Business Statistics Quiz: Variable Types In Business
20 questions · exam conditions
0:00
Variable Types In BusinessQuestion 1 of 20

A multinational corporation analyzes its office locations. For each office, it records the 'City' (e.g., 'New York'), the 'Sales Region' (e.g., 'North America'), and the 'Distance to Corporate HQ' in kilometers. Which option correctly classifies these three variables in order?

Nominal, Ordinal, Continuous Quantitative
Nominal, Nominal, Continuous Quantitative
Ordinal, Nominal, Discrete Quantitative
Nominal, Ordinal, Discrete Quantitative
← Back to quizzes

Business Statistics Quiz

Business Statistics Quiz: Variable Types In Business

Practice Variable Types In Business in Business Statistics with focused quiz questions that help you check what you know, review explanations, and build confidence with test-style prompts.

What this quiz covers

This quiz focuses on Variable Types In Business, giving you a quick way to practice the rules, question types, and explanations that matter most for Business Statistics.

How to use this quiz

Try each quiz question before looking at the correct answer. Use the explanations to review missed ideas, then come back to similar questions until the pattern feels familiar.

All questions

Question 1

A multinational corporation analyzes its office locations. For each office, it records the 'City' (e.g., 'New York'), the 'Sales Region' (e.g., 'North America'), and the 'Distance to Corporate HQ' in kilometers. Which option correctly classifies these three variables in order?

  1. Nominal, Ordinal, Continuous Quantitative
  2. Nominal, Nominal, Continuous Quantitative (correct answer)
  3. Ordinal, Nominal, Discrete Quantitative
  4. Nominal, Ordinal, Discrete Quantitative
Explanation: The correct answer is B. 'City' is a nominal categorical variable; the names are labels for locations with no inherent order. 'Sales Region' is also a nominal categorical variable; 'North America' is not inherently greater or less than 'Europe' or 'Asia'. 'Distance to Corporate HQ' is a physical measurement, making it a continuous quantitative variable. A) and D) incorrectly classify 'Sales Region' as ordinal. C) incorrectly classifies 'City' as ordinal and 'Distance' as discrete.

Question 2

A manager wants to compare the sales performance of three different store layouts: 'Grid', 'Loop', and 'Free-form'. The manager collects data on DailyRevenue, NumberOfCustomers, and AverageDwellTime (average time a customer spends in the store).

To perform this comparison, how must the StoreLayout variable be treated, and which of the collected metrics is a continuous quantitative measure of performance?

  1. StoreLayout must be treated as a quantitative variable, and NumberOfCustomers is the continuous measure.
  2. StoreLayout must be treated as a nominal categorical variable, and NumberOfCustomers is the continuous measure.
  3. StoreLayout must be treated as an ordinal categorical variable, and DailyRevenue is the continuous measure.
  4. StoreLayout must be treated as a nominal categorical variable, and AverageDwellTime is the continuous measure. (correct answer)
Explanation: When analyzing business data, you need to correctly identify variable types to choose appropriate statistical methods. This question tests your ability to classify variables as categorical or quantitative, and understand what makes a measure "continuous." The StoreLayout variable represents three distinct categories: Grid, Loop, and Free-form. These are qualitative labels with no inherent numerical ordering or ranking - one layout isn't "greater than" another in any meaningful numerical sense. This makes StoreLayout a nominal categorical variable, since the categories are simply different names without a natural order. For the performance metrics, AverageDwellTime is indeed a continuous quantitative measure. Time can be measured with infinite precision (15.7 minutes, 15.73 minutes, etc.) and represents a true numerical quantity that can take on any value within a reasonable range. Option A incorrectly treats StoreLayout as quantitative - but store layout names are qualitative categories, not numbers you can perform arithmetic on. Option B correctly identifies StoreLayout as nominal categorical, but NumberOfCustomers is actually discrete (you can't have 15.5 customers), not continuous. Option C suggests StoreLayout is ordinal, but there's no inherent ranking among Grid, Loop, and Free-form layouts - they're just different approaches without a clear "better to worse" sequence. Study tip: Remember that nominal variables are categories without order (colors, names, types), ordinal variables have meaningful order (ratings, grades), and continuous variables can take any value within a range with infinite precision.

