- A medical researcher studying childhood obesity randomly selects 300 children from elementary schools in her city and measures their BMI. She finds that 18% of these children are classified as obese according to CDC guidelines. If her goal is to estimate obesity rates among all elementary school children in the city, which of the following correctly identifies what the 18% represents and what it estimates?
Answer: The 18% is a statistic that estimates the true population parameter for the city
When you encounter questions about data and populations, the key distinction is between parameters (describing populations) and statistics (describing samples). Parameters are the true, usually unknown values we want to learn about, while statistics are the calculated values from our sample data that we use to estimate those parameters.
In this study, the researcher collected data from 300 children (a sample) to learn about all elementary school children in the city (the population). The 18% obesity rate comes directly from her sample of 300 children, making it a statistic. Her goal is to use this sample statistic to estimate the true obesity rate among all elementary children in the city—that unknown true rate is the parameter she's trying to estimate.
Looking at the wrong answers: Choice A reverses the terminology, incorrectly calling 18% a parameter when it's calculated from sample data. Choice C correctly identifies 18% as a statistic but misidentifies the target population—she's studying her city's children, not national rates. Choice D incorrectly calls 18% a parameter simply because it will be used for inference, but what makes something a parameter or statistic depends on whether it describes the population or sample, not how it's used afterward.
Study tip: Remember the flow: Sample → Statistic → Estimates → Parameter → Population. Statistics come from samples and estimate parameters that describe populations. The 18% flows from sample to statistic, estimating the city parameter.
- A health insurance company analyzes claims data for all 50,000 of their members and determines that the average annual healthcare expenditure is $4,200 per member. They want to use this information to set premiums for the following year. What best describes the $4,200 value in this context?
Answer: A parameter, because it describes a characteristic of the complete population of current members
When you encounter questions about data analysis, the fundamental distinction you need to make is whether a calculated value describes an entire population or just a sample from that population.
The $4,200 figure represents a parameter because it was calculated using data from all 50,000 members—the complete population of current policyholders. A parameter is any numerical summary that describes a characteristic of an entire population. Since the insurance company analyzed claims for every single member (not just a subset), this average represents the true population mean, making it a parameter.
Let's examine why the other options miss the mark. Option A incorrectly focuses on the data source (company vs. government), but the distinction between statistics and parameters has nothing to do with who collected the data—it's about whether you're working with complete population data or sample data. Option C mistakenly thinks that because the value will be used for future decision-making, it becomes a statistic, but the intended use of a calculated value doesn't change its fundamental nature as a population measure. Option D correctly identifies this as a parameter but gives the wrong reasoning—being used for business decisions doesn't make something a parameter.
Study tip: Always ask yourself "Am I looking at the entire population or just a sample?" If it's complete population data (like all current members, all patients in a hospital, all births in a state for a given year), any calculated measure is a parameter. If it's only a subset, it's a statistic.
- A public health study examines vaccination rates by surveying 1,500 randomly selected households in a state and finds that 78% of eligible individuals received their annual flu vaccine. The state health department reports that their records show 82% of all eligible individuals in the state received the vaccine. Which statement correctly distinguishes between the statistics and parameters in this context?
Answer: The 78% is a statistic calculated from the sample data, while 82% is a parameter representing the true population proportion
A statistic is calculated from sample data (78% from the 1,500 households), while a parameter describes the entire population (82% from complete state records of all eligible individuals). Choice A incorrectly classifies both as parameters. Choice C reverses the definitions by incorrectly suggesting random sampling creates parameters. Choice D incorrectly classifies the population value as a statistic simply because it was calculated from data.
- A mental health researcher surveys 320 college students about depression symptoms using a standardized scale. The sample mean depression score is 12.4, and she wants to estimate the mean score for all college students in the state. However, she recruited participants by posting flyers in counseling centers and psychology department buildings. Which statement best characterizes the key statistical concepts in this scenario?
Answer: The population is all college students in the state, the sample is the 320 respondents, and 12.4 is a statistic that may not accurately estimate the population parameter due to selection bias
The population is the group about which inferences are desired (all state college students), the sample is those actually measured (320 respondents), and 12.4 is a statistic that may be biased due to the non-random recruitment method. Choice B incorrectly identifies the population and incorrectly calls 12.4 a parameter. Choice C reverses the population and sample definitions and misclassifies the statistic as a parameter. Choice D incorrectly defines the sample and wrongly identifies 12.4 as a parameter while ignoring potential bias.
