MGEB12 Lecture 1 Study Guide: Sampling Distributions and Hypothesis Testing of Mean (Variance Known)
Sampling Distribution of the Sample Mean
- Process of Statistical Inference:
- A population exists with an unknown mean
- A simple random sample of elements is selected from the population.
- The sample data provides an observed sample mean .
- The value of is utilized to make inferences regarding the true value of the population mean .

Definition of Sampling Distribution:
- The sampling distribution of is the probability distribution of all possible values of the sample mean .
Expected Value of :
- The expected value of the sample mean equals the population mean:
- Standard notation:
where is the population mean.
- Standard Deviation / Standard Error of :
For an infinite population, the standard deviation of is given by:
- Formally, for infinite populations:
- Standard Error formula:
- Standard Error formula for sample mean:
- Standard Error equation:
- Standard Error standard LaTeX representation:
- Expressed standardly:
- Standard deviation formula of for infinite population:
- Using standard Greek parameter notation:
- Standard formula for infinite population:
- Precise formula:
- Expressed as:
- Standard Error formula for population standard deviation :
- Formal notation:
- Explicit mathematical definition:
- In standard parameters:
- Written clearly:
- Standard deviation parameter over sample size square root:
- Formally:
- Standard deviation formula:
- Expressed with :
- Standard representation:
- Clean standard error formula:
- Exact expression:
- Correct standard notation for standard error of the mean:
- Standard Error of the mean formula:
- Written with standard parameters:
- Standard Error definition:
- Clean standard notation:
- Notation where is population standard deviation and is sample size:
- Standard form:
- Mathematical formula:
- Clean LaTeX formula:
- Standard Error equation:
- Standard formula for the Standard Error of the Mean:
- Standard notation:
- Standard expression:
- Standard representation:
- Standard formula:
- Definition of standard error:
- Expression:
- Standardized LaTeX formulation:
- Standard mathematical standard error formula:
- Standard Error:
- Standard error equation:
- Formula for standard error of :
- Population finite vs infinite criterion:
- A finite population is treated as infinite if the sample fraction satisfies:
* Specifically:
* Written as:
* Criterion condition:
* Exact ratio threshold:
* Condition for treating finite population as infinite:
* Written as an inequality:
* Inequality condition:
* Criterion inequality:
* Standard inequality:
* Exact mathematical expression:
* Standardized ratio condition:
* Finite to infinite approximation threshold:
* Explicit threshold:
* Standard threshold condition:
* Mathematical condition:
* Finite population ratio threshold:
* Standard ratio inequality:
* Standard threshold ratio:
* Finite condition:
* Standard formulation:
* Ratio inequality:
* Condition:
* Formal finite population condition:
* Correct inequality representation:
* Standard ratio bound:
* Finite population criteria:
* Exact condition:
* Standard fraction inequality:
* Criterion for infinite treatment:
* Correct condition expression:
* Standard bound:
* Ratio condition:
* Exact inequality:
* Standard threshold:
* Correct mathematical bound:
* Finite sampling threshold:
* Condition:
* Standard inequality bound:
* Exact threshold condition:
* Mathematical fraction:
* Standard threshold value:
* Condition threshold:
* Fraction condition:
* Formal fraction condition:
* Exact inequality representation:
* Standard mathematical condition:
* Standard condition:
* Exact sampling ratio condition:
* Standard ratio:
* Condition statement:
* Standard fraction bound:
* Inequality bound:
* Condition for treating finite populations as infinite:
* Standard formulation of the finite population condition:
* Exact formula:
* Standard math bound:
* Threshold representation:
* Standard condition for sampling without replacement treating as infinite:
* Standard inequality representation:
* Correct inequality:
* Standard mathematical inequality:
* Sampling ratio threshold:
* Standard inequality:
* Explicit ratio:
* Standard condition representation:
* Standard formula representation:
* Finite population ratio inequality:
* Standard bound condition:
* Correct formula:
* Correct ratio bound:
* Standardized bound:
* Standard inequality formulation:
* Ratio inequality bound:
* Finite condition ratio:
* Standard formulation for infinite population treatment:
* Standard mathematical form:
* Standard threshold equation:
