MEV 019: Unit 09 - Sampling Distributions
UNIT 9: SAMPLING DISTRIBUTIONS
9.1
Introduction
In statistics, we often cannot examine an entire
population because it may be too large, costly, or time-consuming. Instead, we
study a sample and use the information to make inferences about the population.
However, different samples from the same population can yield slightly
different results. Sampling distributions help us understand the
variability of such sample-based statistics.
This unit introduces the concept of sampling,
sampling distributions, standard error, and exact probability distributions
like the chi-square, t, and F distributions.
9.2
Objectives
After completing this unit, you will be able to:
- Explain
the basics of sampling and sampling distributions.
- Define
and calculate the standard error.
- State
and interpret the Central Limit Theorem.
- Describe
and use sampling distributions of mean, proportion, and their differences.
- Understand
the chi-square, t, and F distributions and their applications.
9.3 Basics
of Sampling
Population – The complete set of items of interest.
Sample – A subset of the population selected for study.
Reasons for Sampling:
- Practicality
- Cost
efficiency
- Time
savings
Types of Sampling:
- Probability
Sampling (e.g., simple random, stratified, cluster,
systematic)
- Non-Probability
Sampling (e.g., convenience, quota, judgmental)
9.4 Sampling
Distribution
A sampling distribution is the probability
distribution of a given statistic (like the mean) calculated from all possible
samples of a fixed size drawn from a population.
9.4.1 Standard Error (SE)
The standard deviation of a sampling distribution
is called the standard error.
For sample mean:
SEXˉ=σnSE_{\bar{X}} = \frac{\sigma}{\sqrt{n}}SEXˉ=nσ
Where:
- σ\sigmaσ
= population standard deviation
- nnn =
sample size
For sample proportion:
SEp=P(1−P)nSE_{p} = \sqrt{\frac{P(1-P)}{n}}SEp=nP(1−P)
Where:
- PPP =
population proportion
9.4.2 Central Limit Theorem (CLT)
The CLT states that, for a large sample size, the
sampling distribution of the sample mean is approximately normal, regardless of
the shape of the population distribution.
This is the basis for using normal probability theory in many statistical
procedures.
9.5 Sampling
Distribution of Statistics
9.5.1 Sampling Distribution of Mean
If population mean = μ\muμ and standard deviation =
σ\sigmaσ, then:
- Mean of
sampling distribution: μXˉ=μ\mu_{\bar{X}} = \muμXˉ=μ
- Standard
deviation: σXˉ=σn\sigma_{\bar{X}} = \frac{\sigma}{\sqrt{n}}σXˉ=nσ
9.5.2 Sampling Distribution of Difference in Two
Means
For two independent samples:
SEXˉ1−Xˉ2=σ12n1+σ22n2SE_{\bar{X}_1 - \bar{X}_2} =
\sqrt{\frac{\sigma_1^2}{n_1} + \frac{\sigma_2^2}{n_2}}SEXˉ1−Xˉ2=n1σ12+n2σ22
9.5.3 Sampling Distribution of Proportion
If population proportion = PPP, then:
SEp=P(1−P)nSE_{p} = \sqrt{\frac{P(1-P)}{n}}SEp=nP(1−P)
9.5.4 Sampling Distribution of Difference in Two
Proportions
For two independent samples:
SEp1−p2=P1(1−P1)n1+P2(1−P2)n2SE_{p_1 - p_2} = \sqrt{\frac{P_1(1-P_1)}{n_1}
+ \frac{P_2(1-P_2)}{n_2}}SEp1−p2=n1P1(1−P1)+n2P2(1−P2)
9.6 Exact
Sampling Distributions
Some statistics follow specific theoretical
distributions exactly when certain conditions are met.
9.6.1 Chi-square Distribution ( χ2\chi^2χ2 )
- Used in
tests of independence and goodness-of-fit.
- Always
positive and skewed right.
- Shape
depends on degrees of freedom (df).
Formula for variance estimation:
χ2=(n−1)s2σ2\chi^2 = \frac{(n-1)s^2}{\sigma^2}χ2=σ2(n−1)s2
9.6.2 Student’s t-Distribution
- Used
when population standard deviation is unknown and sample size is small.
- Symmetrical
like the normal distribution but has heavier tails.
- As nnn
increases, t-distribution approaches the normal distribution.
Test statistic:
t=Xˉ−μs/nt = \frac{\bar{X} - \mu}{s/\sqrt{n}}t=s/nXˉ−μ
9.6.3 F-Distribution
- Used to
compare variances of two populations.
- Always
positive and skewed right.
- Ratio
of two independent chi-square variables divided by their degrees of
freedom.
Formula:
F=s12/σ12s22/σ22F = \frac{s_1^2 / \sigma_1^2}{s_2^2 /
\sigma_2^2}F=s22/σ22s12/σ12
9.7 Let Us
Sum Up
- Sampling
allows us to make conclusions about a population from a subset.
- Sampling
distributions describe the variability of sample statistics.
- Standard
error measures how far sample statistics are likely to be from the
population parameters.
- The
Central Limit Theorem ensures approximate normality for large samples.
- Exact
sampling distributions like chi-square, t, and F have specific
applications in hypothesis testing.
9.8 Key
Words
- Sampling
Distribution – Distribution of a statistic over repeated
sampling.
- Standard
Error – Standard deviation of a sampling
distribution.
- Central
Limit Theorem – Sampling means tend toward a normal
distribution as sample size increases.
- Chi-square
Distribution – Distribution used for categorical data
tests.
- t-Distribution – Used
for small samples with unknown population standard deviation.
- F-Distribution – Used
to compare variances.
Comments
Post a Comment