Question 3

A retail analytics team is developing a customer segmentation model. They collect the following variables: customer age, preferred shopping method (online/in-store/hybrid), annual spending amount, satisfaction rating (1-10 scale), and loyalty program tier (Bronze/Silver/Gold/Platinum). The team needs to apply different statistical techniques based on variable types. Which combination correctly identifies the variable types that would require non-parametric statistical methods?

  1. Preferred shopping method and loyalty program tier only, since both are categorical variables without inherent numerical meaning
  2. Satisfaction rating and loyalty program tier only, since ordinal scales and ranked categories require rank-based statistical approaches (correct answer)
  3. Customer age and annual spending amount only, since continuous variables often violate normality assumptions required for parametric tests
  4. Preferred shopping method, satisfaction rating, and loyalty program tier, since all non-continuous variables require non-parametric approaches
Explanation: Non-parametric methods are primarily used for ordinal data and ranked data. Satisfaction rating (1-10 scale) is ordinal, and loyalty program tiers represent ranked categories (Bronze < Silver < Gold < Platinum). Preferred shopping method is nominal categorical (no inherent order), while age and spending are quantitative variables that can use parametric methods if assumptions are met.

Question 4

An e-commerce company analyzes customer behavior using these variables: customer ID (C001, C002, etc.), purchase frequency category (Low/Medium/High), product rating (1-5 stars), shipping preference (Standard/Express/Overnight), and order value in dollars. The data science team needs to encode these variables for machine learning algorithms. Which encoding approach would be most problematic and why?

  1. Using ordinal encoding (1,2,3) for shipping preference, because it incorrectly implies Standard < Express < Overnight relationships
  2. Using one-hot encoding for purchase frequency category, because it loses the inherent ordering information between Low/Medium/High
  3. Using numerical encoding (1,2,3,4,5) for product rating, because it assumes equal intervals between rating levels
  4. Using label encoding for customer ID, because it creates artificial numerical relationships between unrelated categorical identifiers (correct answer)
Explanation: Customer IDs are nominal categorical variables with no inherent order or relationship. Label encoding (assigning 1, 2, 3, etc.) creates false numerical relationships that algorithms might interpret as meaningful patterns. Shipping preference should use one-hot encoding (A is incorrect), purchase frequency should use ordinal encoding to preserve order (B is incorrect), and product ratings are commonly treated as interval data (C is acceptable practice).

Question 5

A healthcare analytics team is studying patient outcomes using variables including: patient age, diagnosis code (ICD-10 format like J44.0), treatment response (Complete/Partial/None), pain level (0-10 scale), insurance type (Medicare/Medicaid/Private/Uninsured), length of stay (days), and readmission risk score (0.0-1.0 probability). When preparing summary statistics for a medical board presentation, which measures would be most inappropriate for their intended variables?

  1. Calculating mode for diagnosis codes and standard deviation for treatment response categories (correct answer)
  2. Computing mean pain levels across insurance types and median length of stay by treatment response
  3. Finding the range of readmission risk scores and frequency distributions for insurance types
  4. Determining quartiles for patient age and cross-tabulation tables for diagnosis codes versus treatment response
Explanation: Standard deviation cannot be meaningfully calculated for categorical variables like treatment response (Complete/Partial/None) because it requires numerical data with meaningful arithmetic operations. While mode can technically be found for diagnosis codes, it's not particularly useful for ICD-10 codes. The other options appropriately match statistical measures with variable types: means work for quantitative data like pain levels, medians work for quantitative data like length of stay, and cross-tabulations work for categorical variables.

Question 6

To simplify a customer segmentation model, a marketing analyst converts the CustomerAge variable (a quantitative value) into a new variable called AgeGroup with categories '18-29', '30-45', '46-60', and '61+'.

