(Lesson 1, Learning Objectives, had no quiz β pure bullet-list overview.)(Lesson 2, 3.1_Sampling introduction, had no quiz β pure reading.)
Lesson 3: 3.1.1 Introduction of Sampling
QUESTION 1 OF 48
What is the primary reason managers use sampling in decision-making?
β To gain insights efficiently without studying the entire population
Sampling lets managers infer conclusions about a whole population from a small subset, saving cost and time; it does not remove errors or the need for analysis, and it does not survey everyone.
QUESTION 2 OF 48
Which of the following best defines a sampling error?
β The difference between sample characteristics and population characteristics due to chance
Sampling error is the gap between the sampled value and the true population value that arises simply because only a sample was observed - even with random selection. It is not a data-entry mistake (that is non-sampling error), deliberate bias, or a cost.
QUESTION 3 OF 48
Which of the following is a characteristic of probability sampling?
β Each member of the population has a known chance of being selected
Probability sampling gives every unit a known, non-zero probability of selection (random selection from a defined frame). Convenience, expert-chosen and referral samples are non-probability methods.
QUESTION 4 OF 48
Which sampling method involves dividing the population into subgroups and randomly sampling from each subgroup?
β Stratified Sampling
Stratified sampling divides the population into strata and draws a random sample from every stratum. Cluster sampling instead selects whole clusters; convenience and snowball are non-probability.
QUESTION 5 OF 48
Which of the following is an example of a non-sampling error?
β Entering incorrect data during analysis
Non-sampling errors arise from data collection/processing (entry mistakes, measurement error, non-response), not from the act of sampling; a small sample size or random selection relates to sampling error.
QUESTION 6 OF 48
What is the best way to reduce measurement error in a survey?
β Pilot-test the survey and train data collectors
Measurement error comes from poor instruments and inconsistent collection; piloting finds unclear questions and training standardises collection. Increasing sample size only reduces sampling error.
QUESTION 7 OF 48
What does the Central Limit Theorem (CLT) state?
β Sample means from any population will form a normal distribution if the sample size is large enough
CLT says the sampling distribution of the mean approaches normal as n grows (n >= 30 rule of thumb), whatever the population's shape. It does not say all data are normal or that sampling error disappears.
QUESTION 8 OF 48
Which formula is used to calculate the standard error of the mean?
β SE = Ο / βn
The standard deviation of the sampling distribution of the mean is the population SD divided by the square root of the sample size.
QUESTION 9 OF 48
What happens to the standard error of the mean as the sample size increases?
β It decreases
The standard error formula is SE = Ο / βn. As the sample size (n) increases, the denominator increases, causing the standard error to decrease. This is a fundamental principle in statistics: larger samples provide more precise estimates of the population parameter.
QUESTION 10 OF 48
Which of the following statements is true about the mean of the sampling distribution of the mean?
β It is equal to the population mean
The mean of the sampling distribution of the mean equals the population mean (ΞΌ). This is a key property in sampling theory and forms the basis for unbiased estimation. No matter what sample size is used, if you take all possible samples and average their means, you get the population mean.
QUESTION 11 OF 48
What is the formula for the standard error of the sample proportion?
β Οp = β[p(1-p)/n]
The standard error of a sample proportion is Οp = β[p(1-p)/n], where p is the population proportion and n is the sample size. This formula shows how the standard deviation of the sampling distribution decreases as sample size increases (n in the denominator under the square root), providing more precise estimates with larger samples.
QUESTION 12 OF 48
According to the Central Limit Theorem, when is the sampling distribution of the proportion approximately normal?
β When both npβ₯5 and n(1βp)β₯5
For the sampling distribution of a proportion to be approximately normal, both conditions must be met: np β₯ 5 and n(1-p) β₯ 5. This ensures the sample size is large enough relative to the population proportion p. Some sources use β₯10 instead of β₯5, but the principle is the same: both the expected number of successes and failures must be sufficiently large.
QUESTION 13 OF 48
Which of the following is a property of a good estimator?
β It becomes more accurate as sample size increases
A good estimator has the property of consistency β as the sample size n increases, the estimator becomes more accurate and converges to the true population parameter. This is a fundamental characteristic of reliable statistical estimators. The other options describe poor estimators: always overestimating introduces bias, large variance means unreliable estimates, and ignoring data defeats the purpose of estimation.
QUESTION 14 OF 48
What does a 95% confidence interval mean?
