nls: Loop and break in a decided number of iterations - r

I've like two make to sequential operations:
1) Ajusted two nls models in a subset; and
2) Loop the models just a number of iteracions =1.
For the first step I make:
#Packages
library(minpack.lm)
# Data set - Diameter in function of Feature and Age
Feature<-sort(rep(c("A","B"),22))
Age<-c(60,72,88,96,27,
36,48,60,72,88,96,27,36,48,60,72,
88,96,27,36,48,60,27,27,36,48,60,
72,88,96,27,36,48,60,72,88,96,27,
36,48,60,72,88,96)
Diameter<-c(13.9,16.2,
19.1,19.3,4.7,6.7,9.6,11.2,13.1,15.3,
15.4,5.4,7,9.9,11.7,13.4,16.1,16.2,
5.9,8.3,12.3,14.5,2.3,5.2,6.2,8.6,9.3,
11.3,15.1,15.5,5,7,7.9,8.4,10.5,14,14,
4.1,4.9,6,6.7,7.7,8,8.2)
d<-dados <- data.frame(Feature,Age,Diameter)
str(d)
#Create a nls model (Levenberg-Marquardt algoritm) for each Feature (A abd B)
e1<- Diameter ~ a1 * Age^a2
Fecture_vec<-unique(d$Feature)
mod_ND <- list() #List for save each model
for(i in 1:length(Fecture_vec)){
d2 <- subset(d, d$Feature == Fecture_vec[i])
mod_ND[[i]] <- nlsLM(e1, data = d2,
start = list(a1 = 0.1, a2 = 10),
control = nls.control(maxiter = 1000))
print(summary(mod_ND[[i]]))
}
#
Here, so far so good, but if I try to make a loop with 999 simulation and recycle the start values with coef(mod_ND[[i]])[1] and coef(mod_ND[[i]])[2] and stop when number of iterations is 1:
e1<- Diameter ~ a1 * Age^a2
Fecture_vec<-unique(d$Feature)
mod_ND <- list() #List for save each model
for(i in 1:length(Fecture_vec)){
d2 <- subset(d, d$Feature == Fecture_vec[i])
mod_ND[[i]] <- nlsLM(e1, data = d2,
start = list(a1 = 0.1, a2 = 10),
control = nls.control(maxiter = 1000))
Xs<-data.frame()
for(z in 1:999){
d2 <- subset(d, d$Feature == Fecture_vec[i])
mod_ND[[z]] <- nlsLM(e1, data = d2,
start = list(a1 = coef(mod_ND[[i]])[1], a2 = mod_ND[[i]])[2]),
control = nls.control(maxiter = 1000))
if (mod_ND[[z,c(finIter")]] <= 1){ break } ## Stop when iteractions =1
print(summary(mod_ND[[z]]))
}
}
#
Doesn't work!! Please any ideas?

#Packages
library(minpack.lm)
library(dplyr)
m<-function(d, a=0.01,b=10){
mod<- nlsLM(Diameter ~ a1 * Age^a2,start = list(a1 = a, a2 = b),control = nls.control(maxiter = 1000), data = d)
par1<- summary(mod)$coefficients[[1]]
par2 <- summary(mod)$coefficients[[2]]
print(summary(mod))
if(mod$convInfo[["finIter"]]>1){
m(d,par1,par2)
}else{
print(" --------Feature B-----------")
}
}
list_models <- dlply(d,.(Feature),m)
list_models

Related

How can I use try catch for nls function in R

I am doing a regression for a Quadric Linear function. I got two option is to use either nlsLM and nls2. However, for some dataset, the use of nlsLM casing some problem such as: singular gradient matrix at initial parameter estimates or they ran in to an infinitie loop. I want to use the try catch to deal with this issue. Can anyone help me out? Thanks everyone in advance.