What is the primary consequence of this data transformation for statistical analysis?

  1. The AgeGroup variable contains more detailed information than the original CustomerAge variable.
  2. The data has been converted from a quantitative (ratio) scale to a categorical (ordinal) scale, losing some precision. (correct answer)
  3. The data has been converted from a categorical (nominal) scale to a quantitative (interval) scale, allowing for more powerful tests.
  4. The AgeGroup variable can now be used to calculate a meaningful standard deviation for customer age.
Explanation: The transformation from a specific age (e.g., 28) to a group ('18-29') is a process of binning or discretization. The original CustomerAge is quantitative (ratio). The new AgeGroup variable is categorical. Because the groups have a natural order, it is specifically an ordinal variable. This process always involves a loss of information/precision (e.g., we no longer know the difference between a 20-year-old and a 28-year-old). Choice A is incorrect; information is lost, not gained. Choice C reverses the transformation. Choice D is incorrect; one cannot calculate a standard deviation from categorical labels.

Question 7

A supply chain database stores information about products. The ProductTier is encoded as: 1 for 'Basic', 2 for 'Standard', and 3 for 'Premium'. The database also includes ProductWeight in grams.

An intern calculates the average ProductTier as 2.1 and concludes that the average product is slightly better than 'Standard'. Which statement identifies the fundamental flaw in the intern's analysis?

  1. The intern should have used the median instead of the mean because the data is skewed.
  2. The intern treated ProductTier, a categorical (ordinal) variable, as if it were a quantitative (interval) variable. (correct answer)
  3. The calculation is flawed because ProductTier is a discrete variable, and the average cannot be a non-integer.
  4. The intern should have also calculated the average ProductWeight to provide context for the ProductTier average.
Explanation: The core error is treating a numerically coded categorical variable as a quantitative one. ProductTier has a clear order (Basic < Standard < Premium), making it ordinal. However, the numerical difference between 1 and 2 may not represent the same 'jump' in quality as the difference between 2 and 3. Therefore, calculating an arithmetic mean is inappropriate because it assumes equal intervals. Choice A is incorrect because the primary issue isn't skewness but the variable's scale of measurement. Choice C is a common misconception; the average of a discrete variable can certainly be a non-integer (e.g., average family size). Choice D suggests adding more analysis but doesn't identify the flaw in the existing one.

Question 8

A business analyst is choosing a statistical model to predict employee turnover. The model requires an input variable that represents the number of direct reports for each manager. Another variable available is the employee's department (e.g., 'Sales', 'HR', 'Engineering'). How do these two variables, NumberOfReports and Department, differ?

  1. NumberOfReports is continuous quantitative, while Department is nominal categorical.
  2. NumberOfReports is ratio quantitative, while Department is ordinal categorical.
  3. NumberOfReports is discrete quantitative, while Department is nominal categorical. (correct answer)
  4. Both are discrete, but NumberOfReports is interval while Department is nominal.
Explanation: This question tests the distinction between discrete and continuous quantitative variables, and nominal categorical variables. NumberOfReports is quantitative because it's a count; specifically, it's discrete because a manager can have 3 or 4 reports, but not 3.5. It is also a ratio scale variable because 0 is a true zero and ratios are meaningful (4 reports is twice as many as 2). Department is a set of labels with no intrinsic order, making it a nominal categorical variable. Choice A is incorrect because a count is discrete, not continuous. Choice B is incorrect because 'Department' has no natural order. Choice D incorrectly classifies NumberOfReports as interval (it has a true zero, making it ratio).

Question 9

A marketing team is analyzing text from customer reviews. To use this data in a statistical model, they perform sentiment analysis, which assigns each review a SentimentScore from -1.0 (very negative) to +1.0 (very positive). They also categorize each review by the ProductCategory it discusses ('Electronics', 'Apparel', 'Home Goods').

Which of the following best describes the variable types created for the model?

