s-news
[Top] [All Lists]

Re: How to extract variance estimate

To: "Shepherd, Marsha (NIH/NIEHS)" <shepher1@niehs.nih.gov>, "'S-News'" <s-news@wubios.wustl.edu>
Subject: Re: How to extract variance estimate
From: "Richard M. Heiberger" <rmh@temple.edu>
Date: Mon, 24 Jan 2005 13:37:10 -0500
> y <- rnorm(10)
> x <- rnorm(10)
> xy.lm <- lm(y ~ x)
> anova(xy.lm)
Analysis of Variance Table

Response: y

Terms added sequentially (first to last)
          Df Sum of Sq  Mean Sq   F Value     Pr(F) 
        x  1   0.32616 0.326158 0.2489053 0.6312743
Residuals  8  10.48297 1.310372                    
> summary(xy.lm)

Call: lm(formula = y ~ x)
Residuals:
    Min      1Q  Median    3Q   Max 
 -2.269 -0.4222 0.03735 0.583 1.742

Coefficients:
              Value Std. Error t value Pr(>|t|) 
(Intercept) -0.4111  0.4207    -0.9772  0.3571 
          x  0.1841  0.3691     0.4989  0.6313 

Residual standard error: 1.145 on 8 degrees of freedom
Multiple R-Squared: 0.03017 
F-statistic: 0.2489 on 1 and 8 degrees of freedom, the p-value is 0.6313 

Correlation of Coefficients:
  (Intercept) 
x -0.5096    
> names(summary(xy.lm))
 [1] "call"         "terms"        "residuals"    "coefficients" "sigma"       
 [6] "df"           "r.squared"    "fstatistic"   "cov.unscaled" "correlation" 
> summary(xy.lm)$sigma
[1] 1.144715
> summary(xy.lm)$sigma^2
[1] 1.310372
> 

<Prev in Thread] Current Thread [Next in Thread>
  • Re: How to extract variance estimate, Richard M. Heiberger <=