Survey

* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project

Document related concepts

Central limit theorem wikipedia, lookup

Transcript
```Stat 226 SI:
Sampling Distribution
Supplemental Instruction
Iowa State University
Course: Stat 226
Date: 3/4/13
Agenda:
Opening Activity: Fill-in-the-blank
Main Activity: Sampling Distribution Problem
Closing Activity: T/F Questions
Fill-In-The-Blank:
1.) Population parameters μ and σ are typically unknown values.
2.) The sample mean 𝑥̅ will following an approximately normal distribution if the sample size is
large enough.
3.) The symbol for the mean of the sampling distribution of 𝑋̅ is 𝜇𝑋̅ , which is equal to μ.
4.) The standard error of the sampling distribution of 𝑋̅ is 𝜎𝑋̅ , which is equal to
5.) If 𝑋̅follows a normal distribution, it is notated by 𝑋̅~𝑁 (μ,
σ2
n
𝜎
√𝑛
.
).
6.) The notation for the standard error of the sample mean distribution is SE(𝑋̅), which is equal
𝜎
to 𝑛.
√
7.) The z-score of a sampling distribution of a sample mea is calculated by 𝑍 =
𝑥̅ −𝜇
𝜎
√𝑛
.
Sampling Distribution Problem:
A farmer claims that, on his apple orchard, the number of apples per tree follows a normal
distribution with a mean of 230 apples and a standard deviation of 20 apples.
(a.) Describe the shape of the sampling distribution with a sample size of 4 trees.
Normal – Because the population distribution is known to be normal, we assume the
sampling distribution is also normal, regardless of the small sampling size.
(b.) 𝜇 = 230 𝑎𝑝𝑝𝑙𝑒𝑠
𝜇𝑋̅ = 230 𝑎𝑝𝑝𝑙𝑒𝑠
(c.) SE(𝑋̅) =
20
√4
=
20
2
= 10 𝑎𝑝𝑝𝑙𝑒𝑠
(d.) Does the mean of the sampling distribution change if the population distribution is no longer
normal?
If the population distribution is no longer normal, we must apply the CLT, which says the
sampling distribution will be approximately normal if the sample size is sufficiently
large. If 4 trees is a sufficiently large sample size, then the mean of the sampling
distribution will still be equal to the mean of the population distribution.
(e.) Does the standard error of the sampling distribution change if the population distribution is
no longer normal?
See answer D. This also applies for the standard error. It will still be equal to the
standard deviation of the population distribution divided by the sample size if a sample
size of 4 trees is sufficiently large. (The benchmark number for a sufficiently large
sample size is 30.)
(f.) How does the standard error change if the sample size increase to 16?
If the standard error quadruples in size here, the standard error decreases by 50%.
𝜎
20
20
=
=
= 5 𝑎𝑝𝑝𝑙𝑒𝑠
𝑛
4
√
√16
(g.) If the number of apples per tree did not follow a normal distribution, could we find the
probability that a single tree has fewer than 200 apples?
No.
True/False Questions:
If X does not follow a normal distribution, and it has mean equal to 15 and standard deviation
2
2
equal to 2 and sample size of 2, 𝑋~𝑁 (15, ( ) ).
√2
FALSE
2
4
If 𝑋~𝑁(10, 42 ), we need to use the central limit theorem to assume that 𝑋̅~𝑁 (10, ( 𝑛) ).
√
FALSE
If X does not follow a perfectly normal distribution, but it is symmetric and bell-shaped,
2
𝜎
𝑋̅~𝑎𝑝𝑝𝑟𝑜𝑥. 𝑁 (𝜇, ( 𝑛) ).
√
TRUE
```