• Title/Summary/Keyword: 추한 한국인

Search Result 5,308, Processing Time 0.035 seconds

Interval Estimation in Mixed Model by Use of PROC MIXED (PROC MIXED를 활용한 혼합모형의 신뢰구간추정)

  • Park Dong-Joon
    • The Korean Journal of Applied Statistics
    • /
    • v.19 no.2
    • /
    • pp.349-360
    • /
    • 2006
  • PROC MIXED in SAS can be utilized to make inferences on parameters in a mixed model by use of Restricted Maximum Likelihood Estimation Method or Maximum Likelihood Estimation Method which has more merits than ANOVA method. A regression model with unbalanced nested error structure that belongs to a mixed model is used to construct confidence intervals on variances among groups, within groups, and regression coefficients in the model. PROC MIXED is applied to three different sample sizes for simulation. As a result of the simulation study, PROC MIXED generates confidence intervals on parameters that maintain the stated confidence coefficient in a large sample size. However, it does not generate confidence intervals that maintain the stated confidence coefficient for variance components among groups and intercept in a small sample size.