I85PREP
⌘ K
ICDL Data Analytics study materials
ICDL Data Analytics study resources

ICDL Data Analytics (ICDL) practice questions

One question at a time. Build your ICDL Data Analytics understanding.

First 50 of 200 questions. Each one lists the choices, the correct answer, and an explanation. The checker at the top of this page saves progress in this browser when it is available.

Continue in the practice tool above to load more questions, 50 at a time.

Question 1Data analytics concepts and fundamentals

Which measurement scale classifies data into categories that have no natural order?

  1. Ordinal
  2. Ratio
  3. Interval
  4. Nominal Correct answer.

Explanation

The nominal scale only labels or names categories, so values can be compared for equality but not ranked. Ordinal, interval and ratio scales all involve some form of ordering.

Question 2Data analytics concepts and fundamentals

In statistics, what does the term population mean?

  1. The subset of items that returned a completed survey
  2. The average value calculated from a set of observations
  3. The complete set of all items of interest in a study Correct answer.
  4. A small group selected at random from a larger group

Explanation

A population is every item that the study is meant to describe, whether people, transactions or products. Samples are drawn from it so that conclusions can be generalised back to it.

Question 3Data analytics concepts and fundamentals

Which measure of central tendency is most affected by a few extremely large values?

  1. Median
  2. Arithmetic mean Correct answer.
  3. Trimmed mean
  4. Mode

Explanation

The arithmetic mean adds every value together, so an extreme value pulls the total, and therefore the average, strongly in its direction. The median, mode and trimmed mean are all designed to resist this pull.

Question 4Data analytics concepts and fundamentals

Which chart type is most appropriate for showing the distribution of a single continuous variable?

  1. Line chart
  2. Histogram Correct answer.
  3. Scatter plot
  4. Pie chart

Explanation

A histogram groups a continuous variable into bins and shows how many observations fall in each bin, revealing shape, spread and skew. The other chart types are built for proportions, relationships or change over time.

Question 5Data analytics concepts and fundamentals

A set of customer ages has a mean of 40 and a median of 35. What does this pattern suggest about the distribution?

  1. It is perfectly symmetric
  2. It is skewed to the left
  3. It is skewed to the right Correct answer.
  4. The ages were recorded incorrectly

Explanation

When the mean exceeds the median, a long tail of high values is pulling the average upward, which is right (positive) skew. A left-skewed distribution produces the reverse pattern, with the mean below the median.

Question 6Data analytics concepts and fundamentals

Which of the following is an example of unstructured data?

  1. A list of product prices with their tax rates
  2. A CSV file of monthly sales totals
  3. A collection of audio recordings of customer calls Correct answer.
  4. A table of employee salaries held in a spreadsheet

Explanation

Unstructured data have no predefined tabular model, which is true of audio, video, images and free text. Spreadsheets, price lists and CSV files all impose a fixed set of columns and rows.

Question 7Data analytics concepts and fundamentals

Two variables have a correlation coefficient of -0.85. How should this be interpreted?

  1. A strong positive relationship
  2. A strong negative linear relationship Correct answer.
  3. No relationship of any kind
  4. A weak negative relationship

Explanation

Correlation coefficients range from -1 to +1, and values near -1 indicate a strong negative linear association. The magnitude 0.85 is large, and the minus sign shows the two variables move in opposite directions.

Question 8Data analytics concepts and fundamentals

In an ETL process, what happens during the transform step?

  1. Records are written to the target database
  2. Records are deleted after processing
  3. Records are read from source systems
  4. Records are cleaned and reformatted Correct answer.

Explanation

Transformation applies rules that clean, standardise, join or recalculate the extracted data so that it conforms to the target model. Reading from sources is extraction and writing to the destination is loading.

Question 9Data analytics concepts and fundamentals

A survey about internet usage is sent only to customers who have an email address on file. Which problem does this create?

  1. Recall bias
  2. Undercoverage bias Correct answer.
  3. Measurement error
  4. Response bias

Explanation

The sampling frame leaves out customers without an email address, so part of the population has no chance of being selected. This is undercoverage, a form of selection bias that distorts the results.

Question 10Data analytics concepts and fundamentals

Which statistic expresses the spread of values around the mean in the same units as the original data?

  1. Standard deviation Correct answer.
  2. Variance
  3. Coefficient of variation
  4. Correlation coefficient

Explanation

The standard deviation is the square root of the variance, which returns the measure to the original unit, such as kilograms or euros. Variance is expressed in squared units, so it is harder to interpret directly.