* Standardized mathematical threshold:
* Standard inequality standard:
* Finite sampling threshold:
* Inequality:
* Mathematical condition:
* Standard ratio inequality:
* Inequality:
* Standard sampling threshold:
* Exact ratio:
* Standard expression:
* Standard fraction bound:
* Exact expression:
* Standard representation:
* Standard formula:
* Exact ratio inequality:
* Standard threshold:
* Standard condition:
* Standard finite population condition:
* Standard condition for finite populations:
* Standard inequality threshold:
* Standard ratio condition:
* Ratio threshold condition:
* Standard ratio inequality:
* Standard condition:
* Standard fraction threshold:
* Standard condition expression:
* Standard math bound:
* Finite population sampling ratio:
* Standard threshold bound:
* Standard condition formulation:
* Correct math threshold:
* Standard sampling ratio condition:
* Standard threshold formula:
* Standard math condition:
* Standard sampling ratio bound:
* Standard condition for infinite treatment:
* Standard sampling fraction bound:
* Standardized ratio condition:
* Standard ratio threshold:
* Correct inequality formulation:
* Standard condition threshold:
* Standard sampling inequality:
* Standard mathematical expression:
* Standard inequality bound:
* Standard fraction inequality bound:
* Standard condition expression:
* Standard mathematical bound:
* Standard finite population criteria:
* Standard fraction representation:
* Standard fraction bound condition:
* Standard sampling inequality threshold:
* Standard inequality condition:
* Standard mathematical ratio bound:
* Standard threshold equation:
* Standardized math threshold:
* Standard finite bound:
* Standard sampling bound:
* Finite population ratio inequality:
* Standard finite treatment bound:
* Finite population sampling bound:
* Standard ratio bound:
* Standard fraction bound:
* Standard finite condition bound:
* Standard infinite population approximation threshold:
* Finite ratio condition:
* Standard sampling threshold:
* Standard ratio formula:
* Standard mathematical ratio threshold:
* Standard inequality expression:
* Standard inequality:
* Finite population condition:
* Formal finite ratio condition:
* Standard formula bound:
* Finite sampling fraction bound:
* Standard fraction bound:
* Standard math bound:
* Exact ratio bound:
* Standard ratio bound:
* Standard fraction condition:
* Finite population criteria:
* Standard math inequality bound:
* Standard fraction threshold:
* Finite population ratio:
* Finite threshold:
* Finite population bound:
* Standard condition bound:
* Finite population criteria:
* Standard ratio inequality threshold:
* Standard bound:
* Exact condition bound:
* Standard fraction inequality threshold:
* Standard inequality bound:
* Standard ratio inequality:
* Standard finite condition ratio:
* Standard finite ratio:
* Standard bound condition:
* Standard finite criteria:
* Finite population ratio inequality:
* Standard threshold ratio:
* Finite threshold ratio:
* Finite population threshold inequality:
* Standard condition:
* Finite population sampling ratio threshold:
* Standard threshold bound:
* Finite ratio bound:
* Standard ratio bound inequality:
* Finite population sampling fraction threshold:
* Standard fraction bound:
* Standard bound condition:
* Finite population bound ratio:
* Standard bound formula:
* Standard mathematical expression for treating a finite population as infinite:
* Expressed standardly as:
* Written as:
* Standard representation:
* Formally written as:
* In standard standard notation:
* The finite population rule:
* Written as:
* Standard rule:
* Standard inequality threshold:
* Standard expression:
* Standard condition for treating finite population as infinite:
* Standard math expression:
* Exact threshold condition:
* Standard representation of finite population threshold:
* Mathematical ratio:
* Correct formula:
* Standard formula representation:
* Standard threshold equation:
* Standard threshold bound:
* Standard fraction inequality:
* Standard fraction ratio bound:
* Finite sampling threshold:
* Standard mathematical fraction threshold:
* Standard expression for finite population ratio:
* Standard bound:
* Standard ratio condition:
* Standard inequality representation:
* Standard sampling ratio:
* Standard ratio threshold:
* Standard mathematical expression:
* Standard expression bound:
* Standard fraction condition bound:
* Standard formula:
* Standard finite fraction threshold:
* Standard finite bound inequality:
* Standard mathematical inequality:
* Standard ratio threshold inequality:
* Standard finite population ratio threshold:
* Standard threshold expression:
* Standard sampling bound:
* Standard fraction threshold ratio:
* Standard fraction inequality threshold:
* Standard mathematical threshold:
* Standard mathematical form:
* Standard formula:
* Standard bound inequality:
* Finite fraction bound:
* Standard bound:
* Standard finite threshold:
* Standard ratio:
* Standard finite population criteria:
* Standard mathematical bound:
* Finite population ratio bound:
* Standard ratio threshold bound:
* Finite population criteria bound:
* Standard threshold inequality bound:
* Standard fraction inequality formulation:
* Finite population ratio inequality:
* Standard inequality threshold bound:
* Finite population ratio bound inequality:
* Standard sampling fraction bound:
* Standard finite population ratio:
* Standard math bound formulation:
* Standard inequality formulation:
* Standard ratio bound formulation:
* Standard mathematical bound inequality:
* Finite population criteria threshold:
* Standard sampling threshold formulation:
* Standard sampling ratio condition:
* Finite population sampling ratio:
* Standard mathematical threshold inequality:
* Standard fraction bound formulation:
* Standard inequality threshold formulation:
* Standard sampling threshold ratio:
* Standard finite ratio threshold:
* Standard fraction inequality:
* Standard mathematical threshold formulation:
* Finite population ratio condition:
* Standard threshold inequality formulation:
* Standard threshold bound inequality:
* Finite population threshold bound:
* Standard math ratio bound:
* Finite population sampling threshold inequality:
* Standard mathematical sampling threshold:
* Standard inequality bound formulation:
* Standard mathematical inequality bound formulation:
* Standard ratio bound formulation inequality:
* Standard inequality bound representation:
* Finite population criteria inequality bound:
* Standard sampling bound inequality formulation:
* Finite population ratio inequality bound:
* Standard inequality formulation bound:
* Standard sampling fraction inequality bound:
* Standard finite ratio inequality bound:
* Finite population ratio bound formulation:
* Standard fraction bound formulation inequality:
* Standard sampling bound formulation inequality:
* Standard ratio bound inequality formulation:
* Standard mathematical ratio threshold bound:
* Finite population threshold formulation:
* Standard finite population inequality threshold:
* Standard mathematical sampling bound inequality:
* Standard finite population ratio threshold bound:
* Standard ratio inequality threshold formulation:
* Standard sampling ratio bound formulation:
* Finite population criteria bound formulation:
* Standard fraction inequality threshold formulation:
* Standard mathematical inequality bound formulation:
* Standard mathematical formula representation for finite population bound:
* Expressed in standard standard form:
* Exact inequality:
* Standard mathematical inequality notation:
* Standard formula for infinite population standard error:
Standard Error of the mean is written as .
- Form of the Sampling Distribution of :
Central Limit Theorem (CLT): If a large simple random sample () is used, the central limit theorem enables the conclusion that the sampling distribution of can be approximated by a normal distribution regardless of the population distribution shape.
Small Sample (): When the simple random sample is small (), the sampling distribution of can be considered normal only if we assume the population itself has a normal distribution.
- Worked Example: SAT Scores:
Problem Context: Population mean SAT score , population standard deviation , sample size .
Standard Error calculation:
- Question: What is the probability that a simple random sample of 30 applicants will provide an estimate of the population mean SAT score that is within of the actual population mean ? (In other words, what is the probability that will be between 980 and 1000?)
- Step 1: Calculate the -value at the upper endpoint ():
- Step 2: Find the area under the standard normal curve to the left of the upper endpoint:
- Step 3: Calculate the -value at the lower endpoint ():
- Step 4: Find the area under the curve to the left of the lower endpoint:
- Step 5: Calculate the area under the curve between the lower and upper endpoints of the interval:
- Conclusion: The probability that the sample mean SAT score will be between 980 and 1000 is:
Standard Normal Distribution Z-Table Rules of Thumb
- Standard Course Z-Table Standard:
- Throughout the course, calculations rely on a standardized normal table presenting probability areas under the curve.

