Given below is the code for analysis of a resolvable alpha design (alpha lattice design) using the R package asreml.
# load the data
library(agridat)
data(john.alpha)
dat <- john.alpha
# load asreml
library(asreml)
# model1 - random `gen`
#----------------------
# fitting the model
model1 <- asreml(yield ~ 1 + rep, data=dat, random=~ gen + rep:block)
# variance due to `gen`
sg2 <- summary(model1 )$varcomp[1,'component']
# mean variance of a difference of two BLUPs
vblup <- predict(model1 , classify="gen")$avsed ^ 2
# model2 - fixed `gen`
#----------------------
model2 <- asreml(yield ~ 1 + gen + rep, data=dat, random = ~ rep:block)
# mean variance of a difference of two adjusted treatment means (BLUE)
vblue <- predict(model2 , classify="gen")$avsed ^ 2
# H^2 = .803
sg2 / (sg2 + vblue/2)
# H^2c = .809
1-(vblup / 2 / sg2)
I am trying to replicate the above using the R package lme4.
# model1 - random `gen`
#----------------------
# fitting the model
model1 <- lmer(yield ~ 1 + (1|gen) + rep + (1|rep:block), dat)
# variance due to `gen`
varcomp <- VarCorr(model1)
varcomp <- data.frame(print(varcomp, comp = "Variance"))
sg2 <- varcomp[varcomp$grp == "gen",]$vcov
# model2 - fixed `gen`
#----------------------
model2 <- lmer(yield ~ 1 + gen + rep + (1|rep:block), dat)
How to compute the vblup and vblue (mean variance of difference) in lme4 equivalent to predict()$avsed ^ 2 of asreml ?
I'm not that familiar with this variance partitioning stuff, but I'll take a shot.
library(lme4)
model1 <- lmer(yield ~ 1 + rep + (1|gen) + (1|rep:block), john.alpha)
model2 <- update(model1, . ~ . + gen - (1|gen))
## variance due to `gen`
sg2 <- c(VarCorr(model1)[["gen"]]) ## 0.142902
Get conditional variances of BLUPs:
rr1 <- ranef(model1,condVar=TRUE)
vv1 <- attr(rr$gen,"postVar")
str(vv1)
## num [1, 1, 1:24] 0.0289 0.0289 0.0289 0.0289 0.0289 ...
This is a 1x1x24 array (effectively just a vector of variances; we could collapse using c() if we needed to). They're not all the same, but they're pretty close ... I don't know whether they should all be identical (and this is a roundoff issue)
(uv <- unique(vv1))
## [1] 0.02887451 0.02885887 0.02885887
The relative variation is approximately 5.4e-4 ...
If these were all the same then the mean variance of a difference of any two would be just twice the variance (Var(x-y) = Var(x)+Var(y); by construction the BLUPs are all independent). I'm going to go ahead and use this.
vblup <- 2*mean(vv1)
For the model with gen fitted as a fixed effect, let's extract the variances of the parameters relating to genotypes (which are differences in the expected value from the first level):
vv2 <- diag(vcov(model2))[-(1:3)]
summary(vv2)
##
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.06631 0.06678 0.07189 0.07013 0.07246 0.07286
I'm going to take the means of these values (not double the values, since these are already the variances of differences)
vblue <- mean(vv2)
sg2/(sg2+vblue/2) ## 0.8029779
1-(vblup/2/sg2) ## 0.7979965
The H^2 estimate looks right on, but the H^2c estimate is a little different (0.797 vs. 0.809, a 1.5% relative difference); I don't know if that is big enough to be of concern or not.
Related
In the mixed model (or REWB) framework it is common to model within changes by subtracting the cluster mean (demeaning) from a time varying x-variable, see eg. (Bell, Fairbrother & Jones, 2018). This estimator is basically the same as a fixed effects (FE) estimator (shown below using the sleepstudy data).
