I would like to compare two models using f-test fitting my data. For each model I performed Monte-Carlo simulation that provided statistical estimation for each model parameter and rms fit error. I would like to use f-test in R to determine which model is preferable.
Best to use the anova function.
anova(modle1, model2)
This preforms a model f test.
Related
The documentation for the multinom() function from the nnet package in R says that it "[f]its multinomial log-linear models via neural networks" and that "[t]he response should be a factor or a matrix with K columns, which will be interpreted as counts for each of K classes." Even when I go to add a tag for nnet on this question, the description says that it is software for fitting "multinomial log-linear models."
Granting that statistics has wildly inconsistent jargon that is rarely operationally defined by whoever is using it, the documentation for the function even mentions having a count response and so seems to indicate that this function is designed to model count data. Yet virtually every resource I've seen treats it exclusively as if it were fitting a multinomial logistic regression. In short, everyone interprets the results in terms of logged odds relative to the reference (as in logistic regression), not in terms of logged expected count (as in what is typically referred to as a log-linear model).
Can someone clarify what this function is actually doing and what the fitted coefficients actually mean?
nnet::multinom is fitting a multinomial logistic regression as I understand...
If you check the source code of the package, https://github.com/cran/nnet/blob/master/R/multinom.R and https://github.com/cran/nnet/blob/master/R/nnet.R, you will see that the multinom function is indeed using counts (which is a common thing to use as input for a multinomial regression model, see also the MGLM or mclogit package e.g.), and that it is fitting the multinomial regression model using a softmax transform to go from predictions on the additive log-ratio scale to predicted probabilities. The softmax transform is indeed the inverse link scale of a multinomial regression model. The way the multinom model predictions are obtained, cf.predictions from nnet::multinom, is also exactly as you would expect for a multinomial regression model (using an additive log-ratio scale parameterization, i.e. using one outcome category as a baseline).
That is, the coefficients predict the logged odds relative to the reference baseline category (i.e. it is doing a logistic regression), not the logged expected counts (like a log-linear model).
This is shown by the fact that model predictions are calculated as
fit <- nnet::multinom(...)
X <- model.matrix(fit) # covariate matrix / design matrix
betahat <- t(rbind(0, coef(fit))) # model coefficients, with expicit zero row added for reference category & transposed
preds <- mclustAddons::softmax(X %*% betahat)
Furthermore, I verified that the vcov matrix returned by nnet::multinom matches that when I use the formula for the vcov matrix of a multinomial regression model, Faster way to calculate the Hessian / Fisher Information Matrix of a nnet::multinom multinomial regression in R using Rcpp & Kronecker products.
Is it not the case that a multinomial regression model can always be reformulated as a Poisson loglinear model (i.e. as a Poisson GLM) using the Poisson trick (glmnet e.g. uses the Poisson trick to fit multinomial regression models as a Poisson GLM)?
To explain my problem , i have this simulated data using R.
require(splines)
x=rnorm(20 ,0,1)
y=rep(c(0,1),times=10)
First i fitted a regular (linear effects) logistic regression model.
fit1=glm(y~x ,family = "binomial")
Then to check the non linear effects, i fitted this natural spline model .
fit2=glm(y~ns(x,df=2) ,family = "binomial")
Based on my thinking models , i believe these 2 models are non nested models.
Next i wanted check whether the non linear model (fit2) has any significant effects compared to the regular logistic model (fit1).
Is there any way to compare this two models? I believe i cannot use the lrtest function in lmtest package, because these two models are not nested models.
Any suggestion will be highly appreciated
Thank you.
I am trying to use a generalized least square model (gls in R) on my panel data to deal with autocorrelation problem.
I do not want to have any lags for any variables.
I am trying to use Durbin-Watson test (dwtest in R) to check the autocorrelation problem from my generalized least square model (gls).
However, I find that the dwtest is not applicable over gls function while it is applicable to other functions such as lm.
Is there a way to check the autocorrelation problem from my gls model?
Durbin-Watson test is designed to check for presence of autocorrelation in standard least-squares models (such as one fitted by lm). If autocorrelation is detected, one can then capture it explicitly in the model using, for example, generalized least squares (gls in R). My understanding is that Durbin-Watson is not appropriate to then test for "goodness of fit" in the resulting models, as gls residuals may no longer follow the same distribution as residuals from the standard lm model. (Somebody with deeper knowledge of statistics should correct me, if I'm wrong).
With that said, function durbinWatsonTest from the car package will accept arbitrary residuals and return the associated test statistic. You can therefore do something like this:
v <- gls( ... )$residuals
attr(v,"std") <- NULL # get rid of the additional attribute
car::durbinWatsonTest( v )
Note that durbinWatsonTest will compute p-values only for lm models (likely due to the considerations described above), but you can estimate them empirically by permuting your data / residuals.
library(forecast)
data(Nile,package="datasets")
train=Nile[1:50]##I want to use this to train model
test<-Nile[51:length(Nile)]
m1<-auto.arima(Nile)
My question is that now I got a arima model, and how can I use this model combined with the old data(train) to forecast the value in test in dynamics. What I want is like in an OLS regression, I got a model, then I can use other data to test this model. Finally I can draw a picture.
One can perform glm model fit with logistic link function for response from binomial family and then can apply step function to extract the best subset of explanatory features in terms of information criterion such as AIC or BIC.
Have anyone performed such procedure for an output model from cv.glmnetfunction or glmnet from glmnet package? Can you suggest how one can reproduce the same methodology used on regular glm model and cv.glmnet model?
This below doesn't look like it would work:
modelAIC <-step( object= model$glmnet.fit, direction = "backward")