Related
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.
I'm fitting linear models with MatrixModels:::lm.fit.sparse and MatrixModels::glm4 (also sparse).
However, these functions return coeff, residuals and fitted.values only.
What's the fastest and easiest way to get/calculate another values such as stderr, t-value, p-value, predict value?
I use the data from MatrixModels:::lm.fit.sparse example.
I built a custom function summary_sparse to perform a summary for this model.
All matrix operations are performed with Matrix package.
Results are compared with dense type model.
Note lm.fit.sparse have to be evaluated with method = "chol" to get proper results.
Functions:
summary_sparse <- function(l, X) {
XXinv <- Matrix::chol2inv(Matrix::chol(Matrix::crossprod(X)))
se <- sqrt(Matrix::diag(XXinv*sum(l$residuals**2)/(nrow(X)-ncol(X))))
ts <- l$coef/se
pvals <- 2*c(1 - pnorm(abs(ts)))
list(coef = l$coef, se = se, t = ts, p = pvals)
}
predict_sparse <- function(X, coef) {
X %*% coef
}
Application:
dd <- expand.grid(a = as.factor(1:3),
b = as.factor(1:4),
c = as.factor(1:2),
d= as.factor(1:8))
n <- nrow(dd <- dd[rep(seq_len(nrow(dd)), each = 10), ])
set.seed(17)
dM <- cbind(dd, x = round(rnorm(n), 1))
## randomly drop some
n <- nrow(dM <- dM[- sample(n, 50),])
dM <- within(dM, { A <- c(2,5,10)[a]
B <- c(-10,-1, 3:4)[b]
C <- c(-8,8)[c]
D <- c(10*(-5:-2), 20*c(0, 3:5))[d]
Y <- A + B + A*B + C + D + A*D + C*x + rnorm(n)/10
wts <- sample(1:10, n, replace=TRUE)
rm(A,B,C,D)
})
X <- Matrix::sparse.model.matrix( ~ (a+b+c+d)^2 + c*x, data = dM)
Xd <- as(X,"matrix")
fmDense <- lm(dM[,"Y"]~Xd-1)
ss <- summary(fmDense)
r1 <- MatrixModels:::lm.fit.sparse(X, y = dM[,"Y"], method = "chol")
f <- summary_sparse(r1, X)
all.equal(do.call(cbind, f), ss$coefficients, check.attributes = F)
#TRUE
all.equal(predict_sparse(X, r1$coef)#x, predict(fmDense), check.attributes = F, check.names=F)
#TRUE
I have written the following code.
library(quantreg)
# return the g function:
G = function(m, N, gamma) {
Tm = m * N
k = 1:Tm
Gvalue = sqrt(m) * (1 + k/m) * (k/(m + k))^gamma
return(Gvalue)
}
sqroot <- function(A) {
e = eigen(A)
v = e$vectors
val = e$values
sq = v %*% diag(sqrt(val)) %*% solve(v)
return(t(sq))
}
fa = function(m, N, a) {
Tm = m * N
k = 1:Tm
t = (m + k)/m
f_value = (t - 1) * t * (a^2 + log(t/(t - 1)))
return(sqrt(f_value))
}
m = 50
N = 2
n= 50*3
x1 = matrix(runif(n, 0, 1), ncol = 1)
x = cbind(1, x1)
beta = c(1, 1)
xb = x %*% beta
pr = 1/(1+exp(-xb))
y = rbinom(n,1,pr)
# calculate statistic:
stat = function(y, x, m, N, a) {
y_train = y[1:m]
x_train = x[(1:m),]
y_test = y[-(1:m)]
x_test = x[-(1:m),]
fit = glm(y ~ 0 + x, family="binomial")
coef = coef(fit)
log_predict = predict(fit, type="response")
sigma = sqrt(1/(m-1)* sum((y_train - log_predict)^2))
Jvalue = t(x_train) %*% x_train/m * sigma^2
Jsroot = sqroot(Jvalue)
fvalue = fa(m, N, a)
score1 = apply((x_test * as.vector((y_test - x_test %*% coef))), 2, cumsum)
statvalue1 = t(solve(Jsroot) %*% t(score1))/fvalue/sqrt(m)
statmax1 = pmax(abs(statvalue1[, 1]), abs(statvalue1[, 2]))
result = list(stat = statmax1)
return(result)
}
m =50
N = 2
a = 2.795
value = stat(y, x, m, N, a)
value
I want to perform bootstrap to obtain B = 999 number of statistics. I use the following r code. But it produces an error saying "Error in statistic(data, original, ...) :
argument "m" is missing, with no default"
library(boot)
data1 = data.frame(y = y, x = x1, m = m , N = N, a = a)
head(data1)
boot_value = boot(data1, statistic = stat, R = 999)
Can anyone give me a hint? Also, am I able to get the bootstrap results in a matrix format? Since the stat function gives 100 values.