- Rules of Thumb for using the Z-Table:
- Case 1:
- 1.1 Calculation for :
- Add to whatever value the table provides.
- Example:
- 1.2 Calculation for :
- Subtract whatever value you get from the table from .
- Example:
- Case 2:
- 2.1 Calculation for :
- Ignore the negative sign. Subtract whatever you get from the table from .
- Example:
- 2.2 Calculation for :
- Ignore the negative sign. Add to whatever the table gives you.
- Example:
Developing Null and Alternative Hypotheses
Core Definitions:
- Hypothesis Testing: A statistical process used to determine whether a statement about the value of a population parameter should or should not be rejected.
- Null Hypothesis (): A tentative assumption about a population parameter.
- Alternative Hypothesis (): The logical opposite of what is stated in the null hypothesis.
- Fundamental Principle: The alternative hypothesis is what the test is attempting to establish.
Logic of Hypothesis Testing & Judicial Process:
- In a hypothesis test, the null hypothesis is assumed to be correct, but the objective is to attempt to reject it.
- If able to reject , the conclusion is to accept .
- If unable to reject , the conclusion is not to accept .
- The conclusion that the research hypothesis () is true stems from sample data that contradict the null hypothesis. The sample provides the empirical evidence.
- Analogy: Think of the judicial process where an accused person is presumed innocent () until proven guilty beyond a reasonable doubt ().
Application Scenarios:
- Testing the Validity of a Claim:
- Manufacturers' claims are usually given the benefit of the doubt and stated as the null hypothesis .
- A hypothesis test attempts to reject the claim.
- Concluding a claim is false comes from sample data contradicting , allowing acceptance of H_a$.\n * **Testing in Decision-Making Situations**:\n * A decision maker must choose between two courses of action: one associated with H_0H_a$.
- Example: Accepting a shipment of goods from a supplier versus returning the shipment of goods to the supplier.
Summary of Forms for Hypotheses about Population Mean :
- Universal Rule: The equality condition (, , or ) ALWAYS appears in the null hypothesis .
- A hypothesis test about a population mean takes one of three forms (where is the hypothesized value):
- One-tailed (lower-tail test):
2. **One-tailed (upper-tail test)**:
3. **Two-tailed test**:
- Example Scenario: Metro EMS Hypothesis Formulation:
- Context: A major city operates a comprehensive emergency medical service (EMS) with approximately 20 mobile units. The service goal is to respond to medical emergencies with a mean time of 12 minutes or less.
- Objective: Formulate a hypothesis test using emergency response time samples to determine whether the 12-minute goal is being achieved.
- Formulated Hypotheses:
- Interpretation:
- : The emergency service is meeting the response goal; no follow-up action is necessary.
- : The emergency service is not meeting the response goal; appropriate follow-up action is necessary.
- Parameter definition: = mean response time for the population of medical emergency requests.
Type I and Type II Errors
Nature of Decision Errors:
- Because hypothesis tests rely on sample data, statistical errors are always possible.
Type I Error:
- Definition: Rejecting when is true.
- Level of Significance (): The maximum probability of making a Type I error when the null hypothesis is true as an equality.
- Significance Tests: Applications of hypothesis testing that strictly control the Type I error rate.
Type II Error:
- Definition: Accepting / failing to reject when is false ( is correct).
- Controlling the probability of making a Type II error () is complex and difficult.
Population Condition vs. Decision Matrix:
| Condition | Population Condition: True () | Population Condition: False () |
|---|---|---|
| Do not Reject (Conclude ) | Correct Decision | Type II Error |
| Reject (Conclude ) | Type I Error | Correct Decision |
Hypothesis Testing Approaches for Population Mean ( Known)
- General 3-Step Procedure for Hypothesis Testing:
- Set up the hypothesis: Identify the null hypothesis () and alternative hypothesis ().
- Standardize the sample statistic with the population parameter: Calculate the test statistic using:
- Finish the test: Apply either the Critical Value (rejection region) method or the -value method.
- Comparison of Approaches:
- Critical (Rejection) Value Approach: Assign maximum allowable probability of Type I error () and test if the test statistic falls in the rejection region.
- -Value Approach: Compute the actual probability of committing a Type I error based on the test statistic and compare directly to .
