Central Limit Theorem: Sample Means and Normal Approximation
Use the central limit theorem correctly: it supports normal approximation for sample means as n grows, but it does not make the original population normal.
Central Limit Theorem: direct answer
A second Central Limit Theorem check should focus on the distinction between the sampling distribution and the population itself: increasing n can make the distribution of x-bar approximately normal under suitable conditions, but it does not transform the underlying population measurements into a normal distribution.
This page uses central limit theorem as its single primary search focus. Every instructional block and every retained practice item is tied to that title intent rather than to a generic AP Statistics question-bank template.
Quick reference for Central Limit Theorem: Sample Means and Normal Approximation
| CLT target | Shape of the sampling distribution of a sum or mean as sample size grows. |
|---|---|
| Center of x̄ | μ |
| Standard error of x̄ | σ/√n |
| Population shape | Does not itself become normal. |
| Caution | Extreme skewness, heavy tails, or outliers may require larger n. |
Concept mastery: Central Limit Theorem: Sample Means and Normal Approximation
What the central limit theorem actually says
Under broad conditions, the standardized sum or mean of many independent observations approaches a normal distribution as sample size grows. In AP Statistics applications, the key use is deciding when a normal approximation for x̄ is reasonable.
The population does not become normal
Increasing n changes the distribution of the statistic x̄; it does not reshape the underlying population. A right-skewed population remains right-skewed even when the distribution of sample means becomes nearly normal.
Sample size interacts with severity of nonnormality
There is no universal n that guarantees a good approximation in every population. Mild skewness may require only a moderate sample, while extreme skewness, heavy tails, or influential outliers can require much larger samples and more caution.
Center and standard error do not depend on the approximation
For independent observations with finite mean μ and SD σ, x̄ has center μ and standard error σ/√n. The central limit theorem addresses shape; it is a separate question from center and spread.
Normal populations are a special easy case
If the original population is normal, the sample mean is normally distributed for every sample size under independent sampling. The CLT is most valuable when the population is not normal and n is large enough to smooth the distribution of x̄.
Worked analysis for Central Limit Theorem: Sample Means and Normal Approximation
CLT case 1: Urban Transit Riders
For urban transit riders, the source distribution is moderately left-skewed, with μ=45 and σ=10. For samples of size n=16, x̄ still has center 45 and standard error 2.500. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for urban transit riders. With only n=16 observations from a moderately left-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. Check shape only after center and standard error have been identified.
CLT case 2: Regional Hospital Visits
For regional hospital visits, the source distribution is roughly symmetric with mild tails, with μ=50 and σ=11. For samples of size n=25, x̄ still has center 50 and standard error 2.200. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for regional hospital visits. At n=25, the decision depends on how severe the roughly symmetric with mild tails source really is and whether the sampling design avoids dependence or influential extremes. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 3: Community College Placement Scores
For community college placement scores, the source distribution is bimodal but finite-variance, with μ=55 and σ=12. For samples of size n=36, x̄ still has center 55 and standard error 2.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for community college placement scores. At n=36, the decision depends on how severe the bimodal but finite-variance source really is and whether the sampling design avoids dependence or influential extremes. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 4: Warehouse Order Times
For warehouse order times, the source distribution is strongly right-skewed, with μ=60 and σ=13. For samples of size n=49, x̄ still has center 60 and standard error 1.857. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for warehouse order times. Here n=49 is comparatively large, so the averaging process substantially smooths the stated strongly right-skewed source, assuming independent observations and finite variance. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 5: Public-Library Checkouts
For public-library checkouts, the source distribution is moderately left-skewed, with μ=65 and σ=14. For samples of size n=64, x̄ still has center 65 and standard error 1.750. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for public-library checkouts. Here n=64 is comparatively large, so the averaging process substantially smooths the stated moderately left-skewed source, assuming independent observations and finite variance. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 6: Solar-Panel Output Readings
For solar-panel output readings, the source distribution is roughly symmetric with mild tails, with μ=70 and σ=9. For samples of size n=100, x̄ still has center 70 and standard error 0.900. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for solar-panel output readings. Here n=100 is comparatively large, so the averaging process substantially smooths the stated roughly symmetric with mild tails source, assuming independent observations and finite variance. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 7: School Attendance Rates
For school attendance rates, the source distribution is bimodal but finite-variance, with μ=75 and σ=10. For samples of size n=144, x̄ still has center 75 and standard error 0.833. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for school attendance rates. Here n=144 is comparatively large, so the averaging process substantially smooths the stated bimodal but finite-variance source, assuming independent observations and finite variance. Check shape only after center and standard error have been identified.