Here is the full code:
# Packages needed for estimaton of Ideal trajectory - nonlinear regression
#-------------------------------------------------------------------------------
library("minpack.lm")
library("nlstools")
library("nlsMicrobio")
library("stats")
library("tseries") #runs test for auto correlation
#Use NLS2
library(proto)
library(nls2)
################################################################
# Set working directory
setwd("C:/Users/Kevin Le/PycharmProjects/Pig Data Black Box - Copy")
#load dataset
load("Data/JRPData_TTC.Rdata") #load dataset created in MissingData.step
ID <- 5470
#Create a new dataframe which will store Data after ITC estimation
#Dataframe contains ITC parameters
ITC.param.pos2 <- data.frame(ANIMAL_ID=factor(),
X0=double(),
Y1=double(),
Y2=double(),
Ylast=double(),
a=double(),
b=double(),
c=double(),
d=double(),
stringsAsFactors=FALSE)
#Dataframe contains data points on the ITC
Data.remain <- data.frame(ANIMAL_ID=character(),
Age=double(),
obs.CFI=double(),
tt=double(),
ttt=double(),
stringsAsFactors=FALSE)
#===============================================================
# For loop for automatically estimating ITC of all pigs
#===============================================================
IDC <- seq_along(ID) # 17, 23, 52, 57, 116
for (idc in IDC){
# idc = 1
i <- ID[idc]
Data <- No.NA.Data.1[No.NA.Data.1$ANIMAL_ID == i,]
idc1 <- unique(as.numeric(Data$idc.1))
####### Create data frame of x (Age) and y (CFI) ########
x <- as.numeric(Data$Age.plot)
Y <- as.numeric(Data$CFI.plot)
Z <- as.numeric(Data$DFI.plot)
Data.xy <- as.data.frame(cbind(x,Y))
#Initial parameteres for parameter estimation
X0.0 <- x[1]
Xlast <- x[length(x)]
##################################################################
# 1. reparametrization CFI at X0 = 0
#function used for reparametrization in MAPLE
# solve({
# 0=a+b*X_0+c*X_0**2,
# DFIs=b+2*c*Xs,CFIs=a+b*Xs+c*Xs**2},
# {a,b,c});
# a = -X0*(2*CFIs*Xs-CFIs*X0-Xs^2*DFIs+Xs*DFIs*X0)/(Xs^2-2*X0*Xs+X0^2)
# b = (-Xs^2*DFIs+DFIs*X0^2+2*CFIs*Xs)/(Xs^2-2*X0*Xs+X0^2)
# c = -(CFIs-Xs*DFIs+X0*DFIs)/(Xs^2-2*X0*Xs+X0^2)
# 2. with the source of the function abcd and pred
##################################################################
#Provide set of initial parameters
Xs.1 <- round(seq(X0.0 + 1, Xlast - 1, len = 30), digits = 0)
X0.1 <- rep(X0.0, length(Xs.1))
DFIs.1 <- NULL
CFIs.1 <- NULL
for(A in seq_along(Xs.1)){
DFIs2 <- Data[Data$Age.plot == Xs.1[A],]$DFI.plot
CFIs2 <- Data[Data$Age.plot == Xs.1[A],]$CFI.plot
DFIs.1 <- c(DFIs.1, DFIs2)
CFIs.1 <- c(CFIs.1, CFIs2)
}
st1 <- data.frame(cbind(X0.1, Xs.1, DFIs.1, CFIs.1))
names(st1) <- c("X0","Xs", "DFIs","CFIs")
#RUN NLS2 to find optimal initial parameters
st2 <- nls2(Y ~ nls.func.2(X0, Xs, DFIs, CFIs),
Data.xy,
start = st1,
# weights = weight,
# trace = T,
algorithm = "brute-force")
par_init <- coef(st2); par_init