Question 11Data analytics concepts and fundamentals

Which statement best explains how a key performance indicator differs from an ordinary metric?

  1. It is tied to a goal and has a target Correct answer.
  2. It is always expressed as a percentage
  3. It is used only in financial reporting
  4. It must be refreshed in real time

Explanation

A metric becomes a KPI when it is explicitly linked to a strategic objective and compared against a target, so it can drive decisions. Metrics can be tracked without any target or strategic link and still be useful for context.

Question 12Data analytics concepts and fundamentals

Which description best characterises a data lake?

  1. It holds only the current day's transactional records
  2. It stores raw data in its native format until needed Correct answer.
  3. It stores only aggregated numeric data in fixed tables
  4. It requires all data to be modelled before loading

Explanation

A data lake keeps data in its original form, such as files, logs or JSON, and applies structure when the data are read. A data warehouse, by contrast, requires data to be modelled and transformed before loading.

Question 13Data analytics concepts and fundamentals

A numeric column contains a small number of missing values. Which action is usually most appropriate?

  1. Ignore them in all analyses
  2. Delete the entire dataset
  3. Replace them with zero without checking
  4. Impute them with the column mean or median Correct answer.

Explanation

Imputing with a measure of central tendency keeps the affected records and limits distortion when the proportion missing is small. Deleting the whole dataset or substituting an arbitrary value throws away information or introduces bias.

Question 14Data analytics concepts and fundamentals

Which statement about an outlier in a dataset is correct?

  1. It should be investigated before any decision to remove it Correct answer.
  2. It is always caused by a data entry error
  3. It has no effect on the mean of a dataset
  4. It should always be deleted from the dataset

Explanation

An outlier may be an error, but it may also be a genuine rare event that matters, such as a large fraudulent transaction. The correct practice is to check the source and context before deciding whether to correct, retain or exclude it.

Question 15Data analytics concepts and fundamentals

A hypothesis test returns p = 0.03 and the significance level is set at 0.05. What is the correct conclusion?

  1. The result is not statistically significant
  2. There is a 3% chance the null hypothesis is true
  3. The null hypothesis is rejected at the 5% level Correct answer.
  4. The effect being tested must be large

Explanation

The null hypothesis is rejected whenever the p-value falls below the chosen significance level, and 0.03 is below 0.05. The p-value is the probability of data this extreme if the null were true, not the probability that the null is true.

Question 16Data analytics concepts and fundamentals

A retailer's overall conversion rate rose this year, yet conversion fell in every customer segment. What best explains this?

  1. Conversion was measured on the wrong scale
  2. The sample was too small to detect any change
  3. A shift in the mix of customer segments between the years Correct answer.
  4. The data must contain duplicate records

Explanation

This is Simpson's paradox: an overall rate can move in the opposite direction to every subgroup when the proportions of those subgroups change. The aggregate is dominated by the shift in weighting rather than by any segment improving.

Question 17Data analytics concepts and fundamentals

A regression model reports an R-squared value of 0.85. How should this be interpreted?

  1. 85% of the observations were used to fit the model
  2. The model causes 85% of the outcome
  3. 85% of the variation in the outcome is explained Correct answer.
  4. 85% of predictions are exactly correct

Explanation

R-squared is the proportion of variance in the dependent variable accounted for by the model. A value of 0.85 therefore means the predictors explain about 85% of the variation observed in the outcome.

Question 18Data analytics concepts and fundamentals

What is metadata?

  1. Data that describes other data Correct answer.
  2. Data held outside the main warehouse
  3. Data that has been aggregated for reporting
  4. Data that has been anonymised for sharing

Explanation

Metadata is information about data, such as its source, owner, format, definition and last update date. It makes data discoverable and helps analysts judge whether a dataset is suitable and trustworthy.

Question 19Data analytics concepts and fundamentals

Which file format is best suited to holding plain tabular data for analysis?

  1. PNG
  2. CSV Correct answer.
  3. MP3
  4. PDF

Explanation

CSV stores rows and columns as delimited plain text, which almost every analysis tool can read directly. The other formats are designed for images, audio or fixed-layout documents.

Question 20Data analytics concepts and fundamentals

Which of these is a measure of dispersion?

  1. Range Correct answer.
  2. Median
  3. Mode
  4. Mean

Explanation

The range describes how spread out values are, being the difference between the maximum and the minimum. Mean, median and mode all describe the centre of a distribution rather than its spread.

