Mehrere Minima in R

Question

Ich versuche die Werte zu finden, die am meisten und am wenigsten zu einem Gaussian Kernel Density Estimator beitragen. Ich habe eine Funktion geschrieben, um diese zu finden, aber ich bekomme mehrere Werte für ein Maximum, wenn ich es ausführe. Ich dachte, dass dies mit der Anzahl der signifikanten Ziffern zusammenhängt, also habe ich diese erhöht, aber nichts hat sich geändert.

Kann jemand Einblick geben?

#Create a vector with Brainsize-Small Litter Size Data: 
Y_i<-c(0.42, 0.86, 0.88, 1.11, 1.34, 1.38, 1.42, 1.47, 1.63,1.73, 2.17, 2.42, 2.48, 2.74, 2.74, 2.79, 2.90, 3.12,3.18, 3.27, 3.30, 3.61, 3.63, 4.13, 4.40, 5.00, 5.20,5.59, 7.04, 7.15, 7.25, 7.75, 8.00, 8.84, 9.30, 9.68,10.32, 10.41, 10.48, 11.29, 12.30, 12.53, 12.69, 14.14, 14.15,14.27, 14.56, 15.84, 18.55, 19.73, 20.00) 

#Create a kernel density estimator function: 
kern<-function(data=0,effOf=0,bw=0){ 
z<-rep(0,length(data)) 
k<-rep(0,length(data)) 

for(i in data){ 
z[i]=((effOf-data[i])/bw) 
} 

for(j in z){ 
k[j]=(1/sqrt(2*pi))*exp(-(z[j]^2/2))/(length(data)*bw) 
} 

min=min(k) 
imin=which(k==min) 
ymin=data[imin] 

max=max(k) 
imax=which(k==max) 
ymax=data[imax] 

print(paste("The minimum contributor is value",ymin)) 
print(paste("The maximum contributor is value",ymax)) 

estimate=sum(k) 
return(estimate) 
} 

#(a.)Use KDE function to estimate f(16) 
kern(Y_i,16,3) 

Dies ist die Output- daran denken, dass ich nur einen Maximalwert wollen:

[1] "The minimum contributor is value 0.42" "The minimum contributor is value 0.86" 
[3] "The minimum contributor is value 0.88" "The minimum contributor is value 1.38" 
[5] "The minimum contributor is value 1.42" "The minimum contributor is value 1.47" 
[7] "The minimum contributor is value 1.63" "The minimum contributor is value 1.73" 
[9] "The minimum contributor is value 2.17" "The minimum contributor is value 2.42" 
[11] "The minimum contributor is value 2.48" "The minimum contributor is value 2.74" 
[13] "The minimum contributor is value 2.74" "The minimum contributor is value 2.79" 
[15] "The minimum contributor is value 2.9" "The minimum contributor is value 3.12" 
[17] "The minimum contributor is value 3.18" "The minimum contributor is value 3.27" 
[19] "The minimum contributor is value 3.3" "The minimum contributor is value 3.61" 
[21] "The minimum contributor is value 3.63" "The minimum contributor is value 4.13" 
[23] "The minimum contributor is value 4.4" "The minimum contributor is value 5"  
[25] "The minimum contributor is value 5.2" "The minimum contributor is value 5.59" 
[27] "The minimum contributor is value 7.04" "The minimum contributor is value 7.15" 
[29] "The minimum contributor is value 7.25" "The minimum contributor is value 7.75" 
[31] "The minimum contributor is value 8"  "The minimum contributor is value 8.84" 
[33] "The minimum contributor is value 9.3" "The minimum contributor is value 9.68" 
[35] "The minimum contributor is value 10.32" "The minimum contributor is value 10.41" 
[37] "The minimum contributor is value 10.48" "The minimum contributor is value 11.29" 
[39] "The minimum contributor is value 12.3" "The minimum contributor is value 12.53" 
[41] "The minimum contributor is value 12.69" "The minimum contributor is value 14.14" 
[43] "The minimum contributor is value 14.15" "The minimum contributor is value 14.27" 
[45] "The minimum contributor is value 14.56" "The minimum contributor is value 15.84" 
[47] "The minimum contributor is value 18.55" "The minimum contributor is value 19.73" 
[49] "The minimum contributor is value 20" 
[1] "The maximum contributor is value 1.34" 
[1] 2.868016e-08 

Answer 1

denke ich, der richtige Code wie das sein sollte folgende (mit 2 Modifikationen, die Indizierung in der für Schleifen waren falsch, dass in falsch z und Kernel-Werte zur Folge):

kern<-function(data=0,effOf=0,bw=0){ 

    z<-rep(0,length(data)) 
    k<-rep(0,length(data)) 

    for(i in 1:length(data)){ # iterate through all data points 
    z[i]=((effOf-data[i])/bw) 
    } 

    for(j in 1:length(z)){ # iterate through all z values 
    k[j]=(1/sqrt(2*pi))*exp(-(z[j]^2/2))/(length(data)*bw) 
    } 

    min=min(k) 
    imin=which(k==min) 
    ymin=data[imin] 

    max=max(k) 
    imax=which(k==max) 
    ymax=data[imax] 

    print(paste("The minimum contributor is value",ymin)) 
    print(paste("The maximum contributor is value",ymax)) 

    estimate=sum(k) 
    return(estimate) 
} 

#(a.)Use KDE function to estimate f(16) 
kern(Y_i,16,3) 

[1] "The minimum contributor is value 0.42" 
[1] "The maximum contributor is value 15.84" 
[1] 0.02254657