There are different kinds of bootstrapping. If you want to draw from your data 999 samples with replications of same size of your data you may just use replicate, no need for packages.
We put the data to be resampled into a data frame. It looks to me like m, N, a remain constant, so we just provide it as vectors.
data2 <- data.frame(y=y, x=x)
stat function needs to be adapted to unpack y and x-matrix. At the bottom we remove the list call to get just a vector back. unnameing will just give us the numbers.
stat2 <- function(data, m, N, a) {
y_train <- data[1:m, 1]
x_train <- as.matrix(data[1:m, 2:3])
y_test <- data[-(1:m), 1]
x_test <- as.matrix(data[-(1:m), 2:3])
y <- data[, "y"]
x <- as.matrix(data[, 2:3])
fit <- glm(y ~ 0 + x, family="binomial")
coef <- coef(fit)
log_predict <- predict(fit, type="response")
sigma <- sqrt(1/(m-1) * sum((y_train - log_predict)^2))
Jvalue <- t(x_train) %*% x_train/m * sigma^2
Jsroot <- sqroot(Jvalue)
fvalue <- fa(m, N, a)
score1 <- apply((x_test * as.vector((y_test - x_test %*% coef))), 2, cumsum)
statvalue1 <- t(solve(Jsroot) %*% t(score1))/fvalue/sqrt(m)
statmax1 <- pmax(abs(statvalue1[, 1]), abs(statvalue1[, 2]))
result <- unname(statmax1)
return(result)
}
replicate is a cousin of sapply, designed for repeated evaluation. In the call we just sample the rows 999 times and already get a matrix back. As in sapply we need to transform our result.
res <- t(replicate(999, stat2(data2[sample(1:nrow(data2), nrow(data2), replace=TRUE), ], m, N, a)))
Result
As result we get 999 bootstrap replications in the rows with 100 attributes in the columns.
str(res)
# num [1:999, 1:100] 0.00205 0.38486 0.10146 0.12726 0.47056 ...
The code also runs quite fast.
user system elapsed
3.46 0.01 3.49
Note, that there are different kinds of bootstrapping. E.g. sometimes just a part of the sample is resampled, weights are used, clustering is applied etc. Since you attempted to use boot the method shown should be the default, though.
I implemented this simple NN but even when making it do all the interactions it fails to converge and the MSE remains very high
I tried to change the number of iterations and the learning rate but it doesn't work
rm(list=ls())
data <- read.csv("C:/Users/Mikele/Documents/Uni/IA AI & Machine Learning/R/11_23_2018/wine.csv",sep = ',',header = FALSE)
x <- data[,1:11]
y <- as.matrix(data[,12])
y_matrix <- matrix(rep(0,length(y)),nrow = length(y), ncol = 6)
k <-1
for (w in 1:length(y))
{
temp <- y[k] - 2
y_matrix[k,temp] <-1
k <- k + 1
}
hl <- c(40, 30, 20)
iter <- 1000
lr <- 0.1
## add in intercept
x_1 <- as.matrix(cbind(rep(1, nrow(x)),x))
## set error array
error <- rep(0, iter)
## set up weights
## the +1 is to add in the intercept/bias parameter
W1 <- matrix(runif(ncol(x_1)*hl[1], -1, 1), nrow = ncol(x_1))
W2 <- matrix(runif((hl[1]+1)*hl[2], -1, 1), nrow = hl[1]+1)
W3 <- matrix(runif((hl[2]+1)*hl[3], -1, 1), nrow = hl[2]+1)
W4 <- matrix(runif((hl[3]+1)*ncol(y), -1, 1), nrow = hl[3]+1)
for(k in 1:iter)
{
# calculate the hidden and output layers using X and hidden layer as inputs
# hidden layer 1 and 2 have a column of ones appended for the bias term
hidden1 <- cbind(matrix(1, nrow = nrow(x_1)), sigm(x_1 %*% W1))
hidden2 <- cbind(matrix(1, nrow = nrow(x_1)), sigm(hidden1 %*% W2))
hidden3 <- cbind(matrix(1, nrow = nrow(x_1)), sigm(hidden2 %*% W3))
y_hat <- sigm(hidden3 %*% W4)