CLT case 8: Restaurant Service Times
For restaurant service times, the source distribution is strongly right-skewed, with μ=40 and σ=11. For samples of size n=9, x̄ still has center 40 and standard error 3.667. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for restaurant service times. With only n=9 observations from a strongly right-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 9: Wildlife Tag Measurements
For wildlife tag measurements, the source distribution is moderately left-skewed, with μ=45 and σ=12. For samples of size n=16, x̄ still has center 45 and standard error 3.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for wildlife tag measurements. With only n=16 observations from a moderately left-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 10: Municipal Water-Use Records
For municipal water-use records, the source distribution is roughly symmetric with mild tails, with μ=50 and σ=13. For samples of size n=25, x̄ still has center 50 and standard error 2.600. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for municipal water-use records. At n=25, the decision depends on how severe the roughly symmetric with mild tails source really is and whether the sampling design avoids dependence or influential extremes. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 11: Online Course Completion Times
For online course completion times, the source distribution is bimodal but finite-variance, with μ=55 and σ=14. For samples of size n=36, x̄ still has center 55 and standard error 2.333. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for online course completion times. At n=36, the decision depends on how severe the bimodal but finite-variance source really is and whether the sampling design avoids dependence or influential extremes. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 12: Farm Yield Measurements
For farm yield measurements, the source distribution is strongly right-skewed, with μ=60 and σ=9. For samples of size n=49, x̄ still has center 60 and standard error 1.286. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for farm yield measurements. Here n=49 is comparatively large, so the averaging process substantially smooths the stated strongly right-skewed source, assuming independent observations and finite variance. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 13: Clinic Appointment Waits
For clinic appointment waits, the source distribution is moderately left-skewed, with μ=65 and σ=10. For samples of size n=64, x̄ still has center 65 and standard error 1.250. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for clinic appointment waits. Here n=64 is comparatively large, so the averaging process substantially smooths the stated moderately left-skewed source, assuming independent observations and finite variance. Check shape only after center and standard error have been identified.
CLT case 14: Manufacturing Fill Weights
For manufacturing fill weights, the source distribution is roughly symmetric with mild tails, with μ=70 and σ=11. For samples of size n=100, x̄ still has center 70 and standard error 1.100. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for manufacturing fill weights. Here n=100 is comparatively large, so the averaging process substantially smooths the stated roughly symmetric with mild tails source, assuming independent observations and finite variance. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 15: County Commute Times
For county commute times, the source distribution is bimodal but finite-variance, with μ=75 and σ=12. For samples of size n=144, x̄ still has center 75 and standard error 1.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for county commute times. Here n=144 is comparatively large, so the averaging process substantially smooths the stated bimodal but finite-variance source, assuming independent observations and finite variance. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 16: Energy Meter Readings
For energy meter readings, the source distribution is strongly right-skewed, with μ=40 and σ=13. For samples of size n=9, x̄ still has center 40 and standard error 4.333. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for energy meter readings. With only n=9 observations from a strongly right-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 17: University Advising Durations
For university advising durations, the source distribution is moderately left-skewed, with μ=45 and σ=14. For samples of size n=16, x̄ still has center 45 and standard error 3.500. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for university advising durations. With only n=16 observations from a moderately left-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 18: Sports Training Measurements
For sports training measurements, the source distribution is roughly symmetric with mild tails, with μ=50 and σ=9. For samples of size n=25, x̄ still has center 50 and standard error 1.800. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for sports training measurements. At n=25, the decision depends on how severe the roughly symmetric with mild tails source really is and whether the sampling design avoids dependence or influential extremes. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 19: Call-Center Resolution Times
For call-center resolution times, the source distribution is bimodal but finite-variance, with μ=55 and σ=10. For samples of size n=36, x̄ still has center 55 and standard error 1.667. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for call-center resolution times. At n=36, the decision depends on how severe the bimodal but finite-variance source really is and whether the sampling design avoids dependence or influential extremes. Check shape only after center and standard error have been identified.