#--------------------------------------------
# Create empty lists to store data after loop
#--------------------------------------------
par <- list()
AC.res <- list()
AC.pvalue <- NULL
data2 <- list()
data3 <- list()
param <- data.frame(rbind(par_init))
par.abcd <- data.frame(rbind(abcd.2(as.vector(par_init))))
param.2 <- data.frame(X0=double(),
Xs=double(),
DFIs=double(),
CFIs=double(),
a=double(),
b=double(),
c=double(),
stringsAsFactors=FALSE)
j <- 2
AC_pvalue <- 0
AC.pvalue[1] <- AC_pvalue
datapointsleft <- as.numeric(dim(Data)[1])
dpl <- datapointsleft #vector of all dataponitsleft at each step
#-------------------------------------------------------------------------------
# Start the procedure of Non Linear Regression
#-------------------------------------------------------------------------------
while ((AC_pvalue<=0.05) && datapointsleft >= 20){
weight <- 1/Y^2
# ---------------- NON linear reg applied to log(Y) ---------------------------------
st2 <- nls2(Y ~ nls.func.2(X0, Xs, DFIs, CFIs),
Data.xy,
start = st1,
weights = weight,
trace = F,
algorithm = "brute-force")
par_init <- coef(st2)
par_init
# st1 <- st1[!(st1$Xs == par_init[2]),]
nls.CFI <- nlsLM(Y ~ nls.func.2(X0, Xs, DFIs, CFIs),
Data.xy,
control = list(tol = 1e-2, printEval = TRUE, maxiter = 1024),
start = list(X0 = par_init[1], Xs = par_init[2],
DFIs = par_init[3], CFIs = par_init[4]),
weights = weight,
algorithm = "port",
lower = c(-10000,X0.0+1, -10000, -10000),
upper = c(10000, Xlast-1, 10000, 10000),
trace = F)
# nls.CFI <- nls2(Y ~ nls.func.2(X0, Xs, DFIs, CFIs),
# Data.xy,
# start = list(X0 = par_init[1], Xs = par_init[2],
# DFIs = par_init[3], CFIs = par_init[4]),
# weights = weight,
# control = nls.control(warnOnly = TRUE),
# trace = T,
# algorithm = "port",
# lower = c(-100000000,X0.0+1, -1000000000, -1000000000),
# upper = c(1000000000, Xlast-1, 1000000000, 1000000000))
# nls.CFI <- nlsLM(Y ~ nls.func.2(X0, Xs, DFIs, CFIs),
# Data.xy,
# control = nls.control(warnOnly = TRUE),
# start = list(X0 = par_init[1], Xs = par_init[2],
# DFIs = par_init[3], CFIs = par_init[4]),
# weights = weight,
# algorithm = "port",
# lower = c(-1000000000,X0.0+1, -1000000000, -1000000000),
# upper = c(1000000000, Xlast-1, 1000000000, 1000000000),
# trace = F)
#--------RESULTS analysis GOODNESS of fit
#estimate params
par[[j]] <- coef(nls.CFI)
par.abcd[j,] <- abcd.2(as.vector(coef(nls.CFI) )) #calculation of a, b, c and d
param[j,] <- par[[j]]
param.2[j-1,] <- cbind(param[j,], par.abcd[j,])
#summary
# summ = overview((nls.CFI)) #summary
#residuals
res1 <- nlsResiduals(nls.CFI) #residuals
res2 <- nlsResiduals(nls.CFI)$resi1
res <- res2[, 2]
AC.res <- test.nlsResiduals(res1)
AC.pvalue[j] <- AC.res$p.value
#---------Check for negative residuals----------
#Add filtration step order to data
Step <- rep(j - 1, length(x))
#create a new dataset with predicted CFI included
