I'm working with a mgcv::gam model in R to generate predictions in which the relationship between time (year) and the outcome variable (out) varies. For example, in one scenario, I'd like to force time to affect the outcome variable in a linear manner, in another a marginally decreasing manner, and in another, I'd like to specify specific slopes of the time-outcome interaction. I'm unsure how to force the prediction to treat the interaction between time and the outcome variable in a specific manner:
res <- gam(out ~ s(time) + s(GEOID, bs='re'), data = df, method = "REML")
pred <- predict(gam, newdata = ndf, type="response", se=T)
There isn't an interaction betweentime and out; here time has a potentially non-linear effect on out.
Are we talking about trying to force certain shapes for the function of time? If so, you will need to estimate different models; use time if you want a linear effect:
res_lin <- gam(out ~ time + s(GEOID, bs='re'), data = df, method = "REML")
and look at shape constrained p splines to enforce montonicity or concave/convex relationships.
The scam package has these sorts of constraints and uses mgcv with GCV smoothness selection to fit the shape constrained models.
As for specifying a specific slope for the linear effect of time, I think you'll need to include time as an offset in the model. So say the slope you want is 0.5 I think you need to do + offset(I(0.5*time)) because an offset has by definition a coefficient of 1. I would double check this though as I might have messed up my thinking here.
Related
I am currently trying to generate a general additive model in R using a response variable and three predictor variables. One of the predictors is linear, and the dataset consists of 298 observations.
I have run the following code to generate a basic GAM:
GAM <- gam(response~ linearpredictor+ s(predictor2) + s(predictor3), data = data[2:5])
This produces a model with 18 degrees of freedom and seems to substantially overfit the data. I'm wondering how I might generate a GAM that maximizes smoothness and predictive error. I realize that each of these features is going to come at the expense of the other, but is there good a way to find the optimal model that doesn't overfit?
Additionally, I need to perform leave one out cross validation (LOOCV), and I am not sure how to make sure that gam() does this in the MGCV package. Any help on either of these problems uld be greatly appreciated. Thank you.
I've run this to generate a GAM, but it overfits the data.
GAM <- gam(response~ linearpredictor+ s(predictor2) + s(predictor3), data = data[2:5])
I have also generated 1,000,000 GAMs with varying combinations of smoothing parameters and ranged the maximum degrees of freedom allowed from 10 (as shown in the code below) to 19. The variable "combinations2" is a list of all 1,000,000 combinations of smoothers I selected. This code is designed to try and balance degrees of freedom and AIC score. It does function, but I'm not sure that I'm actually going to be able to find the optimal model from this. I also cannot tell how to make sure that it uses LOOCV.
BestGAM <- gam(response~ linearpredictor+ predictor2+ predictor3, data = data[2:5])
for(i in 1:100000){
PotentialGAM <- gam(response~ linearpredictor+ s(predictor2) + s(predictor3), data = data[2:5], sp=c(combinations2[i,]$Var1,combinations2[i,]$Var2))
if (AIC(PotentialGAM,BestGAM)$df[1] <= 10 & AIC(PotentialGAM,BestGAM)$AIC[1] < AIC(PotentialGAM,BestGAM)$AIC[2]){
BestGAM <<- PotentialGAM
listNumber <- i
}
}
You are fitting your GAM using generalised cross validation (GCV) smoothness selection. GCV is a way to get around the invariance problem of ordinary cross validation (OCV; what you also call LOOCV) when estimating GAMs. Note that GCV is the same as OCV on a rotated version of the fitting problem (rotating y - Xβ by Q, any orthogonal matrix), and while when fitting with GCV {mgcv} doesn't actually need to do the rotation and the expected GCV score isn't affected by the rotation, GCV is just OCV (wood 2017, p. 260)
It has been shown that GCV can undersmooth (resulting in more wiggly models) as the objective function (GCV profile) can become flat around the optimum. Instead it is preferred to estimate GAMs (with penalized smooths) using REML or ML smoothness selection; add method = "REML" (or "ML") to your gam() call.
If the REML or ML fit is as wiggly as the GCV one with your data, then I'd be likely to presume gam() is not overfitting, but that there is something about your response data that hasn't been explained here (are the data ordered in time, for example?)
As to your question
how I might generate a GAM that maximizes smoothness and [minimize?] predictive error,
you are already doing that using GCV smoothness selection and for a particular definition of "smoothness" (in this case it is squared second derivatives of the estimated smooths, integrated over the range of the covariates, and summed over smooths).
If you want GCV but smoother models, you can increase the gamma argument above 1; gamma 1.4 is often used for example, which means that each EDF costs 40% more in the GCV criterion.