The issue arises when trying to model polynomials using the same principle. The equality between the estimators break when we enter our demeaned variable as a polynomial. We can restore this equality by first squaring the variable and then demeaning (see. re_poly_fixed).
dt <- lme4::sleepstudy
dt$days_squared <- dt$Days * dt$Days
dt <- cbind(dt, datawizard::demean(dt, select = c("Days", "days_squared"), group = "Subject"))
re <- lme4::lmer(Reaction ~ Days_within + (1 | Subject), data = dt, REML = FALSE)
fe <- fixest::feols(Reaction ~ Days | Subject, data = dt)
re_poly <- lme4::lmer(Reaction ~ poly(Days_within, 2, raw = TRUE) + (1 | Subject),
data = dt, REML = FALSE)
fe_poly <- fixest::feols(Reaction ~ poly(Days, 2, raw = TRUE) | Subject, data = dt)
re_poly_fixed <- lme4::lmer(Reaction ~ Days_within + days_squared_within + (1 | Subject),
data = dt, REML = FALSE)
models <-
list("re" = re, "fe" = fe, "re_poly" = re_poly, "fe_poly" = fe_poly, "re_poly_fixed" = re_poly_fixed)
modelsummary::modelsummary(models)
The main issue with this strategy is that for postestimation, especially packages that calculate marginal effects (e.g. marginaleffects in R or margins in STATA) the variable needs to be entered as a polynomial term for the calculations to consider both x and x^2. That is using poly() or I() in R or factor notation c.x##c.x in STATA). The difference can be seen in the two calls below, where the FE-call returns one effect for "Days" and the manual call returns two separate terms.
(me_fe <- summary(marginaleffects::marginaleffects(fe_poly)))
(me_re <- summary(marginaleffects::marginaleffects(re_poly_fixed)))
I may be missing something obvious here, but is it possible to retain the equality between the estimators in FE and the Mixed model setups with polynomials, while still being able to use common packages for marginal effects?
The problem is that when a transformed variable is hardcoded, the marginaleffects package does not know that it should manipulate both the transformed and the original at the same time to compute the slope. One solution is to de-mean inside the formula with I(). You should be aware that this may make the model fitting less efficient.
Here’s an example where I pre-compute the within-group means using data.table, but you could achieve the same result with dplyr::group_by():
library(lme4)
library(data.table)
library(modelsummary)
library(marginaleffects)
dt <- data.table(lme4::sleepstudy)
dt[, `:=`(Days_mean = mean(Days),
Days_within = Days - mean(Days)),
by = "Subject"]
re_poly <- lmer(
Reaction ~ poly(Days_within, 2, raw = TRUE) + (1 | Subject),
data = dt, REML = FALSE)
re_poly_2 <- lmer(
Reaction ~ poly(I(Days - Days_mean), 2, raw = TRUE) + (1 | Subject),
data = dt, REML = FALSE)
models <- list(re_poly, re_poly_2)
modelsummary(models, output = "markdown")
Model 1
Model 2
(Intercept)
295.727
295.727
(9.173)
(9.173)
poly(Days_within, 2, raw = TRUE)1
10.467
(0.799)
poly(Days_within, 2, raw = TRUE)2
0.337
(0.316)
poly(I(Days - Days_mean), 2, raw = TRUE)1
10.467
(0.799)
poly(I(Days - Days_mean), 2, raw = TRUE)2
0.337
(0.316)
SD (Intercept Subject)
36.021
36.021
SD (Observations)
30.787
30.787
Num.Obs.
180
180
R2 Marg.
0.290
0.290
R2 Cond.
0.700
0.700
AIC
1795.8
1795.8
BIC
1811.8
1811.8
ICC
0.6
0.6
RMSE
29.32
29.32
The estimated average marginal effects are – as expected – different:
marginaleffects(re_poly) |> summary()
#> Term Effect Std. Error z value Pr(>|z|) 2.5 % 97.5 %
#> 1 Days_within 10.47 0.7989 13.1 < 2.22e-16 8.902 12.03
#>
#> Model type: lmerMod
#> Prediction type: response
marginaleffects(re_poly_2) |> summary()
#> Term Effect Std. Error z value Pr(>|z|) 2.5 % 97.5 %
#> 1 Days 10.47 0.7989 13.1 < 2.22e-16 8.902 12.03
#>
#> Model type: lmerMod
#> Prediction type: response
The following answer is not exactly what I asked for in the question. But at least it is a decent workaround for anyone having similar problems.