CLT case 20: Retail Basket Totals
For retail basket totals, the source distribution is strongly right-skewed, with μ=60 and σ=11. For samples of size n=49, x̄ still has center 60 and standard error 1.571. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for retail basket totals. Here n=49 is comparatively large, so the averaging process substantially smooths the stated strongly right-skewed source, assuming independent observations and finite variance. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 21: Lab Assay Values
For lab assay values, the source distribution is moderately left-skewed, with μ=65 and σ=12. For samples of size n=64, x̄ still has center 65 and standard error 1.500. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for lab assay values. Here n=64 is comparatively large, so the averaging process substantially smooths the stated moderately left-skewed source, assuming independent observations and finite variance. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 22: Shipping Transit Times
For shipping transit times, the source distribution is roughly symmetric with mild tails, with μ=70 and σ=13. For samples of size n=100, x̄ still has center 70 and standard error 1.300. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for shipping transit times. Here n=100 is comparatively large, so the averaging process substantially smooths the stated roughly symmetric with mild tails source, assuming independent observations and finite variance. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 23: District Test Scores
For district test scores, the source distribution is bimodal but finite-variance, with μ=75 and σ=14. For samples of size n=144, x̄ still has center 75 and standard error 1.167. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for district test scores. Here n=144 is comparatively large, so the averaging process substantially smooths the stated bimodal but finite-variance source, assuming independent observations and finite variance. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 24: Park Visitor Durations
For park visitor durations, the source distribution is strongly right-skewed, with μ=40 and σ=9. For samples of size n=9, x̄ still has center 40 and standard error 3.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for park visitor durations. With only n=9 observations from a strongly right-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 25: Airport Security Waits
For airport security waits, the source distribution is moderately left-skewed, with μ=45 and σ=10. For samples of size n=16, x̄ still has center 45 and standard error 2.500. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for airport security waits. With only n=16 observations from a moderately left-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. Check shape only after center and standard error have been identified.
CLT case 26: Pharmacy Prescription Times
For pharmacy prescription times, the source distribution is roughly symmetric with mild tails, with μ=50 and σ=11. For samples of size n=25, x̄ still has center 50 and standard error 2.200. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for pharmacy prescription times. At n=25, the decision depends on how severe the roughly symmetric with mild tails source really is and whether the sampling design avoids dependence or influential extremes. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 27: Bicycle Commute Distances
For bicycle commute distances, the source distribution is bimodal but finite-variance, with μ=55 and σ=12. For samples of size n=36, x̄ still has center 55 and standard error 2.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for bicycle commute distances. At n=36, the decision depends on how severe the bimodal but finite-variance source really is and whether the sampling design avoids dependence or influential extremes. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 28: Community Garden Yields
For community garden yields, the source distribution is strongly right-skewed, with μ=60 and σ=13. For samples of size n=49, x̄ still has center 60 and standard error 1.857. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for community garden yields. Here n=49 is comparatively large, so the averaging process substantially smooths the stated strongly right-skewed source, assuming independent observations and finite variance. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 29: Emergency Response Durations
For emergency response durations, the source distribution is moderately left-skewed, with μ=65 and σ=14. For samples of size n=64, x̄ still has center 65 and standard error 1.750. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for emergency response durations. Here n=64 is comparatively large, so the averaging process substantially smooths the stated moderately left-skewed source, assuming independent observations and finite variance. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 30: College Credit Loads
For college credit loads, the source distribution is roughly symmetric with mild tails, with μ=70 and σ=9. For samples of size n=100, x̄ still has center 70 and standard error 0.900. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for college credit loads. Here n=100 is comparatively large, so the averaging process substantially smooths the stated roughly symmetric with mild tails source, assuming independent observations and finite variance. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 31: Household Electricity Use
For household electricity use, the source distribution is bimodal but finite-variance, with μ=75 and σ=10. For samples of size n=144, x̄ still has center 75 and standard error 0.833. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for household electricity use. Here n=144 is comparatively large, so the averaging process substantially smooths the stated bimodal but finite-variance source, assuming independent observations and finite variance. Check shape only after center and standard error have been identified.
