I am working with the R programming language.
I wrote the following code that generates 20 random points from a Normal Distribution and then plots the likelihood function:
# generate random data
x1 = rnorm(1,5,5)
x2 = rnorm(1,5,5)
x3 = rnorm(1,5,5)
x4 = rnorm(1,5,5)
x5 = rnorm(1,5,5)
x6 = rnorm(1,5,5)
x7 = rnorm(1,5,5)
x8 = rnorm(1,5,5)
x9 = rnorm(1,5,5)
x10 = rnorm(1,5,5)
x11 = rnorm(1,5,5)
x12 = rnorm(1,5,5)
x13 = rnorm(1,5,5)
x14 = rnorm(1,5,5)
x15 = rnorm(1,5,5)
x16 = rnorm(1,5,5)
x17 = rnorm(1,5,5)
x18 = rnorm(1,5,5)
x19 = rnorm(1,5,5)
x20 = rnorm(1,5,5)
# Define Likelihood Function (from here: #https://www.statlect.com/fundamentals-of-statistics/normal-distribution-maximum-likelihood - I broke the Likelihood Function into 4 parts "a", "b", "c", "d" : then I added them together to make the full Likelihood Function "f")
my_function <- function(mu,sigma) {
n = 20
a = -n/2*log(2*pi)
b = -n/2*log(sigma^2)
c = -1/(2*sigma^2)
d = (x1-mu)^2 (x2-mu)^2 (x3-mu)^2 (x4-mu)^2 (x5-mu)^2 (x6-mu)^2 (x7-mu)^2 (x8-mu)^2 (x9-mu)^2 (x10-mu)^2 (x11-mu)^2 (x12-mu)^2 (x13-mu)^2 (x14-mu)^2 (x15-mu)^2 (x16-mu)^2 (x17-mu)^2 (x18-mu)^2 (x19-mu)^2 (x20-mu)^2
f = a b c d
}
# plot results
library(plotly)
input_1 <- seq(-20, 20,0.1)
input_2 <- seq(-20,20, 0.1)
z <- outer(input_1, input_2, my_function)
plot_ly(x = input_1, y = input_2, z = z) %>% add_surface()
My Question: Can someone please show me how to make a more "efficient" version of this code?
For example, I had thought of directly generating 20 points from this distribution in one shot
my_data = rnorm(20,5,5)
and then place them into a data frame- but I did not know how to "feed" data from a data frame into the functionSince I had 20 data points, I had to manually write
(x_i -mu)^2
20 different times - would it have been possible to have a function that could have "recognized" that there were 20 points and then "adapted" itself to "accommodate" these 20 points without having to manually re-write(x_i -mu)^2
so many times?
CodePudding user response:
For storing data into the data.frame you can just do the following:
my_data <- rnorm(20, 5, 5)
df <- data.frame(x = my_data, <other_columns>)
Note, the other columns need to be of the same length. If this is not the case, it would be better to keep these numbers separate.
Then within the my_function
, you can have:
d = sum((df$my_data - mu)^2)
If you are not using dataframe, this would be instead:
d = sum((my_data - mu)^2)