# calculate the gradient and back prop the errors
# see theory above
y_hat_del <- (y-y_hat)*(d.sigm(y_hat))
hidden3_del <- y_hat_del %*% t(W4)*d.sigm(hidden3)
hidden2_del <- hidden3_del[,-1] %*% t(W3)*d.sigm(hidden2)
hidden1_del <- hidden2_del[,-1] %*% t(W2)*d.sigm(hidden1)
# update the weights
W4 <- W4 + lr*t(hidden3) %*% y_hat_del
W3 <- W3 + lr*t(hidden2) %*% hidden3_del[,-1]
W2 <- W2 + lr*t(hidden1) %*% hidden2_del[,-1]
W1 <- W1 + lr*t(x_1) %*% hidden1_del[,-1]
error[k] <- 1/nrow(y)*sum((y-y_hat)^2)
if((k %% (10^4+1)) == 0) cat("mse:", error[k], "\n")
}
# plot loss
xvals <- seq(1, iter, length = 100)
print(qplot(xvals, error[xvals], geom = "line", main = "MSE", xlab = "Iteration"))
no error message but I can't understand how to make a deep NN for
Multivariate Linear Regression
in addition I divided the ys into a 6-column matrix (the maximum and minimum of the initial dataset) now there is someone who can help me understand why not cover and in any case the final results are all concentrated on column 4?
I’m trying to write simulation code, that generates data and runs t-test selection (discarding those predictors whose t-test p-value exceeds 0.05, retaining the rest) on it. The simulation is largely an adaptation of Applied Econometrics with R by Kleiber and Zeileis (2008, pp. 183–189).
When running the code, it usually fails. Yet with certain seeds (e.g. 1534) it produces plausible output. If it does not produce output (e.g. 1911), it fails due to: "Error in x[, ii] : subscript out of bounds", which traces back to na.omit.data.frame(). So, for some reason, the way I attempt to handle the NAs seems to fail, but I'm unable to figure out in how so.
coef <- rep(coef[,3], length.out = pdim+1)
err <- as.vector(rnorm(nobs, sd = sd))
uX <- c(rep(1, times = nobs))
pX <- matrix(scale(rnorm(nobs)), byrow = TRUE, ncol = pdim, nrow = nobs)
X <- cbind(uX, pX)
y <- coef %*% t(X) + err
y <- matrix(y)
tTp <- (summary(lm(y ~ pX)))$coefficients[,4]
tTp <- tTp[2:length(tTp)]
TTT <- matrix(c(tTp, rep(.7, ncol(pX)-length(tTp))))
tX <- matrix(NA, ncol = ncol(pX), nrow = nrow(pX))
for(i in 1:ncol(pX)) {ifelse(TTT[i,] < ALPHA, tX[,i] <- pX[,i], NA)}
tX <- matrix(Filter(function(x)!all(is.na(x)), tX), nrow = nobs)
TTR <- lm(y ~ tX)
The first block is unlikely to the cause of the error. It merely generates the data and works well on its own and with other methods, like PCA, as well. The second block pulls the p-values from the regression output; removes the p-value of the intercept (beta_0); and fills the vector with as many 7s as necessary to have the same length as the number of variables, to ensure the same dimension for matrix calculations. Seven is arbitrary and could be any number larger than 0.05 to not pass the test of the loop. This becomes – I believe – necessary, if R discards predictors due to multicollinearity.
The final block creates an empty matrix of the original dimensions; inserts the original data, if the t-test p-value is lower than 0.05, else retains the NA; while the penultimate line removes all columns containing NAs ((exclusively NA or one NA is the same here) taken from mnel’s answer to Remove columns from dataframe where ALL values are NA); lastly, the modified data is again put in the shape of a linear regression.
Does anyone know what causes this behavior or how it would work as intended? I would expect it to either work or not, but not kind of both. Ideally, the former.