  1. SentimentScore is a continuous quantitative variable, and ProductCategory is a nominal categorical variable. (correct answer)
  2. SentimentScore is an ordinal categorical variable, and ProductCategory is a nominal categorical variable.
  3. Both are quantitative variables, but SentimentScore is continuous while ProductCategory is discrete.
  4. Both are categorical variables, but SentimentScore is ordinal while ProductCategory is nominal.
Explanation: This question links variable types to a modern business application (text analysis). ProductCategory consists of unordered labels, making it nominal categorical. The SentimentScore, a measurement on a continuous scale from -1.0 to +1.0, is a continuous quantitative variable. It has magnitude, direction, and equal intervals (the difference between 0.5 and 0.6 is treated as the same as between 0.7 and 0.8). While it originates from subjective text, the resulting score is designed to be quantitative for modeling purposes. The other choices misclassify one or both variables.

Question 10

A business is analyzing its shipping logistics. It records ShippingCost (in dollars), PackageWeight (in kg), ShippingCarrier ('FedEx', 'UPS', 'DHL'), and DeliveryStatus (coded as 1 for 'On-Time', 2 for 'Delayed', 3 for 'Lost'). Which variable is ordinal categorical?

  1. ShippingCost
  2. PackageWeight
  3. ShippingCarrier
  4. DeliveryStatus (correct answer)
Explanation: The question asks to identify the ordinal variable. ShippingCost and PackageWeight are quantitative (ratio). ShippingCarrier is a list of names with no inherent order, making it nominal categorical. DeliveryStatus, although numerically coded, represents categories with a logical order of severity ('On-Time' < 'Delayed' < 'Lost'). This makes it an ordinal categorical variable. The numerical coding is just a label for these ordered categories.

Question 11

A market research firm conducts a consumer preference study for a new product line. They collect data on: household income (in thousands), education level (High School/Some College/Bachelor's/Graduate), product preference rating (1-7 Likert scale), purchase intent (Definitely Not/Probably Not/Might/Probably/Definitely), age group (18-25/26-35/36-45/46-55/55+), and prior brand experience (Yes/No).

The research team needs to determine which statistical tests are appropriate for analyzing relationships between variables. Based on the variable types present, which analysis approach would be methodologically sound?

  1. ANOVA to compare income differences across education levels, and chi-square tests to examine associations between purchase intent and prior brand experience
  2. Pearson correlation between preference rating and purchase intent, and t-tests comparing income means between prior brand experience groups (correct answer)
  3. Multiple regression with income predicting preference rating, and chi-square analysis of education level versus age group relationships
  4. Spearman correlation for all ordinal variable pairs, and independent t-tests comparing preference ratings across all education levels
Explanation: Pearson correlation is appropriate between preference rating (interval-like) and purchase intent (ordinal with meaningful progression). T-tests can compare income (quantitative) between two groups (prior brand experience: Yes/No). Option A incorrectly uses ANOVA (income should be dependent variable, not independent). Option C uses appropriate regression but education vs. age group chi-square isn't particularly meaningful. Option D incorrectly uses t-tests for comparing more than two groups (education levels).

Question 12

A financial analyst is studying corporate performance from 2015 to 2020. The dataset contains the variable FiscalYear. The analyst plans two separate analyses: (1) a time-series plot of revenue over time, and (2) a bar chart comparing the average employee salary in 2017 versus 2020.

How should the FiscalYear variable be treated in these two different business contexts?

  1. As a quantitative variable in the time-series plot and as a categorical variable in the bar chart comparison. (correct answer)
  2. As a categorical variable in both analyses because year is a label, not a measurement.
  3. As a quantitative variable in both analyses because year is a numerical value with equal intervals.
  4. As a nominal variable for the time-series plot and as an ordinal variable for the bar chart comparison.
Explanation: This question highlights how a variable's type can depend on the analytical context. For the time-series plot (1), FiscalYear is treated as a quantitative variable on the x-axis, where the sequence and interval properties are important for showing a trend. For the bar chart comparison (2), FiscalYear serves as a categorical variable to define the two groups being compared ('2017' and '2020'). The analysis isn't about the trend between 2017 and 2020, but about comparing two distinct categories. Choices B and C fail to recognize this contextual difference. Choice D misclassifies the variable types for these specific uses.