CLT case 32: River Flow Measurements
For river flow measurements, the source distribution is strongly right-skewed, with μ=40 and σ=11. For samples of size n=9, x̄ still has center 40 and standard error 3.667. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for river flow measurements. With only n=9 observations from a strongly right-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 33: Mobile Data Usage
For mobile data usage, the source distribution is moderately left-skewed, with μ=45 and σ=12. For samples of size n=16, x̄ still has center 45 and standard error 3.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for mobile data usage. With only n=16 observations from a moderately left-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 34: Food Delivery Times
For food delivery times, the source distribution is roughly symmetric with mild tails, with μ=50 and σ=13. For samples of size n=25, x̄ still has center 50 and standard error 2.600. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for food delivery times. At n=25, the decision depends on how severe the roughly symmetric with mild tails source really is and whether the sampling design avoids dependence or influential extremes. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 35: Factory Cycle Times
For factory cycle times, the source distribution is bimodal but finite-variance, with μ=55 and σ=14. For samples of size n=36, x̄ still has center 55 and standard error 2.333. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for factory cycle times. At n=36, the decision depends on how severe the bimodal but finite-variance source really is and whether the sampling design avoids dependence or influential extremes. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 36: Teacher Grading Times
For teacher grading times, the source distribution is strongly right-skewed, with μ=60 and σ=9. For samples of size n=49, x̄ still has center 60 and standard error 1.286. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for teacher grading times. Here n=49 is comparatively large, so the averaging process substantially smooths the stated strongly right-skewed source, assuming independent observations and finite variance. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 37: Regional Rainfall Totals
For regional rainfall totals, the source distribution is moderately left-skewed, with μ=65 and σ=10. For samples of size n=64, x̄ still has center 65 and standard error 1.250. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for regional rainfall totals. Here n=64 is comparatively large, so the averaging process substantially smooths the stated moderately left-skewed source, assuming independent observations and finite variance. Check shape only after center and standard error have been identified.
CLT case 38: Patient Recovery Times
For patient recovery times, the source distribution is roughly symmetric with mild tails, with μ=70 and σ=11. For samples of size n=100, x̄ still has center 70 and standard error 1.100. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for patient recovery times. Here n=100 is comparatively large, so the averaging process substantially smooths the stated roughly symmetric with mild tails source, assuming independent observations and finite variance. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 39: Store Checkout Waits
For store checkout waits, the source distribution is bimodal but finite-variance, with μ=75 and σ=12. For samples of size n=144, x̄ still has center 75 and standard error 1.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for store checkout waits. Here n=144 is comparatively large, so the averaging process substantially smooths the stated bimodal but finite-variance source, assuming independent observations and finite variance. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 40: Bus Route Delays
For bus route delays, the source distribution is strongly right-skewed, with μ=40 and σ=13. For samples of size n=9, x̄ still has center 40 and standard error 4.333. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for bus route delays. With only n=9 observations from a strongly right-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 41: Housing Repair Costs
For housing repair costs, the source distribution is moderately left-skewed, with μ=45 and σ=14. For samples of size n=16, x̄ still has center 45 and standard error 3.500. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for housing repair costs. With only n=16 observations from a moderately left-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 42: Student Reading Speeds
For student reading speeds, the source distribution is roughly symmetric with mild tails, with μ=50 and σ=9. For samples of size n=25, x̄ still has center 50 and standard error 1.800. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for student reading speeds. At n=25, the decision depends on how severe the roughly symmetric with mild tails source really is and whether the sampling design avoids dependence or influential extremes. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 43: Battery Discharge Times
For battery discharge times, the source distribution is bimodal but finite-variance, with μ=55 and σ=10. For samples of size n=36, x̄ still has center 55 and standard error 1.667. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for battery discharge times. At n=36, the decision depends on how severe the bimodal but finite-variance source really is and whether the sampling design avoids dependence or influential extremes. Check shape only after center and standard error have been identified.