β 95% of such intervals from repeated samples will contain the true population parameter
A 95% confidence interval means that if you were to repeat the sampling process many times and calculate a 95% confidence interval each time, approximately 95% of those intervals would contain the true population parameter. This is the correct interpretation β it's about the long-run behavior of the interval construction method, not about any single interval containing the parameter with 95% probability. The interval either contains the parameter (100%) or doesn't (0%); the probability refers to the method, not the specific interval.
QUESTION 15 OF 48
Which of the following best describes a point estimate?
β A single value used to estimate a population parameter
A point estimate is one statistic (e.g. x-bar for mu, p-hat for P); a range of values is an interval estimate.
QUESTION 16 OF 48
What happens to the width of a confidence interval when the sample size increases?
β It becomes narrower
A larger n shrinks the standard error (Ο/βn), so the margin of error and interval width fall.
QUESTION 17 OF 48
When should you use the t-distribution instead of the z-distribution for estimating the population mean?
β When the sample size is small and the population standard deviation is unknown
With Ο unknown and a small sample, the sample SD is used and the t-distribution (heavier tails) gives the right critical value; z applies when Ο is known or n is large.
QUESTION 18 OF 48
What does the standard error of the mean (SEM) measure?
β The variability of sample means in the sampling distribution
SEM is the standard deviation of the sampling distribution of x-bar, i.e. how much sample means vary around the population mean; it is not the spread of the population itself.
QUESTION 19 OF 48
Which factor leads to a narrower confidence interval?
β Larger sample size
The margin of error is critical value x standard error, and SE = Ο/βn (or s/βn) shrinks as n grows, so a larger sample gives a narrower, more precise interval. A higher confidence level or greater variability would widen it.
QUESTION 20 OF 48
When should you use the t-distribution instead of the z-distribution for constructing a confidence interval for the mean?
β When the population standard deviation is unknown and sample size is small
If Ο is unknown it is replaced by the sample SD s, and with a small sample (< 30) the CLT cannot justify z. The t-distribution has heavier tails, giving a larger critical value (t* with n-1 df) to reflect the extra uncertainty.
QUESTION 21 OF 48
When should the t-distribution be used instead of the z-distribution for estimating a population mean?
β When the population standard deviation is unknown and the sample size is small
The statistic follows a t-distribution when the sample SD replaces the population SD. For very large samples t approximates z, but t works best whenever Ο is unknown.
QUESTION 22 OF 48
Which of the following is a key assumption for using the t-distribution?
β The population should be approximately normally distributed
The t-test is derived assuming the underlying population is (approximately) normal, which matters most for small samples where the CLT cannot rescue normality. Biased samples or dependent observations violate the basic sampling assumptions.
QUESTION 23 OF 48
Which condition must be met to use the normal approximation for constructing a confidence interval for a population proportion?
β nΒ·pΜ β₯ 10 and nΒ·(1βpΜ) β₯ 10
The sampling distribution of pΜ is approximately normal only when the expected numbers of successes and failures are both large enough (β₯ 10 in this course's wording), so the z-based interval pΜ Β± zΒ·β(pΜ(1βpΜ)/n) is valid.
QUESTION 24 OF 48
Which of the following factors leads to a wider confidence interval for a population proportion?
β Higher confidence level
A higher confidence level needs a larger critical value (z), enlarging the margin of error. A larger sample or a lower confidence level narrows the interval; pΜ near 0.5 also gives the widest interval.
QUESTION 25 OF 48
Why is sampling used in the agricultural example involving corn yield estimation?
β Because measuring all 5,000 acres is too costly and time-consuming
A census of the whole population (5,000 acres) is impractical, so a sample (100 acres) is measured and used to infer the population yield - the core reason for sampling.
QUESTION 26 OF 48
In the e-commerce example, what is the standard error of the sample proportion of abandoned carts if the population proportion is 0.20 and the sample size is 500?
In the education case study, why is the t-distribution used instead of the z-distribution to estimate the population mean GPA?
β Because the population standard deviation is unknown and the sample size is small
Same rule as the lesson: unknown Ο plus a small sample means the sample SD must be used and the t-distribution gives the correct, wider critical value.
QUESTION 28 OF 48
In the healthcare case study, what is the sample proportion of patients who are satisfied with their care?
β 0.80
The sample proportion is pΜ = x/n (satisfied patients / patients surveyed); the case study's figures give 0.80 (accepted as correct by the course quiz on the first try).