FWIW, you can get the LOOCV (OCV) score for your model without actually fitting 288 GAMs through the use of the influence matrix A. Here's a reproducible example using my {gratia} package:
library("gratia")
library("mgcv")
df <- data_sim("eg1", seed = 1)
m <- gam(y ~ s(x0) + s(x1) + s(x2) + s(x3), data = df, method = "REML")
A <- influence(m)
r <- residuals(m, type = "response")
ocv_score <- mean(r^2 / (1 - A))
I am building a model using the mgcv package in r. The data has serial measures (data collected during scans 15 minutes apart in time, but discontinuously, e.g. there might be 5 consecutive scans on one day, and then none until the next day, etc.). The model has a binomial response, a random effect of day, a fixed effect, and three smooth effects. My understanding is that REML is the best fitting method for binomial models, but that this method cannot be specified using the gamm function for a binomial model. Thus, I am using the gam function, to allow for the use of REML fitting. When I fit the model, I am left with residual autocorrelation at a lag of 2 (i.e. at 30 minutes), assessed using ACF and PACF plots.
So, we wanted to include an autocorrelation structure in the model, but my understanding is that only the gamm function and not the gam function allows for the inclusion of such structures. I am wondering if there is anything I am missing and/or if there is a way to deal with autocorrelation with a binomial response variable in a GAMM built in mgcv.
My current model structure looks like:
gam(Response ~
s(Day, bs = "re") +
s(SmoothVar1, bs = "cs") +
s(SmoothVar2, bs = "cs") +
s(SmoothVar3, bs = "cs") +
as.factor(FixedVar),
family=binomial(link="logit"), method = "REML",
data = dat)
I tried thinning my data (using only every 3rd data point from consecutive scans), but found this overly restrictive to allow effects to be detected due to my relatively small sample size (only 42 data points left after thinning).
I also tried using the prior value of the binomial response variable as a factor in the model to account for the autocorrelation. This did appear to resolve the residual autocorrelation (based on the updated ACF/PACF plots), but it doesn't feel like the most elegant way to do so and I worry this added variable might be adjusting for more than just the autocorrelation (though it was not collinear with the other explanatory variables; VIF < 2).
I would use bam() for this. You don't need to have big data to fit a with bam(), you just loose some of the guarantees about convergence that you get with gam(). bam() will fit a GEE-like model with an AR(1) working correlation matrix, but you need to specify the AR parameter via rho. This only works for non-Gaussian families if you also set discrete = TRUE when fitting the model.
You could use gamm() with family = binomial() but this uses PQL to estimate the GLMM version of the GAMM and if your binomial counts are low this method isn't very good.
I'm currently trying to use a GAM to calculate a rough estimation of expected goals model based purely on the commentary data from ESPN. However, all the data is either a categorical variable or a logical vector, so I'm not sure if there's a way to smooth, or if I should just use the factor names.
Here are my variables:
shot_where (factor): shot location (e.g. right side of the box)
assist_class (factor): type of assist (cross, through ball, pass)
follow_corner (logical): whether the shot follows a corner
shot_with (factor): right foot, left food, header
follow_set_piece (logical): whether the shot follows a set piece
I think I should just use the formula as just the variable names.
model <- bam(is_goal ~ shot_where + assist_class + follow_set_piece + shot_where + follow_corner + shot_where:shot_with, family = "binomial", method = "REML")
The shot_where and shot_with would incorporate any interactions between these two varaibles.
However, I was told I could smooth factor variables as well using the below structure.
model <- bam(is_goal ~ s(shot_where, bs = 'fs') + s(assist_class, bs = 'fs') + as.logical(follow_set_piece) +
as.logical(follow_corner) + s(shot_with, bs = 'fs'), data = model_data, family = "binomial", method = "REML")
This worked for creating a model, but I want to make sure this is a correct method of building the model. I've yet to see any information on using only factor/logical variables in a GAM model, so I thought it was worth asking.
If you only have categorical covariates then you aren't fitting a GAM, whether you fit the model with gam(), bam(), or something else.
What you are doing when you pass factor variables to s() using the fs basis like this
s(f, bs = 'fs')`
is creating a random intercept for each level of the factor f.
There's no smoothing going on here at all; the model is simply exploiting the equivalence of the Bayesian view of smoothing with random effects.
Given that none of your covariates could reasonably be considered random in the sense of a mixed effects model then the only justification for doing what you're doing might be as a computational trick.
Your first model is just a simple GLM (note the typo in the formula as shot_where is repeated twice in the formula.)
It's not clear to me why you are using bam() to fit this model; you're loosing computational efficiency that bam() provides by using method = 'REML'; it should be 'fREML' for bam() models. But as there is no smoothness selection going on in the first model you'd likely be better off using glm() to fit that model. If the issue is large sample sizes, there are several packages that can fit GLMs to large data, for example biglm and it's bigglm() function.
In the second model there is no smoothing going on but there is penalisation which is shrinking the estimates for the random intercepts toward zero. You're likely to get better performance on big data using the lme4 package or TMB and the glmmTMB package to fit what is a GLMM.
This is more of a theoretical question than about R, but let me provide a brief answer. Essentially, the most flexible model you could estimate would be one where you used the variables as factors. It also produces a model that is reasonably easily interpreted - where each coefficient gives you the expected difference in y between the reference level and the level represented by the dummy regressor.