Question 13

An investment firm classifies bonds using a rating system from 'AAA' (highest quality) to 'D' (lowest, in default). They also track the bond's YieldToMaturity (a percentage) and its IssuingCountry.

If an analyst wants to build a model where bond rating predicts yield, what are the respective types of the predictor (rating) and response (yield) variables?

  1. Predictor: Nominal; Response: Quantitative
  2. Predictor: Nominal; Response: Ordinal
  3. Predictor: Quantitative; Response: Ordinal
  4. Predictor: Ordinal; Response: Quantitative (correct answer)
Explanation: When analyzing variables for statistical modeling, you need to correctly classify both your predictor and response variables by their data types. This determines which analytical methods you can appropriately use. Let's examine each variable in this bond rating scenario. The bond rating uses categories like 'AAA', 'AA', 'A', 'BBB', etc., down to 'D'. These aren't just arbitrary labels—they have a clear ranking from highest quality (AAA) to lowest (D). This makes rating an ordinal variable because the categories have a meaningful order. The yield to maturity, expressed as a percentage, represents a continuous numerical measurement, making it quantitative. Since rating predicts yield in this model, rating is the predictor (ordinal) and yield is the response (quantitative), confirming answer D is correct. Here's why the other options fail: A incorrectly classifies rating as nominal, ignoring the clear quality hierarchy from AAA to D. B makes the same nominal error for rating, plus incorrectly calls the numerical yield percentage "ordinal." C wrongly labels rating as quantitative—while we might assign numbers to ratings for analysis, the original rating categories themselves aren't inherently numerical measurements. Study tip: To distinguish ordinal from nominal, ask "Is there a natural ranking?" For quantitative vs. ordinal, ask "Are these actual numerical measurements or ranked categories?" Bond ratings always have meaningful order (ordinal), while yields are true measurements (quantitative). This pattern appears frequently in business statistics with satisfaction surveys, credit ratings, and performance grades.

Question 14

An analyst aggregates transaction-level sales data to a daily summary. The original dataset had a PaymentMethod column ('Cash', 'Credit', 'Debit'). The new aggregated dataset has a column called MostFrequentPaymentMethod for each day.

How does the variable type of PaymentMethod in the original data compare to the variable type of MostFrequentPaymentMethod in the aggregated data?

  1. Both are quantitative variables because they relate to financial transactions.
  2. The original is quantitative, but the aggregated variable is categorical.
  3. Both are nominal categorical variables. (correct answer)
  4. The original is nominal categorical, but the aggregated variable is ordinal categorical.
Explanation: This question tests whether a student understands that aggregation does not necessarily change the variable type. PaymentMethod in the original data is a list of labels ('Cash', 'Credit', etc.), which is nominal categorical. After aggregating, the MostFrequentPaymentMethod for a given day will be one of those same labels (e.g., 'Credit'). The new variable is still a list of labels with no inherent order. Therefore, both variables are nominal categorical. The act of finding the mode (most frequent) does not change the categorical nature of the data.

Question 15

A human resources department uses a 5-point Likert scale (1=Very Dissatisfied, 2=Dissatisfied, 3=Neutral, 4=Satisfied, 5=Very Satisfied) to measure employee job satisfaction. For the same employees, they also record their office's ambient temperature in degrees Celsius.

Which statement best contrasts the Satisfaction and Temperature variables in terms of their measurement scales?