QUESTION 29 OF 48
What is one of the main justifications for using sampling instead of conducting a census survey?
β Lower cost
A census of the whole population is expensive and slow; sampling gathers data from a small subset, so it saves money (and time) while still allowing inference.
QUESTION 30 OF 48
What is the characteristics of Probability Sampling?
β Each sample unit has an equal probability of selection
In probability sampling every unit has a known, non-zero chance of selection (equal in simple random sampling), so randomness drives selection and results can be generalised statistically.
QUESTION 31 OF 48
How is the Systematic random sample design is implemented?
β By starting with a randomly selected element and then drawing every nth element in the population
Systematic sampling picks a random start and then applies a fixed skip interval k = N/n.
QUESTION 32 OF 48
In sampling with Probability Proportional to Size (PPS), what is the main consideration for selecting clusters?
β Likelihood of selection proportionate to cluster size
PPS gives larger clusters a proportionally larger chance of being chosen, so every individual ends up with a similar overall chance.
QUESTION 33 OF 48
Which of the following statements best describes judgement sampling?
β Participants are chosen based on specific criteria and the opinion of an expert
Judgement (purposive) sampling is non-probability: the researcher/expert deliberately selects units judged most informative or representative.
QUESTION 34 OF 48
What is the primary advantage of using a sample instead of a census?
β Lower cost
Same reasoning as Q111: fewer units to study means lower cost and faster results.
QUESTION 35 OF 48
Which of the following is NOT a feature of the sampling method?
β Infinite scope
Sampling has economy, suitability in most situations and permits detailed study of fewer units; its scope is limited to the sample, not infinite.
QUESTION 36 OF 48
Sampling is essential when:
β Testing requires destroying the material
Destructive testing (e.g. crash tests, bulb life) makes a census impossible - nothing would be left - so only a sample can be tested.
QUESTION 37 OF 48
Probability sampling is characterised by:
β Equal probability of each unit being selected
Probability sampling relies on random selection from a sampling frame; non-random selection, subjective judgement and no frame describe non-probability methods.
QUESTION 38 OF 48
Which sampling method uses a "skip interval" for selecting units?
β Systematic Random Sampling
The skip interval k = N/n is the defining feature of systematic sampling.
QUESTION 39 OF 48
In stratified random sampling, the primary aim of stratification is to:
β Reduce variability within each stratum
Strata are formed to be internally homogeneous, which raises precision of the overall estimate.
QUESTION 40 OF 48
If the target population has a significant natural order, which sampling method is most appropriate?
β Systematic Sampling
Taking every kth unit from an ordered list spreads the sample evenly across the ordering.
QUESTION 41 OF 48
Which of the following is a disadvantage of simple random sampling?
β Difficult to create a comprehensive sampling frame
SRS needs a complete list of every unit, which is hard for large or scattered populations.
QUESTION 42 OF 48
Which of the following statements is TRUE about stratified sampling?
β It enhances precision by reducing variability within strata.
Because strata are homogeneous, the combined estimate has lower variance; it is a probability method, does not ignore subgroups, and need not take equal samples from each stratum.
QUESTION 43 OF 48
The formula for the probability of selecting an element in simple random sampling is:
β Sample size Γ· Population size
Each element's chance is n/N.
QUESTION 44 OF 48
Which sampling method is likely to be used when a researcher wants to ensure representation of specific subgroups?
β Stratified Sampling
Sampling from every stratum guarantees each subgroup appears.
QUESTION 45 OF 48
The possibility of "undetected patterns" in data is a drawback of:
β Systematic Random Sampling
If the list has a periodic pattern matching the skip interval, the sample can systematically miss or over-represent a pattern.
QUESTION 46 OF 48
Which of the following best describes the term "sampling efficiency"?
β The balance between sampling cost and precision
Course definition (Summary): efficiency is the trade-off between cost and precision.
QUESTION 47 OF 48
If a researcher randomly selects 5 cities from a list of 100 cities to conduct a survey, which sampling method is used?
β Simple Random Sampling
Units are drawn at random from the full list, each with equal chance.
QUESTION 48 OF 48
When selecting every 5th person from a list, starting from a random number between 1 and 5, the sampling technique used is
β Systematic Random Sampling
Random start (1-5) plus fixed interval of 5 is systematic sampling.
Module Assessment
3rd Module Assessment (17 questions, 30 marks: ten x 1, four x 2, three x 4; 1 hour; 3 attempts, highest grade; pass mark 15/30; review NOT permitted). Questions are drawn randomly from a larger bank, so each attempt shows a different set.
