Dr.

Abu Awwad - AAUP

Arab American University, Palestine (AAUP)

HEALTHCARE STATISTICS- 152526030

Topic 4: Estimating Parameters and Determining Sample Sizes

Instructor: Dr. Abdul Fattah Abu Awwad

[email protected]

1 / 20
 Dr. Abu Awwad - AAUP

Outline

1 Learning Objectives

2 Introduction

3 Estimating a Population Proportion

4 Estimating a Population Mean

2 / 20
 Dr. Abu Awwad - AAUP Learning Objectives

Outline

1 Learning Objectives

2 Introduction

3 Estimating a Population Proportion

4 Estimating a Population Mean

3 / 20
 Dr. Abu Awwad - AAUP Learning Objectives

Learning Objectives

After studying this chapter, the student will:

1 Understand the importance and basic principles of estimation.

2 Construct a confidence interval estimate of a population proportion and

interpret such confidence interval estimates.

3 Develop the ability to determine the sample size necessary to estimate a

population proportion.

4 Construct a confidence interval estimate of a population mean, and be

able to interpret such confidence interval estimates.

5 Determine the sample size necessary to estimate a population mean.

4 / 20
 Dr. Abu Awwad - AAUP Introduction

Outline

1 Learning Objectives

2 Introduction

3 Estimating a Population Proportion

4 Estimating a Population Mean

5 / 20
 Dr. Abu Awwad - AAUP Introduction

Introduction

Medical researchers have determined so-called normal intervals for a

person’s blood pressure, cholesterol, triglycerides, and the like.

For example, the normal range of systolic blood pressure is 110 to 140.
The normal interval for a person’s triglycerides is from 30 to 200
milligrams per deciliter (mg/dl).

By measuring these variables, a physician can determine if a patient’s vital

statistics are within the normal interval or if some type of treatment is
needed to correct a condition and avoid future illnesses.

The question then is, how does one determine the so-called normal
intervals?

6 / 20
 Dr. Abu Awwad - AAUP Introduction

Introduction

Two methods of estimation are commonly used.

(1) Point Estimation:
It involves using the sample data to calculate a single number to estimate
the parameter of interest.

For instance, we might use the sample mean X̄ to estimate the population
mean µ.

We do not know how close X̄ is to µ in any given situation.

X̄ is more likely to be near the true population mean if the sample size is
large.

(2) Interval Estimation:

This technique provides a range of reasonable values that are intended to
contain the parameter of interest with a certain degree of confidence.

This range of values is called a confidence interval.

The general form of the confidence interval is

Point Estimate ± Margin of Error

7 / 20
 Dr. Abu Awwad - AAUP Introduction

Introduction

The margin of error depends on three factors:

1 Confidence level, denoted by (1 − α)100%: As the level of confidence

increases, the margin of error also increase.

2 Sample size, n: As the sample size increases, the margin of error

decrease.

3 Standard deviation, σ or S:

4 Standard deviation, σ or S: As the standard deviation increase

(observations become more variable), the margin of error also increase.

8 / 20
 Dr. Abu Awwad - AAUP Introduction

Introduction
Interpretation of a confidence interval:

Probabilistic Interpretation: In repeated sampling,

Point Estimate ± Margin of Error, will in the long run include the
population parameter.

Practical Interpretation: We are (1 − α)100% confident that the single

computed interval, Point Estimate ± Margin of Error, actually does
contain the true value of the population parameter.

9 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Proportion

Outline

1 Learning Objectives

2 Introduction

3 Estimating a Population Proportion

4 Estimating a Population Mean

10 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Proportion

Estimating a Population Proportion

Recall that the probability of success in a single trial of a binomial

experiment is p. This probability is a population proportion.

The point estimate for p is denoted by p̂ = Xn , where X is the number of

successes in the sample and n is the sample size.

The sample proportion p̂ is an unbiased estimator of the population

proportion p. That is, E (p̂) = p.

The standard error of p̂ is σp̂ or Sp̂ .

The general form of the confidence interval is constructed by

Point Estimate ± Margin of Error

11 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Proportion

Estimating a Population Proportion: Body Data Example

The sample proportion (point estimate of p) of Male is 51%.

A 95% confidence interval for the population proportion of Male is

(0.453, 0.567).

Interpretation: We are 95% confident that the interval (0.453, 0.567)

actually does contain the true value of the proportion of Males.
0.567−0.453
The margin of error E = 2
= 0.057.

Finding the sample proportion from the confidence interval:

p̂ = 0.453+0.567
2
= 0.51.

12 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Proportion

Sample Size Required to Estimate a Population Proportion

Example: If we were to conduct a survey to determine the percentage of
children (older than 1 year) who have received measles vaccinations, how many
children must be surveyed in order to be 95% confident that the sample
percentage is in error by no more than three percentage points?
1 Assume that a recent survey showed that 90% of children have received

measles vaccinations.

2 Assume that we have no prior information suggesting a possible value of

the population proportion.

13 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Proportion

Sample Size Required to Estimate a Population Proportion

 Technology

Figure: Statdisk output: Sample size required to estimate the proportion of children who have received measles
vaccinations, where the population proportion is used from a recent survey.

Figure: Statdisk output: Sample size required to estimate the proportion of children who have received measles
vaccinations with no prior information suggesting a possible value of the population proportion.

14 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Mean

Outline

1 Learning Objectives

2 Introduction

3 Estimating a Population Proportion

4 Estimating a Population Mean

15 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Mean

Estimating a Population Mean

PN
Xi
i=1
The point estimate
Pn of the population mean, µ = N
, is the sample
Xi
i=1
mean X̄ = n
.

The sample mean X̄ is an unbiased estimator of the population mean µ.

That is, E (X̄ ) = µ.

The standard error of X̄ is σX̄ or SX̄ .

Requirements: Either or both of these conditions must satisfied:
1 The population is normally distributed, and/or
2 n > 30.

16 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Mean

Estimating a Population Mean

SPSS: Analyze ⇒ Descriptive Statistics ⇒ Explore.

Dependent List: Pulse.

Click Statistics: identify the confidence level.

The sample mean (point estimate of µ) of the pulse rate is 71.77 BPM.

A 95% confidence interval for the population mean of pulse rate is

(70.39, 73.14).

Interpretation: We are 95% confident that the interval (70.39, 73.14)

actually does contain the true value of the mean of pulse rate.

17 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Mean

Sample Size Required to Estimate a Population Mean

Example: Data Set 1 “Body Data” in Appendix B (Triola et. al. (2017))
includes pulse rates of 153 randomly selected adult males, and those pulse rates
vary from a low of 40 bpm to a high of 104 bpm. Find the minimum sample
size required to estimate the mean pulse rate of adult males. Assume that we
want 99% confidence that the sample mean is within 2 bpm of the population
mean. Assume that s = 11.3 bpm, based on the value of σ = 11.3 bpm
for the sample of 153 male pulse rates.

18 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Mean

Sample Size Required to Estimate a Population Mean

 Using Statdisk

Figure: Statdisk Output: Sample size required to estimate the mean pulse rate of adult males based on the value
σ = 11.3 bpm.

Interpretation: A simple random sample of size of 212 is needed to reach a

desired precision of ±2 bpm at 99% confidence.

19 / 20
 Dr. Abu Awwad - AAUP Estimating a Population Mean

The End

20 / 20