Statistics for

Managers

P-Value, Estimation and Confidence Intervals

Dr. Raheel Akhtar,
Assistant Professor,
Department of Business and Public Administration
Emerson University Multan
E-mail: raheel.Akhtar@eum.edu.pk
Chapter Objectives:
Understand the Concept of P-value:
•Explain the meaning of the p-value in hypothesis testing.
•Interpret p-values in the context of statistical significance.
Distinguish Between Point and Interval Estimation:
•Define and differentiate point estimation and interval estimation.
•Explain the role of sample statistics in estimating population parameters.
Construct Confidence Intervals:
•Develop confidence intervals for means, proportions, and variances.
•Understand the impact of sample size, confidence level, and variability on the width of confidence intervals.
Analyze the Relationship Between P-values and Confidence Intervals:
•Explain how confidence intervals relate to hypothesis testing outcomes.
•Use confidence intervals to infer the possible range of population parameters.
Apply Z-distribution and T-distribution in Estimation:
•Identify when to use z-scores versus t-scores for constructing confidence intervals.
•Understand the assumptions required for each distribution.
Assess the Reliability and Accuracy of Statistical Estimates:
•Evaluate the factors that influence the precision of estimates, including sample size and population variability.
•Discuss the limitations and potential errors in estimation and confidence interval construction.
P-value
• The p-value measures the probability of obtaining a test
statistic as extreme as the observed one, assuming the null
hypothesis ( H0) is true. It helps decide whether to reject
H0 in hypothesis testing.
Steps to Calculate P-value
• 1. Identify the Test and Distribution
• Based on the problem, determine the appropriate test
statistic (e.g., z-test, t-test).
• Identify the distribution of the test statistic (e.g., normal, t-
distribution)
2. Calculate the Test Statistic
• Use the formula specific to your test:
Z-test vs t-test
Z-test vs t-test
• 1. Z-Test is used for large samples or when the population standard
deviation is known.
• 2. T-Test is used for small samples or when the population standard
deviation is unknown.
• 3. The t-distribution is broader (with thicker tails) than the z-
distribution for small sample sizes, accounting for more uncertainty.
Estimation and Confidence Intervals

• Estimation is a fundamental concept in statistics, enabling researchers and

decision-makers to infer population characteristics based on sample data.
•A rough calculation of the value, number, quantity, or extent of something.
"estimations of protein concentrations"
•Mean estimation is a statistical inference problem in which a sample is used to
produce a point estimate of the mean of an unknown distribution. The problem is
typically solved by using the sample mean as an estimator of the population mean.
• This chapter delves into the key concepts of Point Estimation, Interval
Estimation, and Confidence Intervals, and their applications in managerial and
business contexts.
1. Point Estimation and Interval Estimation

•1.1 Point Estimation

•A point estimate is a single value derived from sample data that serves as the best
estimate of a population parameter.
 Example: If the average height of a sample of 50 people is 165 cm, this value (165
cm) is the point estimate for the population mean height.
•Key Characteristics of a Good Point Estimator:
1. Unbiasedness: The expected value of the estimator equals the true population
parameter.
2. Efficiency: The estimator has the smallest variance among all unbiased estimators.
3. Consistency: As sample size increases, the estimator converges to the true parameter.
1. Point Estimation and Interval
Estimation
•1.2 Interval Estimation

•An interval estimate provides a range of values within which the population
parameter is likely to lie, accompanied by a level of confidence (e.g., 95%).
 Example: If the average height of a sample is 165 cm with a 95% confidence
interval of ±5 cm, the population mean is likely to lie between 160 cm and 170
cm.
2. Confidence Intervals for Means and Proportions

•2.1 Confidence Interval for the Mean (When Population Standard Deviation is Known)

•A confidence interval shows the probability that a parameter will fall between a pair of values around the
mean. Confidence intervals show the degree of uncertainty or certainty in a sampling method. They are
constructed using confidence levels of 95% or 99%.

•The formula for a confidence interval (CI) for the population mean is:
Example 1: Confidence Interval for the Mean
• A manager at a textile company wants to estimate the average monthly production
in units. A random sample of 50 months shows a mean production of 1,200 units
with a population standard deviation of 100 units. Construct a 95% confidence
interval for the mean.

• Interpretation: The manager can be 95% confident that the average monthly production lies
between 1,172.29 and 1,227.71 units.
Population Standard Deviation (σ)
Known
• If σ is known, the confidence interval is:
Example:
• A Karachi-based textile company wants to estimate the average monthly
income of its workers. A random sample of 36 workers reveals a sample
mean (̅x) of PKR 25,000 and a known population standard deviation (σ)
of PKR 5,000. Construct a 95% confidence interval.
2.2 Confidence Interval for the Mean (When
Population Standard Deviation is Unknown)
•If the population standard deviation (σ\sigma σ) is unknown, the sample standard deviation (s) is used, and the
t-distribution is applied:
Example 2: Confidence Interval Using t-Distribution

• A survey of 10 stores finds an average monthly sales revenue of PKR 500,000, with a sample standard
deviation of PKR 50,000. Construct a 95% confidence interval for the population mean.