Data.new <- data.frame(cbind(x, Z, Y, pred.func.2(par[[j]],x)[[1]], res, Step))
names(Data.new) <- c("Age", "Observed_DFI","Observed_CFI", "Predicted_CFI", "Residual", "Step")
# plot(Data.new$Age, Data.new$Predicted_CFI, type = "l", col = "black",lwd = 2,
# ylim = c(0, max(Data.new$Predicted_CFI, Data.new$Observed_CFI)))
# lines(Data.new$Age, Data.new$Observed_CFI, type = "p", cex = 1.5)
#
#remove negative res
Data.pos <- Data.new[!Data.new$Residual<0,]
# lines(Data.pos$Age, Data.pos$Predicted_CFI, type = "l", col = j-1, lwd = 2)
# lines(Data.pos$Age, Data.pos$Observed_CFI, type = "p", col = j, cex = 1.5)
#restart
#Criteria to stop the loop when the estimated parameters are equal to initial parameters
# Crite <- sum(param.2[dim(param.2)[1],c(1:4)] == par_init)
datapointsleft <- as.numeric(dim(Data.pos)[1])
par_init <- par[[j]]
AC_pvalue <- AC.pvalue[j]
j <- j+1
x <- Data.pos$Age
Y <- Data.pos$Observed_CFI
Z <- Data.pos$Observed_DFI
Data.xy <- as.data.frame(cbind(x,Y))
dpl <- c(dpl, datapointsleft)
dpl
#Create again the grid
X0.0 <- x[1]
Xlast <- x[length(x)]
#Xs
if(par_init[2] -15 <= X0.0){
Xs.1 <- round(seq(X0.0 + 5, Xlast - 5, len = 30), digits = 0)
} else if(par_init[2] + 5 >= Xlast){
Xs.1 <- round(seq(par_init[2]-10, par_init[2]-1, len = 6), digits = 0)
} else{
Xs.1 <- round(seq(par_init[2]-5, par_init[2] + 5, len = 6), digits = 0)
}
#
X0.1 <- rep(X0.0, length(Xs.1))
DFIs.1 <- NULL
CFIs.1 <- NULL
for(A in seq_along(Xs.1)){
DFIs2 <- Data[Data$Age.plot == Xs.1[A],]$DFI.plot
CFIs2 <- Data[Data$Age.plot == Xs.1[A],]$CFI.plot
DFIs.1 <- c(DFIs.1, DFIs2)
CFIs.1 <- c(CFIs.1, CFIs2)
}
st1 <- data.frame(cbind(X0.1, Xs.1, DFIs.1, CFIs.1))
if(X0.0 <= par_init[2] && Xlast >=par_init[2]){
st1 <- rbind(st1, par_init)
}
names(st1) <- c("X0","Xs", "DFIs","CFIs")
}
} # end FOR loop
Here is the data file. I have exported my data into the .Rdata for an easier import.: https://drive.google.com/file/d/1GVMarNKWMEyz-noSp1dhzKQNtu2uPS3R/view?usp=sharing
In this file, the set id: 5470 will have this error: singular gradient matrix at initial parameter estimates in this part:
nls.CFI <- nlsLM(Y ~ nls.func.2(X0, Xs, DFIs, CFIs),
Data.xy,
control = list(tol = 1e-2, printEval = TRUE, maxiter = 1024),
start = list(X0 = par_init[1], Xs = par_init[2],
DFIs = par_init[3], CFIs = par_init[4]),
weights = weight,
algorithm = "port",
lower = c(-10000,X0.0+1, -10000, -10000),
upper = c(10000, Xlast-1, 10000, 10000),
trace = F)
The complementary functions (file Function.R):
abcd.2 <- function(P){
X0 <- P[1]
Xs <- P[2]
DFIs <- P[3]
CFIs <- P[4]
a <- -X0*(2*CFIs*Xs-CFIs*X0-Xs^2*DFIs+Xs*DFIs*X0)/(Xs^2-2*X0*Xs+X0^2)
b <- (-Xs^2*DFIs+DFIs*X0^2+2*CFIs*Xs)/(Xs^2-2*X0*Xs+X0^2)
c <- -(CFIs-Xs*DFIs+X0*DFIs)/(Xs^2-2*X0*Xs+X0^2)
pp <- as.vector(c(a, b, c))
return(pp)
}
#--------------------------------------------------------------
