What is the connection between X_n and Y_n?

In summary, the question is about understanding the connection between parts (a) and (b) of the problem. Part (a) involves using the Central Limit Theorem to show that if X_n is Bernoulli with probability p, then the sum of n independent X_n's is binomial with parameters n and p. In part (b), we are asked to show that Y_n, defined as the sum of n independent Y_i's, where each Y_i is binomial with parameters n and p, approaches a standard normal distribution as n approaches infinity. This can be shown using the CLT by finding the mean and variance of Y_n and then applying the theorem.
  • #1
Ted123
446
0

Homework Statement



[PLAIN]http://img263.imageshack.us/img263/8679/statsji.jpg

The Attempt at a Solution



I've done part (a) and I know what the CLT says but how does part (a) link with part (b) as if [itex]X_n \sim Bern(p)[/itex] then [itex]\displaystyle \sum^n_{i=1} X_i \sim Bin(n,p)[/itex] so [itex]X_n = \displaystyle \sum^n_{i=1} Y_i[/itex] where [itex]Y_1 , \cdots , Y_n \sim Bin(n,p)[/itex] are i.i.d

BUT [itex]X_n \sim Bin(n,p)[/itex] so where do I go from here?
 
Last edited by a moderator:
Physics news on Phys.org
  • #2
How did you come up with

[tex]X_n = \sum^n_{i=1} Y_i[/tex]

?
 
  • #3
vela said:
How did you come up with

[tex]X_n = \sum^n_{i=1} Y_i[/tex]

?

Actually it should be [itex]Y_n = \sum^n_{i=1} X_i[/itex] where [itex]X_1, ..., X_n \sim Bern(p)[/itex] (iid)

so [itex]\frac{Y_n - \mathbb{E}[Y_n]}{\sqrt{Var(Y_n)}} = \frac{Y_n - \sum^n_{i=1} \mathbb{E}[Y_i]}{\sqrt{\sum^n_{i=1} Var(Y_i)}} = \frac{Y_n - n\mathbb{E}[Y_1]}{\sqrt{nVar(Y_1)}} = \frac{Y_n - np}{\sqrt{np(1-p)}} \to Y ;\; Y\sim N(0,1) [/itex] by CLT
 
Last edited:

What is the Central Limit Theorem?

The Central Limit Theorem (CLT) is a fundamental theory in statistics that states that when independent random variables are added together, their sum will tend towards a normal distribution, regardless of the underlying distribution of the individual variables.

Why is the Central Limit Theorem important?

The CLT is important because it allows us to make inferences about a population based on a sample, even if the population's distribution is unknown or non-normal. It also forms the basis for many statistical tests and models, such as t-tests and regression analysis.

Is the Central Limit Theorem always applicable?

No, the CLT has certain assumptions and conditions that must be met in order to be applicable. These include having a large sample size, independent observations, and finite variances of the underlying variables. If these conditions are not met, the CLT may not accurately describe the distribution of the sample mean.

Can the Central Limit Theorem be used with any type of data?

The CLT can be used with any type of data, as long as the underlying variables meet the required assumptions and conditions. However, it is most commonly used with continuous data, as discrete data may not follow a normal distribution.

How is the Central Limit Theorem used in practice?

The CLT is used in many areas of research and statistics, such as hypothesis testing, confidence intervals, and parameter estimation. It allows us to make generalizations about a population based on a sample, and to quantify the uncertainty in our estimates. It is also used in quality control and process improvement to assess whether a process is producing consistent and predictable results.

Similar threads

Replies
2
Views
1K
Replies
16
Views
2K
  • Linear and Abstract Algebra
Replies
13
Views
1K
  • Set Theory, Logic, Probability, Statistics
Replies
8
Views
1K
  • Calculus and Beyond Homework Help
Replies
3
Views
2K
Replies
5
Views
379
Replies
24
Views
2K
  • Topology and Analysis
Replies
3
Views
2K
  • Quantum Physics
Replies
1
Views
543
  • Calculus and Beyond Homework Help
Replies
8
Views
1K
Back
Top