Any maths / statistics whizzes here?

[DimPrawn]

There's Lies.

There's damned Lies.

There's Statistics.

And then there's Scooty.

FTFY

[sasguru]

There's Lies.

There's damned Lies.

Then there's Statistics.

I find that's a meaningless cliche often spouted by the mathematically illiterate.

[Old Greg]

I find that's a meaningless cliche often spouted by the mathematically illiterate.

Innumerate is the word you're looking for.

[sasguru]

Innumerate is the word you're looking for.

[SimonMac]

Just knocked up a quick and dirty Java program, based on a population of 1000 people.

package randomActions;

import java.util.ArrayList;

public class randomActionPoint4 {
	public static void main(String[] args) {
		int runningTotal = 0;
		for (int j = 1; j <= 10000; j++) {
			ArrayList<Integer> chosen = new ArrayList<Integer>();
			for (int i = 1; i <= 10000; i++) {
				ArrayList<Integer> choices = new ArrayList<Integer>();
				choices.add(getUnique(choices));
				choices.add(getUnique(choices));
				choices.add(getUnique(choices));
				choices.add(getUnique(choices));
				for (Integer choice : choices) {
					if (!chosen.contains(choice)) {
						chosen.add(choice);
					}
				}
				if (chosen.size() == 1000) {
					runningTotal = runningTotal + i;
					break;
				}
			}
		}
		System.out.println(runningTotal/10000);
	}

	private static int getUnique(ArrayList<Integer> choices) {
		int choice;
		do {
			choice = (int) (Math.random() * ((1000 - 1) + 1)) + 1;
		} while (choices.contains(choice));
		return choice;
	}

}

I've run it a few times, and each time it took on average 1866 weeks for all 1000 people to do it. I'm pretty sure the result is independent of the population size.

Dunno if I understood the prob but here's some R code which gives the average weeks in the order of 1850-ish.

nums <- c(rep(0, 1000))

for (j in 1:1000){
  
  count <- 0
  people <- c(rep(FALSE, 1000))
  while (TRUE) {
    
    count <- count + 1
    
    k <-  sample(1:1000,4,replace=F)
    for (i in 1:4){
      people[k[i]] <- TRUE
    }
    
    if (all(people)) {break}
  }
    nums[j] <- count
  
}

print(mean(nums))

Edit: Actually more like 1860-ish which kind of matches NAT.
Edit2: Assumes sampling with replacement
NATEdit3: Add code tags around it to make it a bit more readable.

Thanks both, the rough assumption is right (well right based on my flawed requirements, there is a chance that the person would need to "do the thing" again after a given number of years, and seeing you are saying we are talking over 30 years to get 100% of the people to "do the thing" it is something we are going to have to account)

I think it's enough to scare the powers that be that we need to carry on with the project to try and improve the 0.4% take up date

[sasguru]

I think jamesbrown had the soundest algebraic approach.

I think that's an interesting POV.
I've done both mathematical stats and computational statistics (simulation) courses where techniques like the jacknife and bootstrap were used to obtain similar results (e.g. confidence intervals) and enjoyed both, but preferred the latter.
I thinks stats should be taught more using simulation than mathematics, especially for those uncomfortable with maths.

Anyone whose interest has been stimulated can read this (extremely simple) starter guide to R and stats:
Statistical Inference via Data Science

[scooterscot]

I've done both mathematical stats and computational statistics (simulation) courses where techniques like the jacknife and bootstrap were used to obtain similar results (e.g. confidence intervals) and enjoyed both, but preferred the latter. I thinks stats should be taught more using simulation than mathematics, especially for those uncomfortable with maths.

Then how is it you don't use a deterministic approach with assumptions, rather the a probabilistic attempt with unknowns?

Making a problem more complicated than it need is so IT.

[sasguru]

Then how is it you don't use a deterministic approach with assumptions, rather the a probabilistic attempt with unknowns?

Making a problem more complicated than it need is so IT.

You clearly didn't understand my statement. How is it you were unable to solve the problem either way?

[scooterscot]

Feck off, you fraud.

Bullying + name calling others might have served you well as a youngster then as an adult, we get Trump. He who shouts loudest is heard the least.

[sasguru]

Bullying + name calling others might have served you well as a youngster then as an adult, we get Trump. He who shouts loudest is heard the least.

When Trump pretends to be an expert in epidemiology, he reminds me of you.