CLT case 44: Water Treatment Measurements
For water treatment measurements, the source distribution is strongly right-skewed, with μ=60 and σ=11. For samples of size n=49, x̄ still has center 60 and standard error 1.571. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for water treatment measurements. Here n=49 is comparatively large, so the averaging process substantially smooths the stated strongly right-skewed source, assuming independent observations and finite variance. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 45: Package Sorting Times
For package sorting times, the source distribution is moderately left-skewed, with μ=65 and σ=12. For samples of size n=64, x̄ still has center 65 and standard error 1.500. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for package sorting times. Here n=64 is comparatively large, so the averaging process substantially smooths the stated moderately left-skewed source, assuming independent observations and finite variance. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 46: Trail Completion Times
For trail completion times, the source distribution is roughly symmetric with mild tails, with μ=70 and σ=13. For samples of size n=100, x̄ still has center 70 and standard error 1.300. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for trail completion times. Here n=100 is comparatively large, so the averaging process substantially smooths the stated roughly symmetric with mild tails source, assuming independent observations and finite variance. State the reason for the approximation rather than citing sample size as an unexplained threshold.
CLT case 47: Clinic Blood-Pressure Readings
For clinic blood-pressure readings, the source distribution is bimodal but finite-variance, with μ=75 and σ=14. For samples of size n=144, x̄ still has center 75 and standard error 1.167. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for clinic blood-pressure readings. Here n=144 is comparatively large, so the averaging process substantially smooths the stated bimodal but finite-variance source, assuming independent observations and finite variance. If extreme outliers are plausible, investigate them before trusting a tail probability based on normality.
CLT case 48: Customer Support Ratings
For customer support ratings, the source distribution is strongly right-skewed, with μ=40 and σ=9. For samples of size n=9, x̄ still has center 40 and standard error 3.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for customer support ratings. With only n=9 observations from a strongly right-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. The theorem improves the distribution of averages; it does not erase problems created by biased sampling.
CLT case 49: Machine Vibration Readings
For machine vibration readings, the source distribution is moderately left-skewed, with μ=45 and σ=10. For samples of size n=16, x̄ still has center 45 and standard error 2.500. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for machine vibration readings. With only n=16 observations from a moderately left-skewed source, normal approximation needs caution; the sample is too small to invoke a large-sample rule mechanically. Check shape only after center and standard error have been identified.
CLT case 50: District Graduation Rates
For district graduation rates, the source distribution is roughly symmetric with mild tails, with μ=50 and σ=11. For samples of size n=25, x̄ still has center 50 and standard error 2.200. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for district graduation rates. At n=25, the decision depends on how severe the roughly symmetric with mild tails source really is and whether the sampling design avoids dependence or influential extremes. A correct conclusion distinguishes the source population from the repeated-sample distribution of x̄.
CLT case 51: Commuter Parking Times
For commuter parking times, the source distribution is bimodal but finite-variance, with μ=55 and σ=12. For samples of size n=36, x̄ still has center 55 and standard error 2.000. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for commuter parking times. At n=36, the decision depends on how severe the bimodal but finite-variance source really is and whether the sampling design avoids dependence or influential extremes. The numerical standard error can be correct even when the normal-shape approximation is questionable.
CLT case 52: Workshop Completion Scores
For workshop completion scores, the source distribution is strongly right-skewed, with μ=60 and σ=13. For samples of size n=49, x̄ still has center 60 and standard error 1.857. The central limit theorem concerns the shape of the sampling distribution of the mean as sample size increases; it does not claim the original population itself becomes normal.
Approximation decision for workshop completion scores. Here n=49 is comparatively large, so the averaging process substantially smooths the stated strongly right-skewed source, assuming independent observations and finite variance. State the reason for the approximation rather than citing sample size as an unexplained threshold.