library(lme4)
library(data.table)
library(fixest)
library(marginaleffects)
dt <- data.table(lme4::sleepstudy)
dt[, `:=`(Days_mean = mean(Days),
Days_within = Days - mean(Days),
Days2 = Days^2,
Days2_within = Days^2 - mean(Days^2)),
by = "Subject"]
fe_poly <- fixest::feols(
Reaction ~ poly(Days, 2, raw = TRUE) | Subject, data = dt)
re_poly_fixed <- lme4::lmer(
Reaction ~ Days_within + Days2_within + (1 | Subject), data = dt, REML = FALSE)
modelsummary(list(fe_poly, re_poly_fixed), output = "markdown")
We start with the two models previously described. We can manually calculate the AME or marginal effects at other values and get confidence intervals using multcomp::glht(). The approach is relatively similar to that of lincom in STATA. I have written a wrapper that returns the values in a data.table:
lincom <- function(model, linhyp) {
t <- summary(multcomp::glht(model, linfct = c(linhyp)))
ci <- confint(t)
dt <- data.table::data.table(
"estimate" = t[["test"]]$coefficients,
"se" = t[["test"]]$sigma,
"ll" = ci[["confint"]][2],
"ul" = ci[["confint"]][3],
"t" = t[["test"]]$tstat,
"p" = t[["test"]]$pvalues,
"id" = rownames(t[["linfct"]])[1])
return(dt)
}
This can likely be improved or adapted to other similar needs. We can calculate the AME by taking the partial derivative. For the present case we do this with the following equation: days + 2 * days^2 * mean(days).
marginaleffects(fe_poly) |> summary()
Term Effect Std. Error z value Pr(>|z|) 2.5 % 97.5 %
1 Days 10.47 1.554 6.734 1.6532e-11 7.421 13.51
Model type: fixest
Prediction type: response
By adding this formula to the lincom function, we get similar results:
names(fe_poly$coefficients) <- c("Days", "Days2")
mean(dt$Days) # Mean = 4.5
lincom(fe_poly, "Days + 2 * Days2 * 4.5 = 0")
estimate se ll ul t p id
1: 10.46729 1.554498 7.397306 13.53727 6.733549 2.817051e-10 Days + 2 * Days2 * 4.5
lincom(re_poly_fixed, "Days_within + 2 * Days2_within * 4.5 = 0")
estimate se ll ul t p id
1: 10.46729 0.798932 8.901408 12.03316 13.1016 0 Days_within + 2 * Days2_within * 4.5
It is possible to check other ranges of values and to add other variables from the model using the formula. This can be done using lapply or a loop and the output can then be combined using a simple rbind. This should make it relatively easy to present/plot results.
EDIT
Like Vincent pointed out below there is also marginaleffects::deltamethod. This looks to be a better more robust option, that provide similar results (with the same syntax):
mfx1 <- marginaleffects::deltamethod(
fe_poly, "Days + 2 * Days2 * 4.5 = 0")
mfx2 <- marginaleffects::deltamethod(
re_poly_fixed, "Days_within + 2 * Days2_within * 4.5 = 0")
rbind(mfx1, mfx2)
term estimate std.error statistic p.value conf.low conf.high
1 Days + 2 * Days2 * 4.5 = 0 10.46729 1.554498 6.733549 1.655739e-11 7.420527 13.51405
2 Days_within + 2 * Days2_within * 4.5 = 0 10.46729 0.798932 13.101597 3.224003e-39 8.901408 12.03316
I have run the Hosmer Lemeshow statistic in R, but I have obtained an p-value of 1. This seems strange to me. I know that a high p-valvalue means that we do not reject the null hypothesis that observed and expected are the same, but is it possible i have an error somewhere?
How do i interpret such p-value?
Below is the code i have used to run the test. I also attach how my model looks like. Response variable is a count variable, while all regressors are continous. I have run a negative binomial model, due to detected overdispersion in my initial poisson model.
