[R-sig-ME] Different lm and aov summary

[Ista Zahn]

summary.aov should be used with aov models, not lm models. I'm not
actually sure if that is the cause of the discrepancy, but I would
start by using the appropriate methods and see if that clears things
up.

Best,
Ista

On Wed, Feb 23, 2011 at 1:38 PM, Szymek Drobniak <geralttee at gmail.com> wrote:
> Dear mixed modellers,
>
> I'm a bit confused and that's why I'm asking. I came across with sthng
> similar on the listbut couldn't actually fimd the answer there... But to the
> point - there's a model with several fixed effects, some of them with 2
> levels (eg. Age). When I look at the regression-like output there seems to
> be no age-relared effect - and in the aov table (summary.aov() or anova())
> this effect is significant. Are these two tests fundamentally different and
> if so - which one givesthe right answer? Below you'll find both outputs
>
>> Lmount1 <- lm(Lmount~age*status*morph, data=age)
>> summary(Lmount1)
>
> Call:
> lm(formula = Lmount ~ age * status * morph, data = age)
>
> Residuals:
>    Min      1Q  Median      3Q     Max
> -3337.0  -868.6  -137.1   708.8  6910.0
>
> Coefficients:
>                    Estimate Std. Error t value Pr(>|t|)
> (Intercept)          2651.16     313.49   8.457 1.53e-13 ***
> ageY                 -659.13     414.71  -1.589   0.1149
> status1              -182.41     224.42  -0.813   0.4181
> status2               650.43     379.11   1.716   0.0891 .
> morphS                -96.31     384.30  -0.251   0.8026
> ageY:status1         -216.24     301.50  -0.717   0.4748
> ageY:status2         -451.82     493.18  -0.916   0.3617
> ageY:morphS          -295.03     527.77  -0.559   0.5773
> status1:morphS       -248.81     279.64  -0.890   0.3756
> status2:morphS       -620.20     456.58  -1.358   0.1772
> ageY:status1:morphS   525.32     385.36   1.363   0.1757
> ageY:status2:morphS   324.96     624.60   0.520   0.6040
> ---
> Signif. codes:  0 �***� 0.001 �**� 0.01 �*� 0.05 �.� 0.1 � � 1
>
> Residual standard error: 1363 on 107 degrees of freedom
>  (30 observations deleted due to missingness)
> Multiple R-squared: 0.2042,     Adjusted R-squared: 0.1223
> F-statistic: 2.495 on 11 and 107 DF,  p-value: 0.007876
>
>> summary.aov(Lmount1)
>                  Df    Sum Sq  Mean Sq F value   Pr(>F)
> age                1  20619061 20619061 11.1010 0.001185 **
> status             2  19083130  9541565  5.1370 0.007408 **
> morph              1   1503500  1503500  0.8095 0.370299
> age:status         2   1480585   740293  0.3986 0.672276
> age:morph          1    741135   741135  0.3990 0.528945
> status:morph       2   3407887  1703943  0.9174 0.402684
> age:status:morph   2   4148964  2074482  1.1169 0.331087
> Residuals        107 198742119  1857403
> ---
> Signif. codes:  0 �***� 0.001 �**� 0.01 �*� 0.05 �.� 0.1 � � 1
> 30 observations deleted due to missingness
>
> Cheers,
> Sz.
>
>        [[alternative HTML version deleted]]
>
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>
>



-- 
Ista Zahn
Graduate student
University of Rochester
Department of Clinical and Social Psychology
http://yourpsyche.org