Central Limit Theorem: Sample Means and Normal Approximation: multiple-choice practice
Question 3. Sampling Distribution of a Sample Mean
A population at a state park in South Harbor during a winter readiness review has mean 70 and SD 24. For random samples of size 49, find the mean and SD of x̄ and P(x̄>74.29) under a normal/CLT approximation.
Answer: C
μx̄=μ=70. σx̄=σ√n=24√49=3.429. The cutoff has z=(74.29−70)3.429=1.251, so P(x̄>cutoff)=0.1054.
Question 5. Sampling Distribution of a Sample Mean
A population at a community bank in Desert County during a service-improvement study has mean 47 and SD 13. For random samples of size 100, find the mean and SD of x̄ and P(x̄>48.04) under a normal/CLT approximation.
Answer: B
μx̄=μ=47. σx̄=σ√n=13√100=1.3. The cutoff has z=(48.04−47)1.3=0.8, so P(x̄>cutoff)=0.2119.
Question 7. Sampling Distribution of a Sample Mean
A population at a digital learning platform in Capital Region during a weekday operations study has mean 74 and SD 21. For random samples of size 36, find the mean and SD of x̄ and P(x̄>76.8) under a normal/CLT approximation.
Answer: B
μx̄=μ=74. σx̄=σ√n=21√36=3.5. The cutoff has z=(76.8−74)3.5=0.8, so P(x̄>cutoff)=0.2119.
Question 9. Sampling Distribution of a Sample Mean
A population at a recycling program in Sunbelt district during a quarterly performance study has mean 78 and SD 20. For random samples of size 100, find the mean and SD of x̄ and P(x̄>80) under a normal/CLT approximation.
Answer: D
μx̄=μ=78. σx̄=σ√n=20√100=2. The cutoff has z=(80−78)2=1, so P(x̄>cutoff)=0.1587.
Question 11. Sampling Distribution of a Sample Mean
A population at a wildlife clinic in Atlantic Corridor during a weekday operations study has mean 86 and SD 13. For random samples of size 100, find the mean and SD of x̄ and P(x̄>87.62) under a normal/CLT approximation.
Answer: C
μx̄=μ=86. σx̄=σ√n=13√100=1.3. The cutoff has z=(87.62−86)1.3=1.246, so P(x̄>cutoff)=0.1064.
Question 13. Sampling Distribution of a Sample Mean
A population at a community bank in North Valley during a service-improvement study has mean 94 and SD 17. For random samples of size 25, find the mean and SD of x̄ and P(x̄>95.7) under a normal/CLT approximation.
Answer: C
μx̄=μ=94. σx̄=σ√n=17√25=3.4. The cutoff has z=(95.7−94)3.4=0.5, so P(x̄>cutoff)=0.3085.
Question 15. Sampling Distribution of a Sample Mean
A population at a school district in Westview during a two-month observation window has mean 88 and SD 18. For random samples of size 49, find the mean and SD of x̄ and P(x̄>90.57) under a normal/CLT approximation.
Answer: D
μx̄=μ=88. σx̄=σ√n=18√49=2.571. The cutoff has z=(90.57−88)2.571=0.999, so P(x̄>cutoff)=0.1588.
Question 17. Sampling Distribution of a Sample Mean
A population at a public health department in Coastal Plains during a fall 2026 audit has mean 58 and SD 24. For random samples of size 100, find the mean and SD of x̄ and P(x̄>59.92) under a normal/CLT approximation.
Answer: C
μx̄=μ=58. σx̄=σ√n=24√100=2.4. The cutoff has z=(59.92−58)2.4=0.8, so P(x̄>cutoff)=0.2119.
Question 19. Sampling Distribution of a Sample Mean
A population at a regional airport authority in Pine Ridge during a service-improvement study has mean 49 and SD 9. For random samples of size 64, find the mean and SD of x̄ and P(x̄>50.41) under a normal/CLT approximation.
Answer: B
μx̄=μ=49. σx̄=σ√n=9√64=1.125. The cutoff has z=(50.41−49)1.125=1.253, so P(x̄>cutoff)=0.105.
Question 21. Sampling Distribution of a Sample Mean
A population at a public health department in Central County during a two-month observation window has mean 81 and SD 19. For random samples of size 100, find the mean and SD of x̄ and P(x̄>82.9) under a normal/CLT approximation.