> hosmerlem <- function(y, yhat, g=10)
+ {cutyhat <- cut(yhat, breaks = quantile(yhat, probs=seq(0,1, 1/g)), include.lowest=TRUE)
+ obs <- xtabs(cbind(1 - y, y) ~ cutyhat)
+ expect <- xtabs(cbind(1 - yhat, yhat) ~ cutyhat)
+ chisq <- sum((obs - expect)^2/expect)
+ P <- 1 - pchisq(chisq, g - 2)
+ return(list(chisq=chisq,p.value=P))}
> hosmerlem(y=TOT.N, yhat=fitted(final.model))
$chisq
[1] -2.529054
$p.value
[1] 1
> final.model <-glm.nb(TOT.N ~ D.PARK + OPEN.L + L.WAT.C + sqrt(L.P.ROAD))
> summary(final.model)
Call:
glm.nb(formula = TOT.N ~ D.PARK + OPEN.L + L.WAT.C + sqrt(L.P.ROAD),
init.theta = 4.979895131, link = log)
Deviance Residuals:
Min 1Q Median 3Q Max
-3.08218 -0.70494 -0.09268 0.55575 1.67860
Coefficients:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 4.032e+00 3.363e-01 11.989 < 2e-16 ***
D.PARK -1.154e-04 1.061e-05 -10.878 < 2e-16 ***
OPEN.L -1.085e-02 3.122e-03 -3.475 0.00051 ***
L.WAT.C 1.597e-01 7.852e-02 2.034 0.04195 *
sqrt(L.P.ROAD) 4.924e-01 3.101e-01 1.588 0.11231
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for Negative Binomial(4.9799) family taken to be 1)
Null deviance: 197.574 on 51 degrees of freedom
Residual deviance: 51.329 on 47 degrees of freedom
AIC: 383.54
Number of Fisher Scoring iterations: 1
Theta: 4.98
Std. Err.: 1.22
2 x log-likelihood: -371.542
As correctly pointed out by #BenBolker, Hosmer-Lemeshow is a test for logistic regression, not for a negative binomial generalized linear model.
If we consider to apply the test to a logistic regression,
the inputs of the function hosmerlem (a copy of the hoslem.test function in the package ResourceSelection) should be:
- y = a numeric vector of observations, binary (0/1)
- yhat = expected values (probabilities)
Here is an illustrative example that shows how to get the correct inputs:
set.seed(123)
n <- 500
x <- rnorm(n)
y <- rbinom(n, 1, plogis(0.1 + 0.5*x))
logmod <- glm(y ~ x, family=binomial)
# Important: use the type="response" option
yhat <- predict(logmod, type="response")
hosmerlem(y, yhat)
########
$chisq
[1] 4.522719
$p.value
[1] 0.8071559
The same result is given by the function hoslem.test:
library(ResourceSelection)
hoslem.test(y, yhat)
########
Hosmer and Lemeshow goodness of fit (GOF) test
data: y, yhat
X-squared = 4.5227, df = 8, p-value = 0.8072
As already mentioned, HL-test is not appropriate for the specified model. It is also important to know that a large p-value doesn't necessarily mean a good fit. It could also be that there isn't enough evidence to prove it's a poor fit.
Meanwhile, the gofcat package implementation of the HL-test provides for passing model objects directly to the function without necessarily supplying the observed and predicted values. For the simulated data one has:
library(gofcat)
set.seed(123)
n <- 500
x <- rnorm(n)
y <- rbinom(n, 1, plogis(0.1 + 0.5*x))
logmod <- glm(y ~ x, family=binomial)
hosmerlem(logmod, group = 10)
Hosmer-Lemeshow Test:
Chi-sq df pr(>chi)
binary(Hosmerlem) 4.5227 8 0.8072
H0: No lack of fit dictated
rho: 100%
I have a list for formulas I want to fit to data, rather than running a loop I'd like to do this at once, for performance's sake. The estimations should still be separate, I'm not trying to estimate a SUR or anything.
The following code does what I want
x <- matrix(rnorm(300),ncol=3)
y <- x %*% c(1,2,3)+rnorm(100)
formulae <-list(y~x[,1],
y~x[,2],
y~x[,1] + x[,2])
lapply(formulae,lm)
Unfortunately this gets somewhat slow as the length of formulae increases is there a way to truly vectorize this?
If it is any help, the only results of lm I care about are coefficients, and some standard errors.
As I said in my comment, what you really need is a more efficient yet stable fitting routine other than lm(). Here I would provide you a well tested one written myself, called lm.chol(). It takes a formula and data, and returns:
a coefficient summary table, as you normally see in summary(lm(...))$coef;
Pearson estimate of residual standard error, as you get from summary(lm(...))$sigma;
adjusted-R.squared, as you get from summary(lm(...))$adj.r.squared.