- A public health researcher studies childhood vaccination rates by analyzing state immunization registry data. For State A, she examines records for all 45,000 children aged 2-3 years and finds that 92% are up-to-date on recommended vaccines. For State B, budget constraints limit her to analyzing a random sample of 800 children from the 38,000 children in this age group, and she finds that 89% are up-to-date. Both states want to use these findings to improve their immunization programs. Which statement best describes the nature of these vaccination rates?
Answer: The 92% for State A is a parameter and the 89% for State B is a statistic, based on data completeness for each state
When you encounter questions about vaccination rates or any health data, the key distinction is whether you're looking at an entire population or just a sample from that population. This determines whether your calculated rate is a parameter (population value) or a statistic (sample estimate).
In State A, the researcher examined records for all 45,000 children aged 2-3 years in the state. Since she captured the complete population of interest, the 92% vaccination rate is a parameter—it represents the true value for the entire population. In State B, budget constraints limited the study to a random sample of 800 children from the total population of 38,000. The 89% rate calculated from this sample is a statistic—an estimate of the true population parameter.
Option A incorrectly suggests that the intended use of data determines whether it's a parameter or statistic. How data will be applied doesn't change its mathematical nature. Option B makes the error of thinking the data source determines the classification—but whether you use state or national systems doesn't matter if you're still dealing with populations versus samples. Option D reverses the correct classification and incorrectly focuses on data reliability rather than population coverage.
Remember this simple rule: if you have data on everyone in your population of interest, you're calculating a parameter. If you only have data on a subset (sample) of that population, you're calculating a statistic. The size, reliability, or intended use of the data doesn't change this fundamental distinction.
- A pharmaceutical company conducts a clinical trial by enrolling 800 patients with hypertension from 15 medical centers across the country. However, the company's ultimate goal is to understand how their new medication will perform when prescribed to the millions of hypertensive patients nationwide. During the trial, 23% of enrolled patients experienced the primary endpoint. What represents the sample in this study design?
Answer: The 800 patients with hypertension who were actually enrolled and participated in the clinical trial
The sample is the actual subset of individuals from whom data was collected - the 800 enrolled patients. Choice A describes the target population (all potential users nationwide). Choice B describes the sampling frame (eligible patients at participating centers). Choice D describes a study outcome, not the sample itself. The key distinction is that the sample consists of the actual study participants, not the broader groups they represent or the results obtained from them.
- A hospital administrator analyzes emergency department wait times by examining every patient visit during a randomly selected week. During this week, 420 patients were seen, and the mean wait time was 47 minutes. The administrator's goal is to understand typical ED performance and identify potential improvements. Given that the hospital operates 52 weeks per year with similar patient volumes, how should the 47-minute mean wait time be classified?
Answer: A statistic, because the week was randomly selected to represent typical hospital performance throughout the year
When you encounter questions about parameters versus statistics, focus on the relationship between your data and the population of interest. The key distinction is whether your calculated value describes the entire population or represents a sample used to make inferences about a larger group.
In this scenario, the administrator wants to understand "typical ED performance" for the hospital throughout the year. The population of interest is all patient visits across all 52 weeks of operation. Since one week was randomly selected to represent this larger population, the 420 patients constitute a sample, and the 47-minute mean is a statistic used to estimate the hospital's overall performance.
Answer B correctly identifies this as a statistic because the randomly selected week serves as a representative sample of the hospital's annual operations. The administrator's goal extends beyond just that one week to understanding general performance patterns.
Answer A is incorrect because analyzing all patients within the selected week doesn't make it a parameter—the week itself is still just a sample of the yearly operations. Answer C misses the broader context; while 47 minutes accurately describes that specific week, the administrator's purpose is to generalize beyond it. Answer D focuses on the intended use of the data rather than the fundamental sampling relationship, which isn't what determines parameter versus statistic classification.
Remember: a parameter describes an entire population, while a statistic describes a sample. Always identify what population the researcher wants to understand, not just what data they collected.
- An occupational health study examines injury rates among healthcare workers. Researchers obtain data from worker compensation records covering all 45,000 healthcare employees in a state over a 5-year period, finding an injury rate of 8.2 per 100 worker-years. They want to use this information to estimate injury rates that might be expected in other states with similar healthcare systems. In this context, what is the most accurate characterization of 8.2 per 100 worker-years?