Question 21Data analytics concepts and fundamentals

What is the main purpose of data cleansing?

  1. Reducing the number of columns in a table
  2. Finding and correcting inaccurate records Correct answer.
  3. Encrypting records before storage
  4. Increasing the speed of a database server

Explanation

Data cleansing detects and resolves errors such as duplicates, inconsistent formats, impossible values and misspellings. Its aim is accuracy and consistency, which are prerequisites for reliable analysis.

Question 22Data analytics concepts and fundamentals

Which of these is one of the commonly cited characteristics of big data?

  1. Variety Correct answer.
  2. Indexing
  3. Aggregation
  4. Normalisation

Explanation

Variety is one of the widely used big data characteristics, alongside volume and velocity, and refers to data arriving in many different forms. Normalisation, aggregation and indexing are processing techniques rather than properties of the data.

Question 23Data analytics concepts and fundamentals

Which of the following is an example of primary data?

  1. Responses collected in a survey run by the analyst Correct answer.
  2. Industry reports purchased from a research firm
  3. Articles downloaded from a journal database
  4. Census figures published by a government agency

Explanation

Primary data are collected first-hand by the person or team carrying out the analysis for the purpose at hand. Published census figures, bought reports and journal articles were gathered by someone else and are therefore secondary.

Question 24Data analytics concepts and fundamentals

A candidate's score lies at the 80th percentile. What does this mean?

  1. The candidate answered 80% of the questions correctly
  2. The candidate is among the top 20 marks overall
  3. The candidate scored 80 out of 100 marks
  4. 80% of candidates scored at or below it Correct answer.

Explanation

A percentile states relative standing: the 80th percentile is the value below which roughly 80% of the observations fall. It says nothing about the raw score or the percentage of questions answered correctly.

Question 25Data analytics concepts and fundamentals

A retail chain's sales rise sharply every December and fall again in January. Which time series component does this describe?

  1. Seasonality Correct answer.
  2. Random variation
  3. Cyclical fluctuation
  4. Trend

Explanation

Seasonality is a pattern that repeats within a fixed calendar period, such as a month or a quarter, and December peaks are a classic example. Trend and cyclical movements operate over longer, less regular horizons.

Question 26Data analytics concepts and fundamentals

Which term describes data stored in a fixed, predefined format such as rows and columns in a relational table?

  1. Semi-structured data
  2. Structured data Correct answer.
  3. Metadata
  4. Unstructured data

Explanation

Structured data follows a predefined schema, such as columns and data types in a relational table, which makes it easy to query and analyse. Unstructured and semi-structured data do not fit neatly into a fixed tabular schema.

Question 27Data analytics concepts and fundamentals

Which type of analytics answers the question 'What happened?' by summarising historical data?

  1. Predictive analytics
  2. Descriptive analytics Correct answer.
  3. Diagnostic analytics
  4. Prescriptive analytics

Explanation

Descriptive analytics summarises past data, often using totals, averages, and trends, to show what has occurred. It does not by itself explain causes or forecast future outcomes.

Question 28Data analytics concepts and fundamentals

Which data quality dimension is concerned with whether a value is correct and free from error?

  1. Timeliness
  2. Consistency
  3. Completeness
  4. Accuracy Correct answer.

Explanation

Accuracy measures whether data correctly represents the real-world fact it is intended to describe. A value can be present and timely yet still be inaccurate if it is wrong.

Question 29Data analytics concepts and fundamentals

A researcher selects every tenth name from an alphabetical list of employees. Which sampling method is being used?

  1. Cluster sampling
  2. Stratified sampling
  3. Simple random sampling
  4. Systematic sampling Correct answer.

Explanation

Systematic sampling selects items at regular intervals from an ordered list after choosing a starting point. Selecting every tenth name follows this fixed-interval pattern.

Question 30Data analytics concepts and fundamentals

Which measure of central tendency is most affected by extreme values in a dataset?

  1. Trimmed mean
  2. Median
  3. Mean Correct answer.
  4. Mode

Explanation

The mean uses every value in its calculation, so very large or very small values can pull it substantially. The median and trimmed mean are designed to resist this influence.

Question 31Data analytics concepts and fundamentals

Which stage of the data lifecycle involves generating or capturing data for the first time?

  1. Data collection Correct answer.
  2. Data modelling
  3. Data visualisation
  4. Data cleansing

Explanation

The data lifecycle begins with collection, when data is generated, captured, or acquired from sources. Cleansing, modelling, and visualisation occur after the data has been collected.

