AP Unit 5 – Sampling Distributions
TPS Chapter 7
Sampling Distribution: The sampling distribution of a statistic is the distribution of values for
the statistic for all possible samples of a given size from a given population.
The sampling distribution of a statistic can be simulated by generating repeated random
samples from a population. (Think Reese’s Pieces simulation applet)
Central Limit Theorem (CLT): The CLT states that when the sample size is sufficiently large, a
sampling distribution of the mean of a random variable will be approximately normally
distributed. The CLT requires that the sample values are independent of each other and that n
is sufficiently large.
Unbiased estimator: An estimator (statistic) is unbiased if, on average, the value of the
estimator is equal to the population parameter. (The statistics center at the parameter.)
Point Estimate: A sample statistic is a point estimator of the corresponding population
parameter.
You should be able to:
Calculate the probability that a particular value lies in a given interval of a normal
distribution.
Determine the interval associated with a given area in a normal distribution.
Estimate sampling distributions using simulation.
Explain why an estimator is or is not unbiased.
Calculate estimates for a population parameter. (sample statistics)
Determine the parameters (mean and standard deviation) of a sampling distribution for
sample proportions, the difference in sample proportions, sample means, and the
difference in sample means.
Determine whether a sampling distribution can be described as approximately normal.
Interpret probabilities and parameters (mean and standard deviation). Probabilities and
parameters for a sampling distribution should be interpreted using appropriate units
and within the context of a specific population.
Sampling Distributions for Proportions (Categorical Variables)
One Sample Two Samples
𝑝1 − 𝑝2 = difference in the true
Parameter p = true proportion
proportions
𝑝̂1 − 𝑝̂2 = difference in the sample
Sample 𝑝̂ = sample proportion
proportions
Large Counts Rule: Large Counts for BOTH samples:
Shape of the sampling
𝑛𝑝 ≥ 10 𝑛1 𝑝1 ≥ 10 𝑛2 𝑝2 ≥ 10
distribution is approx. normal IF
and and and
the large counts condition is met
𝑛(1 − 𝑝) ≥ 10 𝑛1 (1 − 𝑝1 ) ≥ 10 𝑛2 (1 − 𝑝2 ) ≥ 10
Mean of the sampling
𝜇𝑝̂ = 𝑝 𝜇𝑝̂1 −𝑝̂2 = 𝑝1 − 𝑝2
distribution
Standard Deviation of the 𝑝(1 − 𝑝) 𝑝1 (1 − 𝑝1 ) 𝑝2 (1 − 𝑝2 )
sampling distribution 𝜎𝑝̂ = √ 𝜎𝑝̂1 −𝑝̂2 = √ +
𝑛 𝑛1 𝑛2
10% Rule must be met for both
Condition to establish 10% Rule:
samples
independence when sampling n < .10(population)
n < .10(population)
without replacement (in order to or
or
use standard deviation formula)* Population > 10 x n
Population > 10 x n
Sampling Distributions for Means (Quantitative Variables)
One Sample Two Samples
𝜇1 − 𝜇2 = difference in the true
Parameter 𝜇 = true mean
means
𝑥̅1 − 𝑥̅2 = difference in the sample
Sample 𝑥̅ = sample mean
means
𝑛 ≥ 30(according to the CLT) For BOTH populations/samples:
Shape of the sampling OR 𝑛 ≥ 30(according to the CLT)
distribution is approx. normal IF the population is OR
approx..normal the population is approx..normal
Mean of the sampling
𝜇𝑥̅ = 𝜇 𝜇𝑥̅1 −𝑥̅2 = 𝜇1 − 𝜇2
distribution
Standard Deviation of the 𝜎 𝜎12 𝜎22
𝜎𝑥̅ = 𝜎𝑥̅1 −𝑥̅ 2 = √ +
sampling distribution √𝑛 𝑛1 𝑛2
10% Rule must be met for both
Condition to establish 10% Rule:
samples
independence when sampling n < .10(population)
n < .10(population)
without replacement (in order to or
or
use standard deviation formula)* Population > 10 x n
Population > 10 x n
*If sampling without replacement, the standard deviation of the sample proportion is smaller than what
is given by the formula above. If the 10% rule is met, the difference is negligible.