Answer: A
μx̄=μ=81. σx̄=σ√n=19√100=1.9. The cutoff has z=(82.9−81)1.9=1, so P(x̄>cutoff)=0.1587.
Question 23. Sampling Distribution of a Sample Mean
A population at a solar installer in South Harbor during a spring 2027 pilot has mean 74 and SD 11. For random samples of size 36, find the mean and SD of x̄ and P(x̄>76.29) under a normal/CLT approximation.
Answer: B
μx̄=μ=74. σx̄=σ√n=11√36=1.833. The cutoff has z=(76.29−74)1.833=1.249, so P(x̄>cutoff)=0.1058.
Question 25. Sampling Distribution of a Sample Mean
A population at a county election office in Midwest consortium during a semester-long cohort study has mean 51 and SD 20. For random samples of size 64, find the mean and SD of x̄ and P(x̄>54.12) under a normal/CLT approximation.
Answer: B
μx̄=μ=51. σx̄=σ√n=20√64=2.5. The cutoff has z=(54.12−51)2.5=1.248, so P(x̄>cutoff)=0.106.
Question 27. Sampling Distribution of a Sample Mean
A population at a food safety laboratory in Mountain Region during a community outreach cycle has mean 98 and SD 8. For random samples of size 49, find the mean and SD of x̄ and P(x̄>99.43) under a normal/CLT approximation.
Answer: C
μx̄=μ=98. σx̄=σ√n=8√49=1.143. The cutoff has z=(99.43−98)1.143=1.251, so P(x̄>cutoff)=0.1054.
Question 29. Sampling Distribution of a Sample Mean
A population at a county library in New England network during a service-improvement study has mean 104 and SD 23. For random samples of size 64, find the mean and SD of x̄ and P(x̄>107.6) under a normal/CLT approximation.
Answer: B
μx̄=μ=104. σx̄=σ√n=23√64=2.875. The cutoff has z=(107.6−104)2.875=1.249, so P(x̄>cutoff)=0.1059.
Question 31. Sampling Distribution of a Sample Mean
A population at a state park in Metro East during a follow-up evaluation period has mean 57 and SD 17. For random samples of size 49, find the mean and SD of x̄ and P(x̄>58.21) under a normal/CLT approximation.
Answer: C
μx̄=μ=57. σx̄=σ√n=17√49=2.429. The cutoff has z=(58.21−57)2.429=0.498, so P(x̄>cutoff)=0.3092.
Question 33. Sampling Distribution of a Sample Mean
A population at a solar installer in Mountain Region during a quarterly performance study has mean 72 and SD 16. For random samples of size 49, find the mean and SD of x̄ and P(x̄>74.29) under a normal/CLT approximation.
Answer: C
μx̄=μ=72. σx̄=σ√n=16√49=2.286. The cutoff has z=(74.29−72)2.286=1.002, so P(x̄>cutoff)=0.1582.
Question 35. Sampling Distribution of a Sample Mean
A population at a recycling program in Prairie District during a winter readiness review has mean 107 and SD 13. For random samples of size 64, find the mean and SD of x̄ and P(x̄>109.0) under a normal/CLT approximation.
Answer: A
μx̄=μ=107. σx̄=σ√n=13√64=1.625. The cutoff has z=(109.0−107)1.625=1.249, so P(x̄>cutoff)=0.1058.
Question 1. Sampling Distribution of a Sample Mean
A population at a regional hospital in Lakeside district during a follow-up evaluation period has mean 70 and SD 13. For random samples of size 36, find the mean and SD of x̄ and P(x̄>71.08) under a normal/CLT approximation.
Answer: B
μx̄=μ=70. σx̄=σ√n=13√36=2.167. The cutoff has z=(71.08−70)2.167=0.498, so P(x̄>cutoff)=0.3091.
Central Limit Theorem: Sample Means and Normal Approximation: free-response practice
FRQ set 3: Sampling Distribution of a Sample Mean
Scenario. A population at a regional hospital in Riverbend during a six-week field trial has mean 47 and SD 10. For random samples of size 25, find the mean and SD of x̄ and P(x̄>49) under a normal/CLT approximation.