Smoothing splines try to strike the appropriate bias-variance tradeoff. If you've got lots of data and relatively few categories in the categorical variables, there will be no real loss in efficiency for including all of the dummy regressors representing the categories and the bias will also be as small as possible. To the extent that the smoothing spline model is different from the one treating everything as factors, it is likely inducing bias without a corresponding increase in efficiency. If it were me, I would stick with a model that treats all of the categorical variables as factors.
I am using "glmnet" package (in R) mostly to perform regularized linear regression.
However I am wondering if it can perform LASSO-type regressions with non-negative (integer) continuous (dependent) outcome variable.
I can use family = poisson, but the outcome variable is not specifically "count" variable. It is just a continuous variable with lower limit 0.
I aware of "lower.limits" function, but I guess it is for covariates (independent variables). (Please correct me if my understanding of this function not right.)
I look forward to hearing from you all! Thanks :-)
You are right that setting lower limit in glmnet is meant for covariates. Poisson will set a lower limit to zero because you exponentiate to get back the "counts".
Going along those lines, most likely it will work if you transform your response variable. One quick way is to take the log of your response variable, do the fit and transform it back, this will ensure that it's always positive. you have to deal with zeros
An alternative is a power transformation. There's a lot to think about and I can only try a two parameter box-cox with a dataset since you did not provide yours:
library(glmnet)
library(mlbench)
library(geoR)
data(BostonHousing)
data = BostonHousing
data$chas=as.numeric(data$chas)
# change it to min 0 and max 1
data$medv = (data$medv-min(data$medv))/diff(range(data$medv))
Then here I use a quick approximation via pca (without fitting all the variables) to get the suitable lambda1 and lambda2 :
bcfit = boxcoxfit(object = data[,14],
xmat = prcomp(data[,-14],scale=TRUE,center=TRUE)$x[,1:2],
lambda2=TRUE)
bcfit
Fitted parameters:
lambda lambda2 beta0 beta1 beta2 sigmasq
0.42696313 0.00001000 -0.83074178 -0.09876102 0.08970137 0.05655903
Convergence code returned by optim: 0
Check the lambda2, it is the one thats critical for deciding whether you get a negative value.. It should be rather small.
Create the functions to power transform:
bct = function(y,l1,l2){((y+l2)^l1 -1)/l1}
bctinverse = function(y,l1,l2){(y*l1+1)^(1/l1) -l2}
Now we transform the response:
data$medv_trans = bct(data$medv,bcfit$lambda[1],bcfit$lambda[2])
And fit glmnet:
fit = glmnet(x=as.matrix(data[,1:13]),y=data$medv_trans,nlambda=500)
Get predictions over all lambdas, and you can see there's no negative predictions once you transform back:
pred = predict(fit,as.matrix(data[,1:13]))
range(bctinverse(pred,bcfit$lambda[1],bcfit$lambda[2]))
[1] 0.006690685 0.918473356
And let's say we do a fit with cv:
fit = cv.glmnet(x=as.matrix(data[,1:13]),y=data$medv_trans)
pred = predict(fit,as.matrix(data[,1:13]))
pred_transformed = bctinverse(pred,bcfit$lambda[1],bcfit$lambda[2]
plot(data$medv,pred_transformed,xlab="orig response",ylab="predictions")
I am trying to learn gam() in R for a logistic regression using spline on a predictor. The two methods of plotting in my code gives the same shape but different ranges of response in the logit scale, seems like an intercept is missing in one. Both are supposed to be correct but, why the differences in range?
library(ISLR)
attach(Wage)
library(gam)
gam.lr = gam(I(wage >250) ~ s(age), family = binomial(link = "logit"), data = Wage)
agelims = range(age)
age.grid = seq(from = agelims[1], to = agelims[2])
pred=predict(gam.lr, newdata = list(age = age.grid), type = "link")
par(mfrow = c(2,1))
plot(gam.lr)
plot(age.grid, pred)
I expected that both of the methods would give the exact same plot. plot(gam.lr) plots the additive effects of each component and since here there's only one so it is supposed to give the predicted logit function. The predict method is also giving me estimates in the link scale. But the actual outputs are on different ranges. The minimum value of the first method is -4 while that of the second is less than -7.
The first plot is of the estimated smooth function s(age) only. Smooths are subject to identifiability constraints as in the basis expansion used to parametrise the smooth, there is a function or combination of functions that are entirely confounded with the intercept. As such, you can't fit the smooth and an intercept in the same model as you could subtract some value from the intercept and add it back to the smooth and you have the same fit but different coefficients. As you can add and subtract an infinity of values you have an infinite supply of models, which isn't helpful.
Hence identifiability constraints are applied to the basis expansions, and the one that is most useful is to ensure that the smooth sums to zero over the range of the covariate. This involves centering the smooth at 0, with the intercept then representing the overall mean of the response.
So, the first plot is of the smooth, subject to this sum to zero constraint, so it straddles 0. The intercept in this model is:
> coef(gam.lr)[1]
(Intercept)
-4.7175
If you add this to values in this plot, you get the values in the second plot, which is the application of the full model to the data you supplied, intercept + f(age).
This is all also happening on the link scale, the log odds scale, hence all the negative values.