# NLS function
#--------------------------------------------------------------
nls.func.2 <- function(X0, Xs, DFIs, CFIs){
pp <- c(X0, Xs, DFIs, CFIs)
#calculation of a, b and c using these new parameters
c <- abcd.2(pp)[3]
b <- abcd.2(pp)[2]
a <- abcd.2(pp)[1]
ind1 <- as.numeric(x < Xs)
return (ind1*(a+b*x+c*x^2)+(1-ind1)*((a+b*(Xs)+c*(Xs)^2)+(b+2*c*(Xs))*(x-(Xs))))
}
#--------------------------------------------------------------
# Fit new parameters to a quadratic-linear function of CFI
#--------------------------------------------------------------
pred.func.2 <- function(pr,age){
#
X0 <- pr[1]
Xs <- pr[2]
DFIs <- pr[3]
CFIs <- pr[4]
#
x <- age
#calculation of a, b and c using these new parameters
c <- abcd.2(pr)[3]
b <- abcd.2(pr)[2]
a <- abcd.2(pr)[1]
#
ind1 <- as.numeric(x < Xs)
#
results <- list()
cfi <- ind1*(a+b*x+c*x^2)+(1-ind1)*((a+b*(Xs)+c*(Xs)^2)+(b+2*c*(Xs))*(x-(Xs))) #CFI
dfi <- ind1*(b+2*c*x) + (1 - ind1)*(b+2*c*(Xs)) #DFI
results[[1]] <- cfi
results[[2]] <- dfi
return (results)
}
#---------------------------------------------------------------------------------------------------------------
# Quadratic-linear function of CFI curve and its 1st derivative (DFI) with original parameters (only a, b and c)
#---------------------------------------------------------------------------------------------------------------
pred.abcd.2 <- function(pr,age){
#
a <- pr[1]
b <- pr[2]
c <- pr[3]
x <- age
#calculation of a, b and c using these new parameters
#
ind1 <- as.numeric(x < Xs)
#
results <- list()
cfi <- ind1*(a+b*x+c*x^2)+(1-ind1)*((a+b*(Xs)+c*(Xs)^2)+(b+2*c*(Xs))*(x-(Xs))) #CFI
dfi <- ind1*(b+2*c*x) + (1 - ind1)*(b+2*c*(Xs)) #DFI
results[[1]] <- cfi
results[[2]] <- dfi
return (results)
}
Updated: I did review my logic from the previous step and found that my data is a bit messed up because of it. I have fixed it. The case where a set f data ran into an infinite loop has no longer exists, but this error is still there however: singular gradient matrix at initial parameter estimates.

how to organize the output of MLE using R

I wrote down this function for MLE estimation and then I apply it for different settings of parameters.
Finally, I bind all results for an output.
But is not working i have problem with the output and also I need to organize the output like the attached image using R program.
enter image description here
could some one help me please?
What should I fix and how can I print the results like the picture attached.
thank you in advance
rbssn<- function(n,alpha,beta)
{
if(!is.numeric(n)||!is.numeric(alpha)||!is.numeric(beta))
{stop("non-numeric argument to mathematical function")}
if(alpha<=0){ stop("alpha must be positive")}
if(beta<=0) { stop("beta must be positive") }
z <- rnorm(n,0,1)
r <- beta*((alpha*z*0.5)+sqrt((alpha*z*0.5)^2+1))^2
return(r)
}
#Function