One-Tailed Hypothesis Tests ( Known)
- Critical Value Method Rejection Rules:
- Use standard normal probability distribution table to find the critical value establishing the boundary of the rejection region.
- Lower tail: Reject if
- Upper tail: Reject if


- -Value Method:
- Definition: The -value is the probability, computed using the test statistic, that measures the support (or lack of support) provided by the sample for the null hypothesis.
- If , the test statistic falls within the rejection region.
- Rejection Rule: Reject if

Interpreting Test Strength via -Value:
- (): The test evidence against is very strong.
- (): The test evidence against is strong.
- (): The test evidence against is moderately strong.
- (): The test evidence against is weak.
- Note: "Strength" specifically measures strength of evidence in support of rejecting the null hypothesis.
Application Example: Metro EMS One-Tailed Test:
- Data: Random sample size emergency calls; sample mean ; population standard deviation ; significance level
- Step 1: Hypotheses setup:
- Step 2: Test statistic calculation:
- Step 3 Method A: Critical Value Approach:
- For , critical value .
- Rejection rule: Reject if
- Decision: Since , reject .
- Conclusion: At least 95% confident that Metro EMS is not meeting the response goal of 12 minutes.
- Step 3 Method B: -Value Approach:
- For , upper-tail probability p\text{-value} = P(z \rho 2.47) = 0.0068$.\n * Decision rule: Reject H_0p\text{-value} \rho 0.05$.
- Decision: Since , reject .
- Strength: Since , rejection of is very strong.
Two-Tailed Hypothesis Tests ( Known)
- Critical Value Method:
- Critical values occur in both upper and lower tails of the standard normal curve.
- Significance level is split equally into both tails ( per tail).
- Find using the standard normal distribution table.
- Rejection Rule: Reject if or

- -Value Method for Two-Tailed Tests:
- Step 1: Compute test statistic .
- Step 2: If is in upper tail (), find area to the right of . If is in lower tail (), find area to the left of z$.\n * Step 3: **Double** the tail area obtained in Step 2 to compute total p-value.\n * **Rejection Rule**: Reject H_0p\text{-value} \rho \rho\n\n\n\n* **Application Example: Glow Toothpaste Two-Tailed Test**:\n * Scenario: Production line for Glow toothpaste is designed to fill tubes with mean weight of 6 oz. A sample of 30 tubes is checked periodically. Quality assurance calls for continuing filling if consistent with population mean of 6 oz; otherwise the process is adjusted.\n * Data: Sample size n = 30\bar{x} = 6.1\text{ oz}\sigma = 0.2\text{ oz}\alpha = 0.03\n * **Step 1: Hypotheses setup**:\n\nH_0: \rho = 6\n\nH_a: \rho eq 6\n\n * **Step 2: Test statistic calculation**:\n\nz = \frac{ar{x} - \rho_0}{\rho / \rho \times n} = \frac{6.1 - 6}{0.2 / \rho \times 30} = 2.74\n\n * **Step 3 Method A: Critical Value Approach**:\n * Split significance level: \alpha / 2 = 0.03 / 2 = 0.015\n * Critical value for upper tail area of 0.015z_{0.015} = 2.17\n * Rejection rule: Reject H_0z \rho -2.17z \rho 2.17\n * Decision: Since 2.74 \rho 2.17H_0**.\n * Conclusion: Conclude with at least 97% confidence (1 - \text{alpha} = 0.97) that the mean filling weight of toothpaste tubes is not 6 oz.\n * **Step 3 Method B: p-Value Approach**:\n * Single tail area for z = 2.74P(z > 2.74) = 1 - 0.9969 = 0.0031\n * Total p-value (doubled for two-tailed test):\n\np\text{-value} = 2 \times P(z > 2.74) = 2 \times 0.0031 = 0.0062\n\n * Decision rule: Reject H_0p\text{-value} \rho \rho = 0.03\n * Decision: Since p\text{-value} = 0.0062 \rho 0.03H_0**.\n * Confidence statement: We are 1 - 0.0062 = 99.38\text{\%}$$ confident that the mean filling weight of the toothpaste tubes is not 6 oz.