A working version of the code is:
set.seed(1534)
Sim_TTS <- function(nobs = c(1000, 15000), pdim = pdims, coef = coef100,
model = c("MLC", "MHC"), ...){
DGP_TTS <- function(nobs = 1000, model = c("MLC", "MHC"), coef = coef100,
sd = 1, pdim = pdims, ALPHA = 0.05)
{
model <- match.arg(model)
if(model == "MLC") {
coef <- rep(coef[,1], length.out = pdim+1)
err <- as.vector(rnorm(nobs, sd = sd))
uX <- c(rep(1, times = nobs))
pX <- matrix(scale(rnorm(nobs)), byrow = TRUE, ncol = pdim, nrow = nobs)
X <- cbind(uX, pX)
y <- coef %*% t(X) + err
y <- matrix(y)
tTp <- (summary(lm(y ~ pX)))$coefficients[,4]
tTp <- tTp[2:length(tTp)]
TTT <- matrix(c(tTp, rep(.7, ncol(pX)-length(tTp))))
tX <- matrix(NA, ncol = ncol(pX), nrow = nrow(pX))
for(i in 1:ncol(pX)) {ifelse(TTT[i,] < ALPHA, tX[,i] <- pX[,i], NA)}
tX <- matrix(Filter(function(x)!all(is.na(x)), tX), nrow = nobs)
TTR <- lm(y ~ tX)
} else {
coef <- rep(coef[,2], length.out = pdim+1)
err <- as.vector(rnorm(nobs, sd = sd))
uX <- c(rep(1, times = nobs))
pX <- matrix(scale(rnorm(nobs)), byrow = TRUE, ncol = pdim, nrow = nobs)
X <- cbind(uX, pX)
y <- coef %*% t(X) + err
y <- matrix(y)
tTp <- (summary(lm(y ~ pX)))$coefficients[,4]
tTp <- tTp[2:length(tTp)]
TTT <- matrix(c(tTp, rep(.7, ncol(pX)-length(tTp))))
tX <- matrix(NA, ncol = ncol(pX), nrow = nrow(pX))
for(i in 1:ncol(pX)) {ifelse(TTT[i,] < ALPHA, tX[,i] <- pX[,i], NA)}
tX <- matrix(Filter(function(x)!all(is.na(x)), tX), nrow = nobs)
TTR <- lm(y ~ tX)
}
return(TTR)
}
PG_TTS <- function(nrep = 1, ...)
{
rsq <- matrix(rep(NA, nrep), ncol = 1)
rsqad <- matrix(rep(NA, nrep), ncol = 1)
pastr <- matrix(rep(NA, nrep), ncol = 1)
vmat <- cbind(rsq, rsqad, pastr)
colnames(vmat) <- c("R sq.", "adj. R sq.", "p*")
for(i in 1:nrep) {
vmat[i,1] <- summary(DGP_TTS(...))$r.squared
vmat[i,2] <- summary(DGP_TTS(...))$adj.r.squared
vmat[i,3] <- length(DGP_TTS(...)$coefficients)-1
}
return(c(mean(vmat[,1]), mean(vmat[,2]), round(mean(vmat[,3]))))
}
SIM_TTS <- function(...)
{
prs <- expand.grid(pdim = pdim, nobs = nobs, model = model)
nprs <- nrow(prs)
pow <- matrix(rep(NA, 3 * nprs), ncol = 3)
for(i in 1:nprs) pow[i,] <- PG_TTS(pdim = prs[i,1],
nobs = prs[i,2], model = as.character(prs[i,3]), ...)
rval <- rbind(prs, prs, prs)
rval$stat <- factor(rep(1:3, c(nprs, nprs, nprs)),
labels = c("R sq.", "adj. R sq.", "p*"))
rval$power <- c(pow[,1], pow[,2], pow[,3])
rval$nobs <- factor(rval$nobs)
return(rval)
}
psim_TTS <- SIM_TTS()
tab_TTS <- xtabs(power ~ pdim + stat + model + nobs, data = psim_TTS)
ftable(tab_TTS, row.vars = c("model", "nobs", "stat"), col.vars = "pdim")}
FO_TTS <- Sim_TTS()
FO_TTS
}
Preceeded by:
pdims <- seq(12, 100, 4)
coefLC12 <- c(0, rep(0.2, 4), rep(0.1, 4), rep(0, 4))/1.3
rtL <- c(0.2, rep(0, 3))/1.3
coefLC100 <- c(coefLC12, rep(rtL, 22))
coefHC12 <- c(0, rep(0.8, 4), rep(0.4, 4), rep(0, 4))/1.1
rtH <- c(0.8, rep(0, 3))/1.1
coefHC100 <- c(coefHC12, rep(rtH, 22))
coef100 <- cbind(coefLC100, coefHC100)
I’m aware that model selection via the significance of individual predictors is not recommended, but that is the whole point – it is meant to be compared to more sophisticated methods.