- Attempt 2 (1 Oct 2026, ~1 min): 30.00/30 = 100%. Every answer below in "Attempt 2 question set" is therefore confirmed correct.
- Attempt 1 (1 Oct 2026): 25.00/30 = 83.33%. Different question set; 5 marks were lost on questions that could not be identified (review disabled), so that set's answers are listed as best-effort / unconfirmed.
Attempt 2 question set (all confirmed correct, 30/30)
Q: Which sampling technique is used when the population has heterogeneity and needs representation from all segments? (1 mark)
β Stratified Random Sampling
Why: Stratification splits a heterogeneous population into strata and samples from each, so every segment is represented.
Q: Which sampling technique ensures representation from all segments in the population? (1)
β Stratified Random Sampling
Why: Sampling from every stratum guarantees each segment appears; cluster sampling samples only some clusters.
Q: In what type of studies is quota sampling often used? (1)
β Public opinion studies
Why: Quota sampling is a quick, cheap non-probability method used in opinion polls and market surveys where interviewers fill set quotas of age/gender/income groups.
Q: What factor should be considered when determining the sample size? (1)
β Objective of the study, availability of time and other resources
Why: There is no fixed formula; the study's purpose and the available time/money drive how large the sample can and should be.
Q: What is the purpose of the fixed interval selection method? (1)
β To select subsequent sample units at a fixed interval or distance from an initial selection
Why: Fixed-interval (systematic) selection picks a start and then every kth unit (skip interval).
Q: What is the recommended sample size in relation to the population size? (1)
β No hard-and-fast rule, depends on factors such as efficiency, representativeness, reliability, and flexibility
Why: The course lists efficiency, representativeness, reliability and flexibility as the criteria; no fixed percentage applies.
Q: What is the advantage of using multistage sampling? (1)
β It is economical and less tedious for collecting data from a very large area.
Why: Sampling in stages (area -> section -> unit) avoids listing and visiting every unit over a wide region.
Q: Define 'Universe' in sampling. (1)
β Any collection of persons or objects or events in which the research has to be conducted.
Why: The universe is the whole population from which the sample is drawn.
Q: What is sample size determination? (1)
β Choosing the number of observations or sampling units to include in a statistical sample
Why: Direct definition; it is not choosing the test or confidence level.
Q: Why is a well-selected small sample sometimes considered superior to a large but badly selected sample? (1)
β A small but well-selected sample may fulfill the requirements of efficiency, representativeness, reliability, and flexibility
Why: Quality of selection matters more than size - a large biased sample is still biased.
Q: What is a step in the quota sampling process? (2)
β Separate the population into distinct subgroups.
Why: Stage 1 of quota sampling divides the population into subgroups; stage 2 estimates their proportions; then quotas are filled.
Q: What is a disadvantage of judgement (or purposive) sampling? (2)
β There is a high risk of researcher bias.
Why: The expert/researcher's own judgement decides who is selected, so subjectivity and bias creep in and representativeness cannot be measured.
Q: What is a disadvantage of non-probability sampling? (2)
β Making judgments about the entire population is risky.
Why: Without known selection probabilities results cannot be safely generalised.
Q: What is one of the main beliefs of researchers regarding the application of sound judgement in sampling? (2)
β Ensures the creation of a representative sample
Why: Researchers who use judgement sampling believe sound expert judgement yields a sample that represents the population.
Q: What does quota sampling allow for a researcher? (4)
β stratifying or grouping the population
Why: Quotas are set on predefined subgroups (like strata), but filling them is non-random, so it is not proportionate random selection.
Q: How are individuals recruited in snowball sampling? (4)
β Chain referral
Why: Existing respondents refer further respondents (referral sampling).
Q: What belief do researchers commonly hold regarding the application of sound judgement in producing representative samples? (4)
β The results obtained are likely to be very accurate with a small margin of error
Why: The premise of judgement sampling is that expert judgement gives accurate results with little error.
Attempt 1 question set (25/30 - answers are best-effort, 5 marks lost on unidentified question(s))
Q: What is a sampling frame? (1) - answered: The group of people from which the researcher will draw the sample
Why: The frame is the list/source from which units are drawn; the group about whom conclusions are made is the target population.(Flagged: unconfirmed - attempt 1 scored 25/30.)