## linear model estimation based on pivoted Cholesky factorization with Jacobi preconditioner
lm.chol <- function(formula, data) {
## stage0: get response vector and model matrix
## we did not follow the normal route: match.call, model.frame, model.response, model matrix, etc
y <- data[[as.character(formula[[2]])]]
X <- model.matrix(formula, data)
n <- nrow(X); p <- ncol(X)
## stage 1: XtX and Jacobi diagonal preconditioner
XtX <- crossprod(X)
D <- 1 / sqrt(diag(XtX))
## stage 2: pivoted Cholesky factorization
R <- suppressWarnings(chol(t(D * t(D * XtX)), pivot = TRUE))
piv <- attr(R, "pivot")
r <- attr(R, "rank")
if (r < p) {
warning("Model is rank-deficient!")
piv <- piv[1:r]
R <- R[1:r, 1:r]
}
## stage 3: solve linear system for coefficients
D <- D[piv]
b <- D * crossprod(X, y)[piv]
z <- forwardsolve(t(R), b)
RSS <- sum(y * y) - sum(z * z)
sigma <- sqrt(RSS / (n - r))
para <- D * backsolve(R, z)
beta.hat <- rep(NA, p)
beta.hat[piv] <- para
## stage 4: get standard error
Rinv <- backsolve(R, diag(r))
se <- rep(NA, p)
se[piv] <- D * sqrt(rowSums(Rinv * Rinv)) * sigma
## stage 5: t-statistic and p-value
t.statistic <- beta.hat / se
p.value <- 2 * pt(-abs(t.statistic), df = n - r)
## stage 6: construct coefficient summary matrix
coefficients <- matrix(c(beta.hat, se, t.statistic, p.value), ncol = 4L)
colnames(coefficients) <- c("Estimate", "Std. Error", "t value", "Pr(>|t|)")
rownames(coefficients) <- colnames(X)
## stage 7: compute adjusted R.squared
adj.R2 <- 1 - sigma * sigma / var(y)
## return model fitting results
attr(coefficients, "sigma") <- sigma
attr(coefficients, "adj.R2") <- adj.R2
coefficients
}
Here I would offer three examples.
Example 1: full rank linear model
We take R's built-in dataset trees as an example.
# using `lm()`
summary(lm(Height ~ Girth + Volume, trees))
#Coefficients:
# Estimate Std. Error t value Pr(>|t|)
#(Intercept) 83.2958 9.0866 9.167 6.33e-10 ***
#Girth -1.8615 1.1567 -1.609 0.1188
#Volume 0.5756 0.2208 2.607 0.0145 *
#---
#Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#Residual standard error: 5.056 on 28 degrees of freedom
#Multiple R-squared: 0.4123, Adjusted R-squared: 0.3703
#F-statistic: 9.82 on 2 and 28 DF, p-value: 0.0005868
## using `lm.chol()`
lm.chol(Height ~ Girth + Volume, trees)
# Estimate Std. Error t value Pr(>|t|)
#(Intercept) 83.2957705 9.0865753 9.166905 6.333488e-10
#Girth -1.8615109 1.1566879 -1.609346 1.187591e-01
#Volume 0.5755946 0.2208225 2.606594 1.449097e-02
#attr(,"sigma")
#[1] 5.056318
#attr(,"adj.R2")
#[1] 0.3702869
The results are exactly the same!
Example 2: rank-deficient linear model
## toy data
set.seed(0)
dat <- data.frame(y = rnorm(100), x1 = runif(100), x2 = rbeta(100,3,5))
dat$x3 <- with(dat, (x1 + x2) / 2)
## using `lm()`
summary(lm(y ~ x1 + x2 + x3, dat))
#Coefficients: (1 not defined because of singularities)
# Estimate Std. Error t value Pr(>|t|)
#(Intercept) 0.2164 0.2530 0.856 0.394
#x1 -0.1526 0.3252 -0.469 0.640
#x2 -0.3534 0.5707 -0.619 0.537
#x3 NA NA NA NA
#Residual standard error: 0.8886 on 97 degrees of freedom
#Multiple R-squared: 0.0069, Adjusted R-squared: -0.01358
#F-statistic: 0.337 on 2 and 97 DF, p-value: 0.7147
## using `lm.chol()`
lm.chol(y ~ x1 + x2 + x3, dat)
# Estimate Std. Error t value Pr(>|t|)
#(Intercept) 0.2164455 0.2529576 0.8556595 0.3942949
#x1 NA NA NA NA
#x2 -0.2007894 0.6866871 -0.2924030 0.7706030
#x3 -0.3051760 0.6504256 -0.4691944 0.6399836
#attr(,"sigma")
#[1] 0.8886214
#attr(,"adj.R2")
#[1] -0.01357594
#Warning message:
#In lm.chol(y ~ x1 + x2 + x3, dat) : Model is rank-deficient!