Answer: It is a statistic because it represents a sample from the broader population of healthcare workers across states with similar systems
Whether a value is a parameter or statistic depends on the population of interest for the research question. Since the researchers want to make inferences about other similar states, the state data represents a sample from that broader target population, making 8.2 a statistic. Choice A incorrectly focuses on data completeness within the state rather than the research objective. Choice C incorrectly suggests that data quality determines parameter vs. statistic classification. Choice D incorrectly focuses on temporal sampling rather than the geographic scope of inference.
- A medical device company tests a new glucose monitor by having 200 diabetic patients use both their new device and a standard laboratory method to measure blood glucose. The correlation between the two methods is calculated as r = 0.94. The company's goal is to demonstrate that their device is accurate enough for all diabetic patients to use for home monitoring. In this validation study, what does the correlation coefficient r = 0.94 represent?
Answer: A statistic, because it was calculated from the sample of 200 patients and estimates the true correlation for all diabetic patients
When you encounter questions about correlation coefficients in research studies, you need to distinguish between parameters (population values) and statistics (sample values). This distinction is fundamental to understanding what research findings actually represent.
The correlation coefficient r = 0.94 was calculated from data collected on 200 diabetic patients, making it a statistic. A statistic is any numerical measure calculated from sample data that estimates a corresponding population parameter. Since the company's goal is to demonstrate accuracy "for all diabetic patients," the population of interest extends far beyond these 200 participants. The r = 0.94 represents their best estimate of what the true population correlation might be.
Option A is incorrect because a parameter would be the true correlation for all diabetic patients, which is unknown and unknowable without testing every diabetic patient in existence. Option C misses the point entirely—while the measurement relationship between methods might be consistent, the r = 0.94 specifically comes from this sample and estimates the population value. Option D contains a true statement about correlation coefficients generally being sample-based, but fails to capture the key concept that this particular r value serves as an estimate of the population parameter.
Remember this pattern: if a numerical value comes from collected data on a subset of the target population, it's a statistic estimating a parameter. Look for clues about sample size and the broader population the researchers want to generalize to—these signal you're dealing with statistics, not parameters.
- A clinical researcher designs a study to evaluate patient satisfaction with telemedicine visits. She randomly contacts 300 patients who had telemedicine appointments in the past month from a database containing 2,500 such patients. Of the 300 contacted, 240 agree to participate and complete her satisfaction survey. She finds that 78% of respondents report being satisfied with their telemedicine experience. What does the group of 240 survey respondents represent in this study?
Answer: A sample that may not be representative due to nonresponse bias among the originally selected patients
When evaluating survey data, you need to distinguish between your target population, your sampling frame, and your actual respondents, while considering how nonresponse affects representativeness.
The correct answer is D because the 240 respondents represent a sample that has been affected by nonresponse bias. Here's what happened: the researcher started with a proper random sample of 300 patients from the database, but only 240 participated (80% response rate). This creates potential bias because the 60 non-respondents may differ systematically from respondents – perhaps dissatisfied patients were less likely to participate, inflating the 78% satisfaction rate.
Option A is wrong because 240 respondents are clearly not the entire population of interest – there are 2,500 total telemedicine patients, and even among those contacted, some didn't respond. Option B incorrectly suggests the 240 are a sample of the 300 contacted patients, but they're actually all the willing participants from that group, not a subset. Option C misidentifies the 240 as a population, when they're actually a sample affected by self-selection – only those willing to respond participated.
The key insight is that nonresponse can introduce bias even when your initial sampling method is sound. A 20% nonresponse rate is substantial enough to potentially skew results, especially in satisfaction surveys where dissatisfied individuals might be less likely to participate.
Remember: whenever you see response rates below 100% in survey research, consider nonresponse bias as a potential limitation affecting the representativeness of your sample.
- An epidemiologist states that 'the true proportion of adults in California who have been vaccinated against COVID-19 is 0.73.' Assuming this statement is accurate, what best characterizes this value of 0.73?
Answer: A parameter, because it represents the true value for the entire population of California adults
When you encounter questions about parameters versus statistics, focus on whether the value describes an entire population or just a sample from that population. This fundamental distinction is crucial in biostatistics.
The key phrase here is "the true proportion of adults in California" — this indicates we're dealing with the actual value for the complete population of all California adults. Since 0.73 represents the true population value, it's a parameter by definition. Parameters describe characteristics of entire populations, while statistics describe characteristics of samples drawn from populations.