• Interpretation: The true average monthly sales revenue is likely between PKR 464,241.44 and PKR
535,758.56 with 95% confidence.
2.3 Confidence Interval for Proportions

• The formula for a confidence interval for a population proportion is:

Example 3: Confidence Interval for Proportion

• In a survey of 500 customers, 120 indicated they were dissatisfied with a service. Construct a 95% confidence
interval for the proportion of dissatisfied customers.

• Interpretation: The true proportion of dissatisfied customers is likely between 20.24% and 27.76% with
95% confidence.
3. Interpretation of Confidence Intervals

1. Confidence Level: Indicates the degree of certainty (e.g., 95%) that the interval
contains the population parameter.
2. Width of Interval:
o A narrower interval indicates higher precision but requires a larger sample
size.
o A wider interval reflects less precision and may result from smaller sample
sizes or higher variability.
3. Practical Use: Managers and decision-makers use confidence intervals to
estimate population parameters while accounting for uncertainty.
Practical Applications
1.Banking Sector: Estimating the average loan repayment period based
on a sample of borrowers.
2.Retail: Determining the proportion of customers preferring specific
product categories in metropolitan areas.
3.Healthcare: Estimating the average wait time for patients in public
hospitals like Nishtar Hospital, Multan.
4.Education: Gauging the percentage of students using e-learning
platforms in private universities.
Conclusion

• Understanding and applying point estimation and confidence

intervals allows managers to make informed decisions in uncertain
environments.
• Whether estimating average sales, customer satisfaction, or
operational efficiency, confidence intervals provide a range of
plausible values for population parameters, fostering data-driven
decision-making.
Practice Questions
1. A sample of 50 students from a Lahore university has an average GPA of 3.2 with a population
standard deviation of 0.4. Construct a 95% confidence interval for the population mean GPA.
2. A survey conducted in Karachi found that 200 out of 500 respondents prefer cash payments
over digital payments. Estimate the population proportion with a 95% confidence level.
3. A factory in Faisalabad inspects 30 products and finds the average defect rate to be 5% with a
sample standard deviation of 2%. Construct a 90% confidence interval for the defect rate.
4. A marketing firm in Multan samples 40 businesses and finds that the average monthly
advertising expenditure is PKR 100,000 with a population standard deviation of PKR 20,000.
Construct a 99% confidence interval for the population mean.
5. A study on internet usage in Pakistan reveals that 300 out of 600 participants use social media
for more than 3 hours daily. Estimate the proportion with a 90% confidence level.
Multiple-Choice Questions
• Question 1:
• What is the primary purpose of constructing a confidence interval?

A. To test a hypothesis about a population parameter

B. To estimate the range within which a population parameter lies
C. To determine the mean of a sample
D. To calculate the sample size
Question 2:
• Which of the following factors affects the width of a confidence
interval?

A. Sample size
B. Confidence level
C. Population standard deviation
D. All of the above
Question 3:
• What happens to the width of a confidence interval if the confidence
level is increased?

A. It decreases
B. It increases
C. It remains the same
D. It depends on the sample size
Question 4:
• If the population standard deviation is unknown, which statistic is
used to construct a confidence interval?

A. Z-statistic
B. T-statistic
C. F-statistic
D. Chi-square statistic
Question 5:
• A 95% confidence interval means:

A. The interval contains the population parameter 95% of the time

B. The interval contains the sample mean 95% of the time
C. The interval contains all population values
D. The interval guarantees that the population mean lies within it
Question 6:
• Which of the following increases the precision of a confidence
interval?

A. Increasing the sample size

B. Increasing the confidence level
C. Increasing the population variance
D. Decreasing the sample size
Question 7:
• For a given sample size, which confidence level will produce the
narrowest confidence interval?

A. 90%
B. 95%
C. 99%
D. 80%
Question 8:
• What does the margin of error in a confidence interval represent?

A. The range of the population parameter

B. The maximum amount the sample statistic is expected to differ from
the population parameter
C. The standard deviation of the population
D. The error in the population mean
Question 9:
• If the sample size is doubled, how does it affect the margin of error of
a confidence interval?

A. The margin of error doubles

B. The margin of error is halved
C. The margin of error remains the same
D. The margin of error decreases slightly
Question 10:
• Which of the following is NOT an assumption for constructing a
confidence interval for the population mean using a t-distribution?

A. The sample is randomly selected

B. The population follows a normal distribution
C. The sample size must be greater than 30
D. The population standard deviation is unknown