mymle <- function(n,alpha,beta,rep)
{
theta=c(alpha,beta) # store starting values
#Tables
LHE=array(0, c(2,rep));
rownames(LHE)= c("MLE_alpha", "MLE_beta")
#Bias
bias= array(0, c(2,rep));
rownames(bias)= c("bias_alpha", "bias_beta")
#Simulation
set.seed(1)
#Loop
for(i in 1:rep){
myx <- exp(-rbssn(n, alpha, beta))
Score <- function(x) {
y <- numeric(2)
y[1] <- (-n/x[1])*(1+2/(x[1]^2)) - (1/(x[2]*x[1]^3))*sum(log(myx)) - (x[2]/(x[1]^3))*sum(1/log(myx))
y[2] <- -(n/(2*x[2])) + sum((1/(x[2]-log(myx)))) - (1/(2*(x[1]^2)*(x[2]^2)))*sum(log(myx)) + (1/(2*x[1]^2))*sum(1/(log(myx)))
y
}
Sin <- c(alpha,beta)
mle<- nleqslv(Sin, Score, control=list(btol=.01))[1]
LHE[i,]= mle
bias[i,]= c(mle[1]-theta[1], mle[2]-theta[2])
}
# end for i
#Format results
L <-round(apply(LHE, 1, mean), 3) # MLE of all the applied iterations
bs <-round(apply(bias,1, mean),3) # bias of all the applied iterations
row<- c(L, bs)
#Format a label
lab <- paste0('n= ',n,';',' alpha= ',alpha,';',' beta= ',beta)
row2 <- c(lab,row)
row2 <- as.data.frame(t(row2))
return(row2)
}
#Bind all
#Example 1
ex1 <- mymle(n = 20,alpha = 1,beta = 0.5,rep = 100)
ex2 <- mymle(n = 50,alpha = 2,beta = 0.5,rep = 100)
ex3 <- mymle(n = 100,alpha = 3,beta = 0.5,rep = 100)
#Example 2
ex4 <- mymle(n = 20,alpha = 0.5,beta = 0.5,rep = 100)
ex5 <- mymle(n = 50,alpha = 0.5,beta = 1,rep = 100)
ex6 <- mymle(n = 100,alpha = 0.5,beta = 1,rep = 100)
df <- rbind(ex1,ex2,ex3,ex4,ex5,ex6)
Any help will be appreciated.

Optimising nested for loops in R

I tried to speed the below code but without any success.
I read about Rfast package but I also fail in implementing that package.
Is there any way to optimise the following code in R?
RI<-function(y,x,a,mu,R=500,t=500){
x <- as.matrix(x)
dm <- dim(x)
n <- dm[1]
bias1 <- bias2 <- bias3 <- numeric(t)
b1 <- b2<- b3 <- numeric(R)
### Outliers in Y ######
for (j in 1:t) {
for (i in 1:R) {
id <- sample(n, a * n)
z <- y
z[id] <- rnorm(id, mu)
b1[i] <- var(coef(lm(z ~., data = as.data.frame(x))))
b2[i] <- var(coef(rlm(z ~ ., data = data.frame(x), maxit = 2000, method = "MM")))
b3[i] <- var(coef(rlm(z ~ ., data = data.frame(x), psi = psi.huber,maxit = 300)))
}
bias1[j] <- sum(b1) ; bias2[j] <- sum(b2); bias3[j] <- sum(b3)
}
bias <- cbind("lm" = bias1,"MM-rlm" = bias2, "H-rlm" = bias3)
colMeans(bias)
}
#######################################
p <- 5
n <- 200
x<- matrix(rnorm(n * p), ncol = p)
y<-rnorm(n)
a=0.2
mu <-10
#######################################
RI(y,x,a,mu)

Convert for loops into foreach loops

I want to make the code below more efficient by using the foreach package. I tried it for a very long time but I don't manage to get the same result as when using the for-loops. I would like to use a nested foreach-loop including parallelization... And as output I would like to have two matrices with dim [R,b1] I would be very grateful for some suggestions!!