Let's examine why the other options miss the mark. Choice A incorrectly suggests that geographic scope determines whether something is a parameter or statistic — but the distinction isn't about location, it's about whether you're describing a complete population versus a sample. Choice C assumes the value came from survey data, but the question states this is the "true proportion," not an estimate from a sample. Choice D creates a false condition by suggesting a parameter only exists if determined through a census. In reality, parameters exist as true population values regardless of how (or whether) they're measured — we might estimate them through sampling or determine them through a census, but the parameter itself is the actual population characteristic.
Remember this key distinction: if a value describes the entire population of interest (like all California adults), it's a parameter. If it describes only a subset or sample from that population, it's a statistic. The method of data collection doesn't change this fundamental classification.
- A researcher is studying the effectiveness of a new diabetes medication. She collects data from 150 patients with type 2 diabetes who are enrolled in her clinical trial. The average reduction in HbA1c levels among these 150 patients is 1.2%. If this study aims to make inferences about all adults with type 2 diabetes in the United States, what best describes the 1.2% value?
Answer: A statistic, because it is calculated from the sample data collected in the study
When you encounter questions about parameters versus statistics, focus on the fundamental distinction: parameters describe populations, while statistics describe samples. This is one of the most tested concepts in biostatistics because it's foundational to understanding inference.
The 1.2% average HbA1c reduction is calculated from the 150 patients who participated in the study - this is your sample. Since this value is computed from sample data, it's a statistic by definition. A statistic is any numerical summary calculated from sample observations, regardless of what you plan to do with it afterward.
Let's examine why the other choices miss the mark. Choice A incorrectly calls 1.2% a parameter and wrongly identifies the 150 patients as the "population of interest." The population of interest is actually all adults with type 2 diabetes in the United States - a much larger group that the researcher wants to understand. Choice C makes the same parameter/statistic error and confuses the sample result with the "true effect," which would be the unknown parameter we're trying to estimate. Choice D correctly identifies 1.2% as a statistic but gives the wrong reasoning - something isn't a statistic because you'll use it for inference; it's a statistic because it comes from sample data.
Remember this simple rule: if the number comes from your sample (the actual data you collected), it's a statistic. If it describes the entire population you're interested in, it's a parameter. The intended use of the number doesn't change its classification - only its source matters.
- A health policy analyst wants to evaluate emergency department wait times. She collects data from a random sample of 15 hospitals within a large healthcare network that operates 200 hospitals nationwide. At the sampled hospitals, she reviews records for all patients who visited emergency departments during a specific month, totaling 8,943 patient visits, and calculates a mean wait time of 127 minutes. Her goal is to make recommendations for the entire healthcare network. What represents the sampling unit in this study design?
Answer: Each hospital that was randomly selected from the healthcare network for inclusion in the study
The sampling unit is the entity that was randomly selected - in this case, the 15 hospitals chosen from the 200 in the network. While data was collected from individual patients, the randomization occurred at the hospital level. Choice A confuses the unit of measurement with the sampling unit. Choice C identifies a subunit within the sampled hospitals rather than the sampling unit itself. Choice D describes the target population rather than the sampling unit.
- A hospital quality improvement team reviews infection rates across different units. They examine data from all patients admitted to the surgical unit during the past year (2,400 patients total) and find a surgical site infection rate of 3.2%. They also randomly audit 200 patients from the medical unit and find a healthcare-associated infection rate of 1.8%. The team wants to compare infection control effectiveness between units. Which statement correctly characterizes these rates?
Answer: The 3.2% is a parameter and the 1.8% is a statistic, reflecting the completeness of data collection for each unit
When you encounter questions about infection rates or any numerical summaries in biostatistics, immediately ask yourself: "Does this number describe an entire population or just a sample?" This distinction determines whether you're looking at a parameter (population value) or a statistic (sample value).
The surgical unit data represents all 2,400 patients admitted during the year - this is the complete population of surgical patients for that time period. Therefore, the 3.2% infection rate is a parameter because it describes the entire population of interest, not a subset. In contrast, the medical unit involved a random audit of only 200 patients from a larger population of medical unit patients. This makes the 1.8% rate a statistic since it's calculated from a sample.
Option A is wrong because the intended use of data (quality improvement decisions) doesn't determine whether values are parameters or statistics - the sampling method does. Option B incorrectly suggests that the data source (internal vs. external) determines this classification, when it's actually about population versus sample. Option D reverses the correct classification and incorrectly focuses on tracking system reliability rather than sampling methodology.
The key insight is that completeness of data collection is what matters - when you have complete enumeration (all surgical patients), you get a parameter. When you have partial data collection through sampling (200 medical patients), you get a statistic.
