I tried to read over below article but don't understand, anybody shade me a light?
UNDERSTANDING 3WAY INTERACTIONS BETWEEN CONTINUOUS VARIABLES
R LME4 mixed models with nesting and nestinginteractions
Above question asked about nested interaction model, I do appreciate if somebody shade me a light.
your first post is ideas on how to graph fitted models of a certain type.
your second post is about how to construct a particular model.
I think you would have higher likelihood of being supported here, if you ask a very specific question. Try to be clear on whether you have an R question, or a statistics question...
General requests to be supported in understanding large openended topics are unlikely to be successful in garnering help.
Result < lmer(Y ~ X*Z*W+(1PPX)+I(X*Z*W)^2+I(X*Z*W)^3,data=Matrix)
From bove example, I don't know how to interpret above model?
How to calculate X
value, Z
value and W
value in R?
You should study the lmer formula syntax
https://benwhalley.github.io/justenoughr/fittingmodels.html
Your second question doesn't make sense so I can't answer it the way you asked it. You should be aware that X Z W are symbols representing the variables containing training data for the model to be fit on
Result < lm(Y ~ X * Z * W, data = Matrix)
How to interpret above model, calculate X
value and Z
value and W
value in R?
if you repeat yourself I also can repeat myself. but its not a very fun game....
in a normal lm()
the * syntax means to have the variable and also its interaction with the other variable in the model
so X*Z is equivalent to X + Z + X:Z
X and Z and W values
are not something that one would calculate
....
Update model : 3way interaction terms not dropped there is an example for 3way interaction terms with polynomial models, may I know how to interpret it?
you want to understand a model on data you dont know over a modelling context you dont know, and also the model is incorrect as it was based on a users syntax error ?
I'm sorry but I won't touch this.
https://stats.stackexchange.com/a/373259/68357 is an example, I kust wonder if I have lm()
...
Below is another example
>> x < lm(mpg ~ cyl * disp * hp * drat, mtcars)
>> summary(x)
>
> Call:
> lm(formula = mpg ~ cyl * disp * hp * drat, data = mtcars)
>
> Residuals:
> Min 1Q Median 3Q Max
> 3.5725 0.6603 0.0108 1.1017 2.6956
>
> Coefficients:
> Estimate Std. Error t value Pr(>t)
> (Intercept) 1.070e+03 3.856e+02 2.776 0.01350 *
> cyl 2.084e+02 7.196e+01 2.896 0.01052 *
> disp 6.760e+00 3.700e+00 1.827 0.08642 .
> hp 9.302e+00 3.295e+00 2.823 0.01225 *
> drat 2.824e+02 1.073e+02 2.633 0.01809 *
> cyl:disp 1.065e+00 5.034e01 2.116 0.05038 .
> cyl:hp 1.587e+00 5.296e01 2.996 0.00855 **
> disp:hp 7.422e02 3.461e02 2.145 0.04769 *
> cyl:drat 5.652e+01 2.036e+01 2.776 0.01350 *
> disp:drat 1.824e+00 1.011e+00 1.805 0.08990 .
> hp:drat 2.600e+00 9.226e01 2.819 0.01236 *
> cyl:disp:hp 1.050e02 4.518e03 2.323 0.03368 *
> cyl:disp:drat 2.884e01 1.392e01 2.071 0.05484 .
> cyl:hp:drat 4.428e01 1.504e01 2.945 0.00950 **
> disp:hp:drat 2.070e02 9.568e03 2.163 0.04600 *
> cyl:disp:hp:drat 2.923e03 1.254e03 2.331 0.03317 *
> 
> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>
> Residual standard error: 2.245 on 16 degrees of freedom
> Multiple Rsquared: 0.9284, Adjusted Rsquared: 0.8612
> Fstatistic: 13.83 on 15 and 16 DF, pvalue: 2.007e06
Source : https://stat.ethz.ch/pipermail/rhelp/2013April/351761.html
mpg
is y, may I know below calculation if correct?

cyl
= cyl 
disp
= disp + cyl:disph + cyl:disp:hp + cyl:disp:drat + cyl:disp:hp:drat 
hp
= hp + cyl:hp + cyl:disp:hp +disp:hp:drat + cyl:disp:hp:drat 
drat
= drat + hp:drat + cyl:disp:drat + disp:hp:drat + cyl:disp:hp:drat
This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.