Linear combination of random variables

In summary: Whoops! I just totally misread the question, sorry. I think my brain just said that doesn't make any sense and converted 10 people into 1000 kilograms.
  • #1
archaic
688
214
Homework Statement
The weight of ##25## individuals trying to squeeze themselves into an elevator is normally distributed with a mean of ##76\,kg## and a standard deviation of ##16\,kg##. The elevator is designed to hold ##1950\,kg##.
a) Determine the mean and standard deviation of the total weight inside the elevator.
b) What's the probability that that weight exceeds the limit?
c) Knowing that the electricity costs ##0.1\,$## per ##kg## for the first ##10## persons, and ##0.2\,$## per ##kg## for any extra person, find the mean and the variance of the cost for this scenario.
Relevant Equations
n/a
a) Total weight ##W=W_1+W_2+...+W_{25}##.$$E[W]=E[W_1]+E[W_2]+...+E[W_{25}]=25\times76=1900\,kg$$$$\sigma_W=\sqrt{V(W_1)+V(W_2)+...+V(W_{25})}=\sqrt{25\times(16)^2}=80\,kg$$
b) Since ##W## is a linear combination of normal distributions, the reproductive property tells us that ##W## is also normally distributed.$$P(W>1950)=P(Z>0.625)=1-P(Z<0.625)=0.26599$$
c) Cost ##C=0.1W_1+...+0.1W_{10}+0.2W_{11}+...+0.2W_{25}##.$$\begin{align*}E[C]&=0.1E[W_1]+...+0.1E[W_{10}]+0.2E[W_{11}]+...+0.2E[W_{25}]\\&=10\times0.1\times76+15\times0.2\times76\\&=304\,$\end{align*}$$$$\begin{align*}
V(C)&=(0.1)^2V(W_1)+...+(0.1)^2V(W_{10})+(0.2)^2V(W_{11})+...+(0.2)^2V(W_{25})\\
&=10\times(0.1)^2\times(16)^2+15\times(0.2)^2\times(16)^2\\
&=179.2\,$^2
\end{align*}$$
Correct, right? Thanks!
 
  • Like
Likes Delta2
Physics news on Phys.org
  • #2
Part (c) is done incorrectly I think. To give an extreme example to demonstrate the issue, suppose electricity cost nothing for the first 1900 kg and cost 20 cents per kilogram after. What would the expected cost of the electricity be?
In practice I think the number you computed for the e.v. is going to be very close to the true answer.
 
  • #3
Office_Shredder said:
Part (c) is done incorrectly I think. To give an extreme example to demonstrate the issue, suppose electricity cost nothing for the first 1900 kg and cost 20 cents per kilogram after. What would the expected cost of the electricity be?
In practice I think the number you computed for the e.v. is going to be very close to the true answer.
Then we expect the cost to be zero since the expected mass in the elevator is 1900 kg. But isn't this a different scenario? They specified that the cost is per person.
I am sorry, I don't see the point.
 
  • #4
Office_Shredder said:
Part (c) is done incorrectly I think. To give an extreme example to demonstrate the issue, suppose electricity cost nothing for the first 1900 kg and cost 20 cents per kilogram after. What would the expected cost of the electricity be?
In practice I think the number you computed for the e.v. is going to be very close to the true answer.
Well, it is not stated as so much per kg for the first so many kg; it is for the first so many persons. That's a bit of a problem because we could arrange to have the heaviest get in first!
But I agree that it needs to be approached from first principles: find ##E[C^2]## etc.
 
  • #5
haruspex said:
Well, it is not stated as so much per kg for the first so many kg; it is for the first so many persons. That's a bit of a problem because we could arrange to have the heaviest get in first!
But I agree that it needs to be approached from first principles: find ##E[C^2]## etc.
What is the significance of the square? Why is it a first principle?
 
  • #6
archaic said:
What is the significance of the square? Why is it a first principle?
It's part of the definition of variance: ##E[X^2]-E[X]^2##. Use that to find the variance of the cost.
 
  • #7
haruspex said:
It's part of the definition of variance: ##E[X^2]-E[X]^2##. Use that to find the variance of the cost.
Oh, ok. I thought that you had some thing in mind that I didn't know like in the other post (minimizing the expression you wrote, and finding ##R^2##).
This is from the lecture slides:
Capture.PNG

I forgot to mention it, but the ##W_i## are identical and independent, so the double sum is null. My bad..
 
  • Like
Likes Delta2
  • #8
archaic said:
Oh, ok. I thought that you had some thing in mind that I didn't know like in the other post (minimizing the expression you wrote, and finding ##R^2##).
This is from the lecture slides:
View attachment 271835
I forgot to mention it, but the ##W_i## are identical and independent, so the double sum is null. My bad..
Then it's fine.
 
  • Like
Likes archaic
  • #9
haruspex said:
Well, it is not stated as so much per kg for the first so many kg; it is for the first so many persons. That's a bit of a problem because we could arrange to have the heaviest get in first!
But I agree that it needs to be approached from first principles: find ##E[C^2]## etc.

Whoops! I just totally misread the question, sorry. I think my brain just said that doesn't make any sense and converted 10 people into 1000 kilograms.
 

FAQ: Linear combination of random variables

What is a linear combination of random variables?

A linear combination of random variables is a mathematical expression that combines two or more random variables using coefficients and addition or subtraction operations. It is used to create a new random variable that is a linear combination of the original variables.

How is a linear combination of random variables different from a single random variable?

A linear combination of random variables is a combination of two or more random variables, whereas a single random variable is just one variable. The linear combination allows for the creation of a new variable with different characteristics and properties than the individual variables.

What are the properties of a linear combination of random variables?

A linear combination of random variables inherits certain properties from the original variables, such as mean, variance, and distribution. However, the specific properties of the new variable depend on the coefficients and operations used in the combination.

How is a linear combination of random variables used in scientific research?

Linear combinations of random variables are commonly used in statistical analysis and modeling. They can be used to create new variables that better represent the data and to study the relationships between variables. They are also used in fields such as economics, finance, and engineering to model complex systems and make predictions.

What are some examples of linear combinations of random variables?

Examples of linear combinations of random variables include weighted averages, such as the combination of stock prices in a stock portfolio, and regression models, where the dependent variable is a linear combination of the independent variables. They can also be used to create new variables, such as principal components, in data analysis.

Back
Top