Study tip: Always identify the population first, then determine if the data represents that entire population (parameter) or just a sample from it (statistic).
- A pharmaceutical researcher conducts a clinical trial comparing two pain medications. She enrolls 400 patients with chronic arthritis: 200 receive Drug A and 200 receive Drug B. After 8 weeks, she measures pain reduction on a 0-10 scale and finds that Drug A patients had a mean reduction of 3.2 points while Drug B patients had a mean reduction of 2.8 points. Her research goal is to determine which medication is more effective for treating chronic arthritis in general. In this context, what do the 400 enrolled patients represent?
Answer: A sample representing all patients with chronic arthritis who might benefit from these pain medications
When you encounter questions about populations versus samples in biostatistics, focus on the researcher's ultimate goal and what group they want to make conclusions about. The key distinction is whether the study participants represent a broader group or constitute the entire group of interest.
In this clinical trial, the researcher wants to determine which medication is more effective "for treating chronic arthritis in general." This phrase signals that she aims to make inferences about a much larger group than just the 400 patients she studied. The 400 enrolled patients serve as representatives of all chronic arthritis patients who might potentially benefit from these medications. This makes them a sample from the broader population of interest.
Option A incorrectly suggests that including both treatment groups makes this a population, but having comparison groups doesn't determine population versus sample status. Option B misunderstands the study design—while patients receive different treatments, they're all drawn from the same underlying population of chronic arthritis patients. The treatment assignment doesn't create separate populations. Option D is tempting because it acknowledges the patients represent a broader group, but it artificially limits the population to only those "eligible and willing to participate in trials," which is too narrow given the researcher's goal of understanding effectiveness "in general."
Remember this pattern: when researchers want to make conclusions about effectiveness "in general" or for broader clinical practice, their study participants almost always represent a sample, regardless of study size. Look for language indicating the scope of intended conclusions.
- An infectious disease researcher tracks antibiotic resistance patterns by analyzing laboratory cultures from 2,400 patients treated at hospitals throughout a region during a 6-month period. She finds that 31% of bacterial cultures show resistance to first-line antibiotics. However, her ultimate research question concerns antibiotic resistance patterns that could be expected in similar healthcare settings globally over the long term. Given this research objective, which statement correctly identifies what 31% represents and explains why?
Answer: It is a statistic because the 2,400 patients represent a sample from the broader population of patients in similar healthcare settings globally
When you encounter questions about parameters versus statistics, focus on identifying the population of interest based on the research question. The key distinction isn't about data quality or completeness—it's about whether your data represents the entire population you're studying or just a sample from it.
The researcher's ultimate goal is understanding antibiotic resistance "in similar healthcare settings globally over the long term." This defines her population of interest as much broader than just one region over six months. The 2,400 patients from this specific region and time period represent a sample from that larger global population, making 31% a sample statistic. Even though she may have captured every patient in that region during those six months, she's still only observing a subset of the population she wants to make inferences about.
Option A incorrectly suggests that the source of data (laboratory results vs. surveys) determines whether something is a parameter—this is irrelevant to the parameter/statistic distinction. Option B gets the right answer but for the wrong reason; the six-month timeframe alone doesn't make this a sample. Option C focuses only on the immediate data collection scope, missing that the research question extends far beyond this regional dataset to global healthcare settings.
Remember this strategy: always identify the population of interest from the research question first. If your data covers that entire population, you have a parameter. If your data represents only part of that population (even if it's complete within a smaller scope), you have a statistic.
- A health department epidemiologist tracks influenza cases during flu season. She maintains a database of all confirmed cases in her county and notes that as of March 1st, there have been 1,847 confirmed cases among the county's 125,000 residents. She calculates the cumulative incidence rate as 1.48%. Meanwhile, a CDC researcher conducting a national flu surveillance study randomly samples 500 counties nationwide and calculates their average cumulative incidence rate. How should the epidemiologist's 1.48% rate be classified?
Answer: A parameter, because it describes the true cumulative incidence rate for the entire population of county residents
When you encounter questions about parameters versus statistics, focus on whether the measurement describes an entire population or just a sample from that population. This distinction is fundamental to understanding statistical inference.
The epidemiologist calculated 1.48% by dividing 1,847 confirmed cases by the county's entire population of 125,000 residents. Since she's describing the actual cumulative incidence rate for every resident in her defined population (the county), this 1.48% is a parameter—a true population value, not an estimate.
