21
Estimating a Population Proportion Goal: Given a sample proportion, estimate the value of the population proportion p. Example: In a sample of 750 people, 27% said they feel that health care is the most important issue facing our state. What proportion of the population feels that health care is the most important issue?

Estimating a Population Proportion

  • Upload
    alagan

  • View
    74

  • Download
    0

Embed Size (px)

DESCRIPTION

Estimating a Population Proportion. Goal: Given a sample proportion, estimate the value of the population proportion p . - PowerPoint PPT Presentation

Citation preview

Page 1: Estimating a Population Proportion

Estimating a Population Proportion

Goal: Given a sample proportion, estimate the value of the population proportion p.

Example: In a sample of 750 people, 27% said they feel that health care is the most important issue facing our state. What proportion of the population feels that health care is the most important issue?

Page 2: Estimating a Population Proportion

Assumptions

1. The sample is a simple random sample.2. The conditions for the binomial distribution apply:

There are a fixed number of trials, the trials are independent, there are two categories of outcomes, and the probabilities remain constant for each trial.

3. The normal distribution can be used to approximate the distribution of sample proportions, since and

 Since p and q are not known, we use the sample proportion

to estimate their values. 5np 5nq

Page 3: Estimating a Population Proportion

New Notation

p = population proportion

sample proportion (of x successes in a sample of size n)nxp ˆ

pq ˆ1ˆ

Page 4: Estimating a Population Proportion

The sample proportion is the best point estimate (single value approximation) of the population proportion p.

 

Problem: Using to approximate p doesn’t convey how accurate we expect our estimate to be. To do that, we need confidence intervals

Page 5: Estimating a Population Proportion

Confidence Intervals (CI)A confidence interval is a range (or interval) of

values used to estimate the true value of the population parameter.

 A confidence level is the probability that our

confidence interval contains the true value of p. The confidence level is expressed as a probability

1- α

Page 6: Estimating a Population Proportion

Common Values

90% confidence level (α = 0.10)95% confidence level (α = 0.05)99% confidence level (α = 0.01)

Page 7: Estimating a Population Proportion

An example of a Confidence Interval

Based on our survey earlier, The 95% confidence interval estimate of the population

proportion p is: 0.235 < p < 0.305 This means that there is 95% chance that this interval

contains the actual population proportion p.  In other words, 95% of the time that we do a sample, the

confidence interval will contain the true population proportion.

Page 8: Estimating a Population Proportion

Critical ValuesA critical value is a z-score that separates

outcomes that are likely to occur from those that are unlikely to occur.

 An example: For 95% confidence interval:

Page 9: Estimating a Population Proportion

For the 95% confidence interval, α = .05

Notice that 0.025 falls above the critical value, and 0.025 falls below the opposite (negative) critical value. Each of these areas is α/2.

 

Notation

The critical value zα/2 is the positive z-value that separates the top area of α/2. -zα/2 is the boundary of the bottom area of α/2.

Page 10: Estimating a Population Proportion

Another Example

So if our confidence level was 99%, the critical value zα/2 would be the score that separates the top 0.5% of data, and –zα/2

would separate the bottom 0.5% of data.

Leaving 99% of the data between –zα/2 and zα/2

Page 11: Estimating a Population Proportion

Finding Critical Values

Example:For the 95% confidence interval, the area

above zα/2 is .025, so the area below is 1-.025 = .975

So P(z < zα/2) = .975. From the table, we find zα/2 =1.96

Page 12: Estimating a Population Proportion

Common Critical Values

90% α = .10 Critical value 1.64595% α = .05 Critical value 1.9699% α = .01 Critical value 2.575 

(listed at bottom of z-score table)

Page 13: Estimating a Population Proportion

Creating a Confidence Interval

nqpzEˆˆ

2

EppEp ˆˆ

Epˆ

EpEp ˆ,ˆ

Page 14: Estimating a Population Proportion

Margin of Error

The margin of error E is the maximum likely (with probability 1-α) difference between the observed proportion and the population proportion p.

Page 15: Estimating a Population Proportion

Summary of Procedure for finding a Confidence Interval

1. Verify the required assumptions are satisfied

2. Find the critical value that corresponds to the desired confidence level

3. Evaluate the margin of error E4. Find the values and . Write

the confidence interval5. Round values to three decimal places

Ep ˆ Ep ˆ

Page 16: Estimating a Population Proportion

ExampleIn a sample of 750 people, 27% said they feel

that health care is the most important issue facing our state.

 

95% confidence level, so

27.0ˆ p

96.12 z

Page 17: Estimating a Population Proportion

Example continued

so our confidence interval is 0.238 < p < 0.302

0318.750

)73.0)(27.0(96.1ˆˆ

2 nqpzE

3018.00318.27.0ˆ2382.00318.27.0ˆ

EpEp

Page 18: Estimating a Population Proportion

Example continued

0.238 < p < 0.302

Based on our survey results, we are 95% confident that the true percentage of Washingtonians who feel that health care is the most important issue facing the state is between 23.8% and 30.2%.

Page 19: Estimating a Population Proportion

From a Confidence IntervalIf you know a confidence interval, the middle

value is the point estimate (in this case, ). You can find it by calculating

If you know a confidence interval, the Margin of Error is half the width of the confidence interval. You can find it by calculating

2limitlower limitupper

2limitlower limitupper

Page 20: Estimating a Population Proportion

Determining Sample Size from desired Margin of Error

2

22 ˆˆE

qpzn

2

22 25.0E

zn

when is known p̂

when is not known p̂

Page 21: Estimating a Population Proportion

Homework

6.2: 5, 13, 17, 21, 27, (29)