  1. Both are interval variables because the numerical difference between values is constant and meaningful.
  2. Satisfaction is an ordinal variable where the difference between rankings may not be uniform, while Temperature is an interval variable with uniform differences. (correct answer)
  3. Satisfaction is a nominal variable because it represents categories of feeling, while Temperature is a ratio variable because it has a true zero point.
  4. Both are ratio variables because they are represented by numbers and can be used in mathematical calculations.
Explanation: This question tests the subtle distinction between ordinal and interval scales. Satisfaction is ordinal because the values have a clear order, but the difference in satisfaction between a '1' and '2' is not necessarily the same as between a '4' and '5'. Temperature in Celsius is an interval variable because the difference between 20°C and 21°C is the same as between 30°C and 31°C. Choice A is wrong because the intervals for satisfaction are not uniform. Choice C incorrectly classifies Satisfaction as nominal (it has an order) and Temperature as ratio (0°C is not a true absence of temperature). Choice D is incorrect as neither is a ratio variable in this context (and satisfaction is not even interval).

Question 16

An airline's operational dataset includes the variable FlightNumber (e.g., 'UA241', 'DL588') and FlightDuration (in minutes).

A new data scientist on the team is tasked with building a model to predict flight delays. They consider using both FlightNumber and FlightDuration as predictors. Which statement accurately describes the treatment of these variables?

  1. Both are quantitative variables and can be entered directly into most regression models.
  2. Both are categorical variables, as FlightNumber is a unique label and FlightDuration can be considered an ordered set of discrete times.
  3. FlightNumber is a quantitative variable because it contains numbers, while FlightDuration is a categorical variable because it can be grouped into bins (e.g., 'short', 'medium', 'long').
  4. FlightNumber is a categorical variable that serves as an identifier, while FlightDuration is a quantitative variable. (correct answer)
Explanation: When classifying variables for statistical modeling, you need to distinguish between data that represents quantities versus data that represents categories or labels, regardless of whether numbers appear in the values. FlightNumber serves as a categorical identifier. Even though it contains numbers like "UA241," these numbers don't represent measurable quantities that you can meaningfully add, subtract, or average. Flight number "UA241" isn't "twice as much" as "UA120" in any meaningful sense—it's simply a unique label to identify a specific flight route. In modeling, you'd typically treat this as a categorical variable, possibly using techniques like one-hot encoding. FlightDuration, measured in minutes, is clearly quantitative. You can perform arithmetic operations on these values: a 180-minute flight is exactly twice as long as a 90-minute flight. This variable represents a measurable quantity that can be directly used in regression models. Option A incorrectly classifies FlightNumber as quantitative just because it contains numbers. Option B wrongly calls FlightDuration categorical—while you could bin it into categories, the original variable itself measures a continuous quantity. Option C makes the opposite mistake, calling FlightNumber quantitative (falling for the "contains numbers" trap) while incorrectly labeling the genuinely measurable FlightDuration as categorical. Study tip: Don't let the presence of numbers fool you. Ask yourself: "Can I meaningfully perform math operations on this data?" If employee ID #347 isn't mathematically larger than ID #125, it's categorical regardless of the numbers involved.

Question 17

A consulting firm analyzes project outcomes. They create a new variable, ProjectSuccess, coded as 1 if the project was profitable and 0 if it was not. They also track ProjectDuration in months.

The firm's lead statistician states that while ProjectSuccess can be used to calculate a meaningful proportion, it is fundamentally a different type of variable than ProjectDuration. Why is this statement correct?

  1. ProjectSuccess is a discrete quantitative variable, while ProjectDuration is a continuous quantitative variable.
  2. ProjectSuccess is a binary categorical variable, while ProjectDuration is a continuous quantitative variable. (correct answer)
  3. Both are discrete variables, but ProjectSuccess is nominal while ProjectDuration is ratio.
  4. ProjectSuccess is a dependent variable, while ProjectDuration is an independent variable.
Explanation: This question addresses the nature of binary (0/1) coded variables. ProjectSuccess represents two distinct categories (profitable/not profitable), making it a binary categorical variable. The numerical coding allows for calculating a mean, which is interpreted as a proportion, but its underlying nature is categorical. ProjectDuration is a measurement on a continuous scale, making it a continuous quantitative variable. Choice A incorrectly classifies ProjectSuccess as quantitative. Choice C is incorrect because duration in months, while often recorded in integers, is conceptually continuous. Choice D confuses variable type with its role in a specific model, which is not stated.

