu Brian T. Keller, Co-P.I. Email: btkeller@missouri.edu Han Du, Co-P.I. Email: hdu@psych.ucla.edu Roy Levy, Co-P.I. Email: roy.levy@asu.edu Programming and Blimp Studio by Brian T. Keller There is no expressed license given. --------------------------------------------------------------------------- ALGORITHMIC OPTIONS SPECIFIED: Imputation method: Fully Bayesian model-based MCMC algorithm: Full conditional Metropolis sampler with Auto-Derived Conditional Distributions Between-cluster imputation model: Not applicable, single-level imputation Prior for random effect variances: Not applicable, single-level imputation Prior for residual variances: Zero sum of squares, df = -2 (PRIOR2) Prior for predictor variances: Unit sum of squares, df = 2 (XPRIOR1) Chain Starting Values: Random starting values BURN-IN POTENTIAL SCALE REDUCTION (PSR) OUTPUT: NOTE: Split chain PSR is being used. This splits each chain's iterations to create twice as many chains. Comparing iterations across 2 chains Highest PSR Parameter # 126 to 250 1.025 10 251 to 500 1.014 4 376 to 750 1.017 10 501 to 1000 1.007 1 626 to 1250 1.006 8 751 to 1500 1.004 10 876 to 1750 1.008 11 1001 to 2000 1.002 11 1126 to 2250 1.003 11 1251 to 2500 1.003 11 1376 to 2750 1.001 3 1501 to 3000 1.001 7 1626 to 3250 1.002 5 1751 to 3500 1.002 11 1876 to 3750 1.002 11 2001 to 4000 1.001 11 2126 to 4250 1.002 10 2251 to 4500 1.001 5 2376 to 4750 1.001 7 2501 to 5000 1.001 7 METROPOLIS-HASTINGS ACCEPTANCE RATES: Chain 1: Variable Type Probability Target Value x1 imputation 0.499 0.500 NOTE: Suppressing printing of 1 chains. Use keyword 'tuneinfo' in options to override. DATA INFORMATION: Sample Size: 1000 Missing Data Rates: y = 00.00 x1 = 08.80 MODEL INFORMATION: NUMBER OF PARAMETERS Outcome Models: 4 Predictor Models: 3 PREDICTORS Fixed variables: x2 Incomplete continuous: x1 MODELS [1] y ~ Intercept x1 x2 WARNING MESSAGES: No warning messages. MODEL FIT: INFORMATION CRITERIA Marginal Likelihood DIC2 2797.690 WAIC 2814.756 Conditional Likelihood DIC2 2797.690 WAIC 2814.756 CORRELATIONS AMONG RESIDUALS: No residual correlations. OUTCOME MODEL ESTIMATES: Summaries based on 5000 iterations using 2 chains. Outcome Variable: y Parameters Median StdDev 2.5% 97.5% PSR N_Eff ------------------------------------------------------------------- Variances: Residual Var. 0.938 0.044 0.859 1.029 1.002 3527.214 Coefficients: Intercept -0.021 0.031 -0.084 0.040 1.001 4155.296 x1 0.964 0.034 0.898 1.031 1.001 3914.456 x2 1.009 0.031 0.951 1.069 1.001 3898.620 Standardized Coefficients: x1 0.509 0.015 0.479 0.538 1.002 3884.470 x2 0.572 0.014 0.543 0.599 1.001 3662.815 Proportion Variance Explained by Coefficients 0.721 0.013 0.696 0.744 1.003 3567.152 by Residual Variation 0.279 0.013 0.256 0.304 1.003 3567.152 ------------------------------------------------------------------- PREDICTOR MODEL ESTIMATES: Summaries based on 5000 iterations using 2 chains. Missing predictor: x1 Parameters Median StdDev 2.5% 97.5% PSR N_Eff ------------------------------------------------------------------- Grand Mean -0.013 0.031 -0.072 0.049 1.000 4300.645 Level 1: x2 0.216 0.029 0.159 0.273 1.001 3883.537 Residual Var. 0.888 0.041 0.812 0.974 1.000 3451.772 -------------------------------------------------------------------