n <- c(100, 300, 500)
R <- 100
b0 <- 110
b1 <- seq(0.01, 0.1, length.out = 100)
## all combinations of n and b1
grid <- expand.grid(n, b1)
names(grid) <- c("n", "b1")
calcPower <- function( R, b0, grid) {
cl <- makeCluster(3)
registerDoParallel(cl)
## n and b1 coefficients
n <- grid$n
b1 <- grid$b1
## ensures reproducibility
set.seed(2020)
x <- runif(n, 18, 80)
x.dich <- factor( ifelse( x < median( x), 0, 1))
## enables to store two outputs
solution <- list()
## .options.RNG ensures reproducibility
res <- foreach(i = 1:R, .combine = rbind, .inorder = TRUE, .options.RNG = 666) %dorng% {
p.val <- list()
p.val.d <- list()
for( j in seq_along(b1)) {
y <- b0 + b1[j] * x + rnorm(n, 0, sd = 10)
mod.lm <- lm( y ~ x)
mod.lm.d <- lm( y ~ x.dich)
p.val <- c( p.val, ifelse( summary(mod.lm)$coef[2,4] <= 0.05, 1, 0))
p.val.d <- c( p.val.d, ifelse( summary(mod.lm.d)$coef[2,4] <= 0.05, 1, 0))
}
solution[[1]] <- p.val
solution[[2]] <- p.val.d
return(solution)
}
dp.val <- matrix( unlist(res[,1], use.names = FALSE), R, length(b1), byrow = TRUE)
dp.val.d <- matrix( unlist(res[,2], use.names = FALSE), R, length(b1), byrow = TRUE)
stopCluster(cl)
df <- data.frame(
effectS = b1,
power = apply( dp.val, 2, function(x){ mean(x) * 100}),
power.d = apply( dp.val.d, 2, function(x){ mean(x) * 100}),
n = factor(n))
return(df)
}
## simulation for different n
tmp <- with(grid,
by( grid, n,
calcPower, R = R, b0 = b0))
## combines the 3 results
df.power <- rbind(tmp[[1]], tmp[[2]], tmp[[3]])
I created a foreach loop in following code. There had to be some changes made. It is a lot easier to return a list then a matrix in foreach, since it's combined with rbind. Especially when you want to return multiple ones. My solution here is to save everything in a list and afterwards transform it into a matrix of length 100.
Note: there is one mistake in your code. summary( mod.lm.d)$coef[2,4] does not exist. I changed it to [2]. Adjust to your needing
solution <- list()
df2<-foreach(i = 1:R, .combine = rbind, .inorder=TRUE) %dopar%{
set.seed(i)
p.val <- list()
p.val.d <- list()
counter <- list()
for( j in seq_along(b1)){
x <- sort( runif(n, 18, 80))
x.dich <- factor( ifelse( x < median(x), 0, 1))
y <- b0 + b1[j] * x + rnorm( n, 0, sd = 10)
mod.lm <- lm( y ~ x)
mod.lm.d <- lm( y ~ x.dich)
p.val <- c(p.val, ifelse( summary( mod.lm)$coef[2] <= 0.05, 1, 0))
p.val.d <- c(p.val.d, ifelse( summary( mod.lm.d)$coef[2] <= 0.05, 1, 0))
counter <- c(counter, j)
}
solution[[1]] <- p.val
solution[[2]] <- p.val.d
solution[[3]] <- counter
return(solution)
}
dp.val <- unlist(df2[,1], use.names = FALSE)
dp.val.d <- unlist(df2[,2], use.names = FALSE)
dp.val.matr <- matrix(dp.val, R, length(b1))
dp.val.d.matr <- matrix(dp.val.d, R, length(b1))
stopCluster(cl)
for your comment:
A foreach does work with a normal for loop. Minimal reproducible example:
df<-foreach(i = 1:R, .combine = cbind, .inorder=TRUE) %dopar%{
x <- list()
for(j in 1:3){
x <- c(x,j)
}
return(x)
}

Adapting the meansd moderator option in sjPlot interaction

I am using sjPlot, the sjp.int function, to plot an interaction of an lme.
The options for the moderator values are means +/- sd, quartiles, all, max/min. Is there a way to plot the mean +/- 2sd?