Here, lm.chol() based on Cholesky factorization with complete pivoting and lm() based on QR factorization with partial pivoting have shrunk different coefficients to NA. But two estimation are equivalent, with the same fitted values and residuals.
Example 3: performance for large linear models
n <- 10000; p <- 300
set.seed(0)
dat <- as.data.frame(setNames(replicate(p, rnorm(n), simplify = FALSE), paste0("x",1:p)))
dat$y <- rnorm(n)
## using `lm()`
system.time(lm(y ~ ., dat))
# user system elapsed
# 3.212 0.096 3.315
## using `lm.chol()`
system.time(lm.chol(y ~ ., dat))
# user system elapsed
# 1.024 0.028 1.056
lm.chol() is 3 ~ 4 times faster than lm(). If you want to know the reason, read my this answer.
Remark
I have focused on improving performance on computational kernel. You can take one step further, by using Ben Bolker's parallelism suggestion. If my approach gives 3 times boost, and parallel computing gives 3 times boost on 4 cores, you end up with 9 times boost!
There's not really an easy way to vectorize this, but the pdredge function from the MuMIn package gives you a pretty easy way to parallelize it (this assumes you have multiple cores on your machine or that you can set up a local cluster in one of the ways supported by the parallel package ...
library(parallel)
clust <- makeCluster(2,"PSOCK")
library(MuMIn)
Construct data:
set.seed(101)
x <- matrix(rnorm(300),ncol=3)
y <- x %*% c(1,2,3)+rnorm(100)
It will be easier to do this with a named data frame rather than an anonymous matrix:
df <- setNames(data.frame(y,x),c("y",paste0("x",1:3)))
The cluster nodes all need access to the data set:
clusterExport(clust,"df")
Fit the full model (you could use y~. to fit all variables)
full <- lm(y~x1+x2,data=df,na.action=na.fail)
Now fit all submodels (see ?MuMIn::dredge for many more options to control which submodels are fitted)
p <- pdredge(full,cluster=clust)
coef(p)
## (Intercept) x1 x2
## 3 -0.003805107 0.7488708 2.590204
## 2 -0.028502039 NA 2.665305
## 1 -0.101434662 1.0490816 NA
## 0 -0.140451160 NA NA
I'm running a multivariate regression with 2 outcome variables and 5 predictors. I would like to obtain the confidence intervals for all regression coefficients. Usually I use the function lm but it doesn't seem to work for a multivariate regression model (object mlm).
Here's a reproducible example.
library(car)
mod <- lm(cbind(income, prestige) ~ education + women, data=Prestige)
confint(mod) # doesn't return anything.
Any alternative way to do it? (I could just use the value of the standard error and multiply by the right critical t value, but I was wondering if there was an easier way to do it).
confint won't return you anything, because there is no "mlm" method supported:
methods(confint)
#[1] confint.default confint.glm* confint.lm confint.nls*
As you said, we can just plus / minus some multiple of standard error to get upper / lower bound of confidence interval. You were probably going to do this via coef(summary(mod)), then use some *apply method to extract standard errors. But my answer to Obtain standard errors of regression coefficients for an “mlm” object returned by lm() gives you a supper efficient way to get standard errors without going through summary. Applying std_mlm to your example model gives:
se <- std_mlm(mod)
# income prestige
#(Intercept) 1162.299027 3.54212524
#education 103.731410 0.31612316
#women 8.921229 0.02718759
Now, we define another small function to compute lower and upper bound:
## add "mlm" method to generic function "confint"
confint.mlm <- function (model, level = 0.95) {
beta <- coef(model)
se <- std_mlm (model)
alpha <- qt((1 - level) / 2, df = model$df.residual)
list(lower = beta + alpha * se, upper = beta - alpha * se)
}
## call "confint"
confint(mod)
#$lower
# income prestige
#(Intercept) -3798.25140 -15.7825086
#education 739.05564 4.8005390
#women -81.75738 -0.1469923
#
#$upper
# income prestige
#(Intercept) 814.25546 -1.72581876
#education 1150.70689 6.05505285
#women -46.35407 -0.03910015
It is easy to interpret this. For example, for response income, the 95%-confidence interval for all variables are
#(intercept) (-3798.25140, 814.25546)
# education (739.05564, 1150.70689)
# women (-81.75738, -46.35407)
This comes from the predict.lm example. You want the interval = 'confidence' option.