- Identify the statistic and describe its sampling distribution target.
- Verify independence and the normal/large-count or central-limit condition.
- Calculate the sampling-distribution center, standard deviation, standardized value, and requested probability.
- Interpret the probability across repeated random samples of the stated size.
Model response
μx̄=μ=47. σx̄=σ√n=10√25=2. The cutoff has z=(49−47)2=1, so P(x̄>cutoff)=0.1587.
FRQ set 5: Sampling Distribution of a Sample Mean
Scenario. A population at a grocery cooperative in Westview during a regional benchmarking study has mean 97 and SD 22. For random samples of size 25, find the mean and SD of x̄ and P(x̄>100.5) under a normal/CLT approximation.
- Identify the statistic and describe its sampling distribution target.
- Verify independence and the normal/large-count or central-limit condition.
- Calculate the sampling-distribution center, standard deviation, standardized value, and requested probability.
- Interpret the probability across repeated random samples of the stated size.
Model response
μx̄=μ=97. σx̄=σ√n=22√25=4.4. The cutoff has z=(100.5−97)4.4=0.8, so P(x̄>cutoff)=0.2119.
FRQ set 7: Sampling Distribution of a Sample Mean
Scenario. A population at a state park in Pacific Northwest during a yearly program evaluation has mean 86 and SD 13. For random samples of size 36, find the mean and SD of x̄ and P(x̄>88.71) under a normal/CLT approximation.
- Identify the statistic and describe its sampling distribution target.
- Verify independence and the normal/large-count or central-limit condition.
- Calculate the sampling-distribution center, standard deviation, standardized value, and requested probability.
- Interpret the probability across repeated random samples of the stated size.
Model response
μx̄=μ=86. σx̄=σ√n=13√36=2.167. The cutoff has z=(88.71−86)2.167=1.251, so P(x̄>cutoff)=0.1055.
FRQ set 9: Sampling Distribution of a Sample Mean
Scenario. A population at a city recreation department in Mountain Region during a service-improvement study has mean 46 and SD 15. For random samples of size 100, find the mean and SD of x̄ and P(x̄>46.75) under a normal/CLT approximation.
- Identify the statistic and describe its sampling distribution target.
- Verify independence and the normal/large-count or central-limit condition.
- Calculate the sampling-distribution center, standard deviation, standardized value, and requested probability.
- Interpret the probability across repeated random samples of the stated size.
Model response
μx̄=μ=46. σx̄=σ√n=15√100=1.5. The cutoff has z=(46.75−46)1.5=0.5, so P(x̄>cutoff)=0.3085.
FRQ set 11: Sampling Distribution of a Sample Mean
Scenario. A population at a regional manufacturer in Desert County during a follow-up evaluation period has mean 49 and SD 15. For random samples of size 100, find the mean and SD of x̄ and P(x̄>50.2) under a normal/CLT approximation.
- Identify the statistic and describe its sampling distribution target.
- Verify independence and the normal/large-count or central-limit condition.
- Calculate the sampling-distribution center, standard deviation, standardized value, and requested probability.
- Interpret the probability across repeated random samples of the stated size.
Model response
μx̄=μ=49. σx̄=σ√n=15√100=1.5. The cutoff has z=(50.2−49)1.5=0.8, so P(x̄>cutoff)=0.2119.
FRQ set 13: Sampling Distribution of a Sample Mean
Scenario. A population at a food safety laboratory in Atlantic Corridor during a weekday operations study has mean 84 and SD 9. For random samples of size 64, find the mean and SD of x̄ and P(x̄>85.12) under a normal/CLT approximation.
- Identify the statistic and describe its sampling distribution target.
- Verify independence and the normal/large-count or central-limit condition.
- Calculate the sampling-distribution center, standard deviation, standardized value, and requested probability.
- Interpret the probability across repeated random samples of the stated size.
Model response
μx̄=μ=84. σx̄=σ√n=9√64=1.125. The cutoff has z=(85.12−84)1.125=0.996, so P(x̄>cutoff)=0.1597.