Q: What is the final step in sampling decisions? (1) - answered: Implement the plan
Why: Sampling decisions run: identify population -> frame -> method -> size -> implement the plan.(Flagged: unconfirmed.)
Q: What is the advantage of the cell selection method over the fixed interval selection method? (1) - answered: It avoids problems related to patterns in the data.
Why: Picking one unit at random from each cell avoids the periodicity problem of a fixed skip interval.(Flagged: unconfirmed.)
Q: What is an economical sampling method? (1) - answered: One that requires minimum cost and effort.
(Flagged: unconfirmed.)
Q: What is the first step in sampling decisions? (1) - answered: Identify the population of interest
(Flagged: unconfirmed - consistent with Q67.)
Q: When is non-probability sampling preferred over probability sampling? (1) - answered: Qualitative research, pilot studies or exploratory research.
(Flagged: unconfirmed.)
Q: What is the first step in cluster sampling? (1) - answered: Dividing the population into clusters or groups.
(Flagged: unconfirmed.)
Q: What is convenience sampling also known as? (1) - answered: chunk
(Flagged: unconfirmed.)
Q: What is the purpose of a sampling frame? (1) - answered: To provide a list of all units in the population from which a sample can be selected.
(Flagged: unconfirmed.)
Q: Which sampling method should be used if the sampling frame does not represent the population well? (1) - answered: Non-random selection method
(Flagged: LEADING SUSPECT for a lost mark - genuinely unsure; options were cell selection / non-random / fixed interval / random selection.)
Q: What is Two-Stage Clustering in cluster sampling? (2) - answered: Process of randomly selecting students from each cluster by random or systematic sampling
(Flagged: unconfirmed.)
Q: What does cluster sampling do? (2) - answered: Divides the population into different clusters
(Flagged: unconfirmed.)
Q: Why are convenience samples prone to severe bias? (2) - answered: Because the sample may not be representative of the population.
(Flagged: unconfirmed; alternative option was "Due to the availability and desire of participants".)
Q: What makes non-probability samples preferred when precision of results is not critical? (2) - answered: They are low-cost, easy-to-run, and don't require a frame.
(Flagged: unconfirmed.)
Q: How is bias reduced in convenience sampling? (4) - answered: Using convenience sampling in conjunction with probability sampling.
(Flagged: LEADING SUSPECT for lost marks - genuinely unsure.)
Q: What is one of the benefits of using a convenience sampling strategy? (4) - answered: Simple data collection and access to samples.
(Flagged: unconfirmed.)
Q: What does the researcher estimate during the second stage of quota sampling? (4) - answered: proportion of subgroups in the population
(Flagged: unconfirmed; consistent with Q59.)
UNVERIFIED assessment set (attempt 101799354, scored 27/30)
3 mark(s) were lost in this attempt and the platform does not show which question, so none of these picks is confirmed.
When do researchers adopt snowball sampling? - answered: When the sample size is small and not readily available
How is the sample selected in systematic sampling? - answered: Every kth unit is selected in the sample.
What is probability sampling? - answered: Sampling methods in which every item in the universe has an equal chance or probability to be chosen for the sample.
Why do researchers rely on convenience sampling? - answered: speed, cost-effectiveness and accessibility of availability
What are non-probability sampling methods? - answered: Methods that do not provide every item in the universe with a known chance of being included in the sample.
In what type of universe would a small sample be sufficient? - answered: Homogeneous universe
What is the sample size determined by? - answered: The research objectives of the study.
What is simple random sampling? - answered: A method where every unit of the population has an equal chance of being selected in the sample.
What is judgement sampling? - answered: Sampling in which researchers choose samples based solely on their own knowledge and reputation.
When is non-probability sampling preferred over probability sampling? - answered: When researchers have a restricted amount of time to do study or a limited funding.
What is an example of one-stage cluster sampling? - answered: Picking the total students from the random engineering institutions
What is a disadvantage of quota sampling? - answered: The results are not generalizable.
What is an advantage of judgement (or purposive) sampling? - answered: Enables controlled selection of sample members.
What is an advantage of non-probability sampling? - answered: ItΓ’β¬β’s low-cost, easy-to-run, and doesnΓ’β¬β’t require a frame.
When is snowball sampling economical? - answered: The referrals come from a primary data source.
What makes consecutive sampling different from convenience sampling? - answered: It involves studying and moving on to a different subject or group if necessary.
What characteristic do researchers attribute to the sampling technique using the researcher's expertise? - answered: Likely to yield very accurate results with a small margin of error