Looking at why the other options miss the mark: Option A incorrectly focuses on whether the data might be used elsewhere, but being part of someone else's sample doesn't change what the 1.48% represents for the original county population. Option C misinterprets the measurement as an estimate of typical seasonal patterns, when it's actually the definitive rate for this specific time period in this specific population. Option D gets distracted by irrelevant details about data collection methods and the collector's job title—the distinction between parameters and statistics depends solely on whether you're describing a complete population or a sample, not on who collected the data or how comprehensive their methods were.
The key insight here is that the county represents the epidemiologist's entire population of interest. She's not sampling from county residents; she's measuring all of them. Remember: if you have data on every member of your defined population, any descriptive measure you calculate is a parameter, regardless of whether that population might be considered a "sample" in someone else's study.
- A public health department wants to estimate the prevalence of hypertension among adults aged 65 and older in their county. They randomly select and examine 400 individuals from this age group and find that 180 have hypertension. In this study, what represents the population of interest?
Answer: All adults aged 65 and older living in the county at the time of the study
When you encounter a research study question, always identify what the researchers are trying to learn about versus what they actually studied. The population of interest is the entire group the researchers want to draw conclusions about, not the group they actually examined.
In this study, the public health department wants to estimate hypertension prevalence among all adults aged 65 and older in their county. This means their population of interest is every single person in that age group living in the county - answer C. The 400 people they examined are just a sample drawn from this larger population to make inferences about the whole group.
Answer A incorrectly identifies the sample as the population. The 400 individuals are the sample - the subset actually studied to represent the larger group. Answer B makes an even more restrictive error by focusing only on those with hypertension. These 180 people represent neither the sample nor the population, but rather just the positive cases within the sample. Answer D expands the scope too broadly beyond what the researchers actually want to study. The department specifically wants information about their county, not the entire United States.
Remember this key distinction: the population is who you want to know about, while the sample is who you actually study. Look for phrases like "wants to estimate" or "interested in learning about" to identify the true population of interest, which is typically broader than the group actually examined but narrower than the most expansive option offered.
- An occupational health specialist studies workplace injuries by examining safety records from a manufacturing company. She reviews all 180 reported injuries from the past two years and calculates that the average time lost per injury was 8.5 days. She plans to use this information to recommend policy changes for this company. Later, a government researcher studying the same topic randomly selects 60 of these injury reports for a broader analysis of manufacturing injuries nationwide. Which statement correctly describes the relationship between these two studies?
Answer: The 180 injuries represent a population for the company study but a sample for the government study, demonstrating different research contexts
When you encounter questions about populations versus samples, remember that these terms are defined by the research context and purpose, not just the absolute size of the dataset.
The occupational health specialist uses all 180 injury reports to understand workplace safety at her specific company. Since she's examining every injury case for her defined scope of interest (this company's injuries), the 180 injuries constitute her population, and the 8.5-day average is a parameter. The government researcher, however, has a different research goal: understanding manufacturing injuries nationwide. For this broader scope, all manufacturing injuries everywhere would be the population, making the randomly selected 60 reports a sample from which statistics would be calculated.
Looking at the wrong answers: Choice A incorrectly assumes both researchers share the same population and both calculate parameters, but their research scopes differ entirely. Choice C contains a major misconception—taking a sample of a sample doesn't invalidate statistical conclusions. The 60 randomly selected injuries still represent a valid sample of the broader manufacturing injury population that the government researcher wants to study. Choice D makes the error of applying one researcher's perspective to both studies. While it's true that neither examined all manufacturing companies nationwide, the company specialist wasn't trying to generalize beyond her company.
Remember this key principle: population and sample are always defined relative to your research question and scope of inference. The same dataset can be a population for one study and a sample for another, depending on what each researcher is trying to understand.
- A nutrition researcher studies vitamin D deficiency by testing blood samples from 650 adults who volunteered for a community health screening. She finds that 34% have insufficient vitamin D levels. Her research aims to understand vitamin D deficiency prevalence in the general adult population of her city. The city's actual adult population is approximately 180,000. Which elements are correctly matched to their statistical definitions?
Answer: Sample: 650 volunteers; Statistic: 34% with insufficient levels; Population: general adult population of the city; Parameter: true proportion with deficiency in the city
The sample is the group actually studied (650 volunteers), the statistic is the calculated value from the sample (34%), the population is the target group for inference (city's adult population), and the parameter is the unknown true value for that population (true proportion with deficiency). Choices B and C reverse the population and sample definitions. Choice D correctly identifies the sample but incorrectly matches statistics and parameters by confusing calculated sample values with unknown population values.