Typically it would be like this:
model <- lme(outcome ~ var1+var2*time, random=~1|ID, data=mydata, na.action="na.omit")
sjp.int(model, show.ci=T, mdrt.values="meansd")
Many thanks
Reproducible example:
#create data
mydata <- data.frame( SID=sample(1:150,400,replace=TRUE),age=sample(50:70,400,replace=TRUE), sex=sample(c("Male","Female"),200, replace=TRUE),time= seq(0.7, 6.2, length.out=400), Vol =rnorm(400),HCD =rnorm(400))
mydata$time <- as.numeric(mydata$time)
#insert random NAs
NAins <- NAinsert <- function(df, prop = .1){
n <- nrow(df)
m <- ncol(df)
num.to.na <- ceiling(prop*n*m)
id <- sample(0:(m*n-1), num.to.na, replace = FALSE)
rows <- id %/% m + 1
cols <- id %% m + 1
sapply(seq(num.to.na), function(x){
df[rows[x], cols[x]] <<- NA
}
)
return(df)
}
mydata2 <- NAins(mydata,0.1)
#run the lme which gives error message
model = lme(Vol ~ age+sex*time+time* HCD, random=~time|SID,na.action="na.omit",data=mydata2);summary(model)
mydf <- ggpredict(model, terms=c("time","HCD [-2.5, -0.5, 2.0]"))
#lmer works
model2 = lmer(Vol ~ age+sex*time+time* HCD+(time|SID),control=lmerControl(check.nobs.vs.nlev = "ignore",check.nobs.vs.rankZ = "ignore", check.nobs.vs.nRE="ignore"), na.action="na.omit",data=mydata2);summary(model)
mydf <- ggpredict(model2, terms=c("time","HCD [-2.5, -0.5, 2.0]"))
#plotting gives problems (jittered lines)
plot(mydf)
With sjPlot, it's currently not possible. However, I have written a package especially dedicated to compute and plot marginal effects: ggeffects. This package is a bit more flexible (for marginal effects plots).
In the ggeffects-package, there's a ggpredict()-function, where you can compute marginal effects at specific values. Once you know the sd of your model term in question, you can specify these values in the function call to plot your interaction:
library(ggeffects)
# plot interaction for time and var2, for values
# 10, 30 and 50 of var2
mydf <- ggpredict(model, terms = c("time", "var2 [10,30,50]"))
plot(mydf)
There are some examples in the package-vignette, see especially this section.
Edit
Here are the results, based on your reproducible example (note that GitHub-Version is currently required!):
# requires at least the GitHub-Versiob 0.1.0.9000!
library(ggeffects)
library(nlme)
library(lme4)
library(glmmTMB)
#create data
mydata <-
data.frame(
SID = sample(1:150, 400, replace = TRUE),
age = sample(50:70, 400, replace = TRUE),
sex = sample(c("Male", "Female"), 200, replace = TRUE),
time = seq(0.7, 6.2, length.out = 400),
Vol = rnorm(400),
HCD = rnorm(400)
)
mydata$time <- as.numeric(mydata$time)
#insert random NAs
NAins <- NAinsert <- function(df, prop = .1) {
n <- nrow(df)
m <- ncol(df)
num.to.na <- ceiling(prop * n * m)
id <- sample(0:(m * n - 1), num.to.na, replace = FALSE)
rows <- id %/% m + 1
cols <- id %% m + 1
sapply(seq(num.to.na), function(x) {
df[rows[x], cols[x]] <<- NA
})
return(df)
}
mydata2 <- NAins(mydata, 0.1)
# run the lme, works now
model = lme(
Vol ~ age + sex * time + time * HCD,
random = ~ time |
SID,
na.action = "na.omit",
data = mydata2
)
summary(model)
mydf <- ggpredict(model, terms = c("time", "HCD [-2.5, -0.5, 2.0]"))
plot(mydf)
lme-plot
# lmer also works
model2 <- lmer(
Vol ~ age + sex * time + time * HCD + (time |
SID),
control = lmerControl(
check.nobs.vs.nlev = "ignore",
check.nobs.vs.rankZ = "ignore",
check.nobs.vs.nRE = "ignore"
),
na.action = "na.omit",
data = mydata2
)
summary(model)
mydf <- ggpredict(model2, terms = c("time", "HCD [-2.5, -0.5, 2.0]"), ci.lvl = NA)
# plotting works, but only w/o CI
plot(mydf)
lmer-plot
# lmer also works
model3 <- glmmTMB(
Vol ~ age + sex * time + time * HCD + (time | SID),
data = mydata2
)
summary(model)
mydf <- ggpredict(model3, terms = c("time", "HCD [-2.5, -0.5, 2.0]"))
plot(mydf)
plot(mydf, facets = T)
glmmTMB-plots

Resources