[R] help interpreting a model summary

[zozio32]

Actually, rereading trough my post, I think I understood a bit better now.
I have now fit a much simpler to each part of the data, and things looks a
bit easier to understand.

for the part were reflection < break[xmin], i now have:

Call:
lm(formula = weightedDiff ~ angleNoise * reflection, data = data1)

Residuals:
       Min         1Q     Median         3Q        Max 
-1.081e-03 -2.296e-04  1.335e-05  2.010e-04  1.287e-03 

Coefficients:
                        Estimate Std. Error t value Pr(>|t|)    
(Intercept)            1.057e-02  7.536e-05 140.273  < 2e-16 ***
angleNoise             1.648e-03  1.542e-04  10.684  < 2e-16 ***
reflection             1.021e-01  3.155e-03  32.361  < 2e-16 ***
angleNoise:reflection -3.877e-02  6.679e-03  -5.804  2.1e-08 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 

Residual standard error: 0.0003556 on 233 degrees of freedom
Multiple R-squared: 0.8971,	Adjusted R-squared: 0.8957 
F-statistic: 676.9 on 3 and 233 DF,  p-value: < 2.2e-16 


and for the other I have:

Call:
lm(formula = weightedDiff ~ angleNoise * reflection, data = data2)

Residuals:
       Min         1Q     Median         3Q        Max 
-6.252e-04 -1.391e-04 -1.086e-05  1.365e-04  7.281e-04 

Coefficients:
                        Estimate Std. Error t value Pr(>|t|)    
(Intercept)            1.342e-02  8.197e-05 163.715  < 2e-16 ***
angleNoise             5.577e-04  1.696e-04   3.289  0.00110 ** 
reflection             3.236e-02  1.127e-03  28.722  < 2e-16 ***
angleNoise:reflection -6.719e-03  2.340e-03  -2.871  0.00433 ** 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 

Residual standard error: 0.0002341 on 359 degrees of freedom
Multiple R-squared: 0.8269,	Adjusted R-squared: 0.8254 
F-statistic: 571.5 on 3 and 359 DF,  p-value: < 2.2e-16 


i hope i can now safely conclude that both parameters are significant, and
that their respective slope decreases when reflection is > Break[xMin]
I also assume that the negative sign on both interaction term can be
interpret as angleNoise "influence" decreaes as reflection increases.
Is that a more sensible interpretation of my data?
-- 
View this message in context: http://r.789695.n4.nabble.com/help-interpreting-a-model-summary-tp2546161p2546303.html
Sent from the R help mailing list archive at Nabble.com.