x <- rnorm(15)
y <- x + rnorm(15)
predict(lm(y ~ x))
new <- data.frame(x = seq(-3, 3, 0.5))
predict(lm(y ~ x), new, se.fit = TRUE)
pred.w.clim <- predict(lm(y ~ x), new, interval = "confidence")
matplot(new$x, pred.w.clim,
lty = c(1,2,2,3,3), type = "l", ylab = "predicted y")
This seems to have been discussed recently (July 2018) on the R-devel list, so hopefully by the next version of R it will be fixed. A workaround proposed on that list is to use:
confint.mlm <- function (object, level = 0.95, ...) {
cf <- coef(object)
ncfs <- as.numeric(cf)
a <- (1 - level)/2
a <- c(a, 1 - a)
fac <- qt(a, object$df.residual)
pct <- stats:::format.perc(a, 3)
ses <- sqrt(diag(vcov(object)))
ci <- ncfs + ses %o% fac
setNames(data.frame(ci),pct)
}
Test:
fit_mlm <- lm(cbind(mpg, disp) ~ wt, mtcars)
confint(fit_mlm)
Gives:
2.5 % 97.5 %
mpg:(Intercept) 33.450500 41.119753
mpg:wt -6.486308 -4.202635
disp:(Intercept) -204.091436 -58.205395
disp:wt 90.757897 134.198380
Personnally, I like it in a clean tibble way (using broom::tidy would be even better, but has an issue currently)
library(tidyverse)
confint(fit_mlm) %>%
rownames_to_column() %>%
separate(rowname, c("response", "term"), sep=":")
Gives:
response term 2.5 % 97.5 %
1 mpg (Intercept) 33.450500 41.119753
2 mpg wt -6.486308 -4.202635
3 disp (Intercept) -204.091436 -58.205395
4 disp wt 90.757897 134.198380
Consider the code:
x <- read.table("http://data.princeton.edu/wws509/datasets/cuse.dat",
header=TRUE)[,1:2]
fit <- glm(education ~ age, family="binomial", data=x)
summary(fit)
Where age has 4 levels: "<25" "25-29" "30-39" "40-49"
The results are:
So by default, one of the levels is used as a reference level. Is there a way to have glm output coefficients for all 4 levels + the intercept (i.e. have no reference level)? Software packages like SAS do this by default, so I was wondering if there was any option for this.
Thanks!
See ?formula, specifically, the meaning of including + 0 in your model specification...
# Sample data - explanatory variable (continuous)
x <- runif( 100 )
# explanatory data, factor with 3 levels
f <- as.factor( sample( 3 , 100 , TRUE ) )
# outcome data
y <- runif( 100 ) + rnorm(100) + rnorm( 100 , mean = c(1,3,6) )
# model without intercept
summary( glm( y ~ x + f + 0 ) )
#Call:
#glm(formula = y ~ x + f + 0)
#Deviance Residuals:
# Min 1Q Median 3Q Max
#-5.7316 -1.8923 0.0195 1.8918 5.9520
#Coefficients:
# Estimate Std. Error t value Pr(>|t|)
#x 0.3216 0.9772 0.329 0.743
#f1 3.4493 0.6823 5.055 2.06e-06 ***
#f2 3.6349 0.6959 5.223 1.02e-06 ***
#f3 3.1962 0.6598 4.844 4.87e-06 ***
You'll want to use the model.matrix function to convert the factors in the age variable to binary variables.
See this answer.
EDIT:
Here is an example:
x <- read.table("http://data.princeton.edu/wws509/datasets/cuse.dat",
header=TRUE)[,1:2]
binary_variables <- model.matrix(~ x$age -1, x)
fit <- glm(x$education ~ binary_variables, family="binomial")
summary(fit)