Question 18

Consider three variables from a manufacturing plant's database: X = Machine serial number, Y = Number of units produced per hour, and Z = Quality assessment ranked as 'Poor', 'Average', 'Good', or 'Excellent'. Which statement provides the most accurate classification of these variables?

  1. X is nominal, Y is discrete quantitative, and Z is ordinal. (correct answer)
  2. X is quantitative, Y is continuous quantitative, and Z is nominal.
  3. X is ordinal, Y is discrete quantitative, and Z is nominal.
  4. X is nominal, Y is continuous quantitative, and Z is ordinal.
Explanation: This question requires the simultaneous and correct classification of three distinct variable types. X (Machine serial number) is a unique identifier with no inherent order, making it nominal categorical. Y (Number of units produced) is a count, which is a discrete quantitative variable. Z (Quality assessment) has categories with a clear, meaningful order ('Poor' < 'Average' < 'Good' < 'Excellent'), making it ordinal categorical. Choice A correctly identifies all three. The other choices contain at least one misclassification: B calls X quantitative, C calls X ordinal and Z nominal, and D calls Y continuous.

Question 19

A consulting firm develops a 'Client Risk Score' for each of its clients. The score is an integer from 0 to 100, calculated from several inputs, including payment history (quantitative), industry volatility (categorical), and contract duration (quantitative). A higher score indicates a higher risk of the client defaulting.

How should this 'Client Risk Score' itself be classified?

  1. As a nominal categorical variable, because it classifies clients into risk groups.
  2. As a discrete quantitative variable, because it is a numerical score with meaningful intervals. (correct answer)
  3. As a composite categorical variable, because it is derived from both quantitative and categorical inputs.
  4. As an ordinal variable, because while a higher score means more risk, the difference between a score of 80 and 81 may not be the same as between 20 and 21.
Explanation: Composite scores like credit scores or risk scores are designed to be quantitative. Although derived from mixed inputs, the final score is treated as having interval (or even ratio) properties. It is discrete because it takes on integer values. A score of 80 is meaningfully higher than 79, and the scale is consistent. Therefore, it is best classified as a discrete quantitative variable. Choice A is incorrect; it has a clear order and magnitude. Choice C is incorrect because the output type is not determined by the input types. Choice D suggests it is ordinal, which is a common misconception; these scores are typically designed such that the intervals are meaningful and consistent, making them stronger than just ordinal.

Question 20

A hotel chain wants to analyze customer satisfaction. They collect survey data where customers rate their stay on a scale of 1 to 5, where 1 = Very Dissatisfied, 2 = Dissatisfied, 3 = Neutral, 4 = Satisfied, and 5 = Very Satisfied. The analytics team debates how to treat this 'Satisfaction Rating' variable. Which statement presents the most precise statistical classification of this variable?

  1. The variable is quantitative discrete because it is represented by countable integer values.
  2. The variable is quantitative continuous because satisfaction exists on a spectrum that the numbers approximate.
  3. The variable is categorical nominal because each number is just a label for a distinct satisfaction category.
  4. The variable is categorical ordinal because the numeric values represent ordered categories with non-uniform differences. (correct answer)
Explanation: The correct answer is D. This is a classic Likert scale. The numbers (1, 2, 3, 4, 5) represent categories that have a clear, logical order (Very Satisfied is better than Satisfied). However, the difference in satisfaction between a '1' and '2' is not necessarily the same as the difference between a '4' and '5'. Because the intervals are not guaranteed to be equal, the variable is ordinal, not quantitative. A) is a common misconception; while the values are integers, they represent ordered ranks, not counts or measurements, making them ordinal. B) is incorrect; the measurement itself is not continuous. C) is incorrect because the categories have a meaningful order, so it is not nominal.