Question 32Data analytics concepts and fundamentals

Which of these is an example of semi-structured data?

  1. A JSON document with nested fields Correct answer.
  2. A scanned image
  3. A CSV file with fixed columns
  4. A binary audio file

Explanation

Semi-structured data contains organisational markers such as tags or nested fields but does not need a rigid table schema, and JSON is a common example. Fixed CSV columns are structured, while images and audio are unstructured.

Question 33Data analytics concepts and fundamentals

Which attribute should a key performance indicator have?

  1. It should be difficult to measure
  2. It should be linked to a strategic objective Correct answer.
  3. It should be reported only once a year
  4. It should change randomly from day to day

Explanation

A key performance indicator should be tied to an important strategic objective and measured consistently over time. Randomness, difficulty of measurement, and very infrequent reporting weaken its usefulness.

Question 34Data analytics concepts and fundamentals

A company observes that sales of ice cream and sales of sunscreen rise together during summer. Which conclusion is most appropriate?

  1. The relationship must be a coincidence with no cause
  2. Sunscreen purchases directly cause ice cream purchases
  3. Ice cream purchases directly cause sunscreen purchases
  4. A hidden variable such as warm weather may drive both increases Correct answer.

Explanation

Correlation does not imply causation, and a third variable such as warm weather can influence both products. Without a controlled study, a causal claim is not justified.

Question 35Data analytics concepts and fundamentals

A manager wants to show the proportion of total revenue contributed by each of five product categories. Which chart is most appropriate?

  1. Pie chart Correct answer.
  2. Histogram
  3. Scatter plot
  4. Line chart

Explanation

A pie chart displays parts of a whole, making it suitable for showing each category's share of total revenue. Line charts, scatter plots, and histograms serve different analytical purposes.

Question 36Data analytics concepts and fundamentals

In a normal distribution, approximately what percentage of observations lie within one standard deviation of the mean?

  1. 50%
  2. 68% Correct answer.
  3. 99.7%
  4. 95%

Explanation

In a normal distribution, about 68% of observations fall within one standard deviation of the mean under the empirical rule. About 95% fall within two standard deviations and about 99.7% within three.

Question 37Data analytics concepts and fundamentals

A test yields a p-value of 0.20 at a 0.05 significance level. What is the appropriate decision?

  1. Fail to reject the null hypothesis Correct answer.
  2. Reject the null hypothesis
  3. Increase the sample size until the p-value falls below 0.05
  4. Accept the null hypothesis as true

Explanation

A p-value above the significance level provides insufficient evidence to reject the null hypothesis. Failing to reject does not prove that the null hypothesis is true.

Question 38Data analytics concepts and fundamentals

What is the main purpose of a data warehouse?

  1. To store only unstructured multimedia files
  2. To handle high-volume day-to-day transaction processing
  3. To replace all operational databases
  4. To support analytical reporting by integrating data from multiple sources Correct answer.

Explanation

A data warehouse consolidates data from multiple operational sources and organises it for querying and analytical reporting. It is not designed primarily for real-time transaction processing.

Question 39Data analytics concepts and fundamentals

Which activity is part of data governance?

  1. Writing application code for a mobile app
  2. Defining policies for data access and ownership Correct answer.
  3. Designing a company logo
  4. Installing network cables

Explanation

Data governance establishes policies, roles, and standards for managing data, including who may access it and who owns it. Technical coding, branding, and cabling are not governance activities.

Question 40Data analytics concepts and fundamentals

A researcher surveys shoppers in a shopping mall during weekday afternoons. Which group is most likely to be underrepresented?

  1. Retired people
  2. Full-time employees Correct answer.
  3. Local residents
  4. Part-time workers

Explanation

Full-time employees are likely to be at work during weekday afternoons, so they are less available to be surveyed in a shopping mall at that time. This creates a coverage or selection bias.

Question 41Data analytics concepts and fundamentals

Which SQL clause is used to filter individual rows before aggregation?

  1. WHERE Correct answer.
  2. HAVING
  3. ORDER BY
  4. GROUP BY

Explanation

The WHERE clause filters rows before grouping and aggregation takes place. HAVING filters groups after aggregation, while ORDER BY sorts results.

Question 42Data analytics concepts and fundamentals

A dataset records income in dollars. To compare income across countries with different currencies, what should be done first?

  1. Round every value to the nearest million
  2. Delete the income column
  3. Convert all values to a common currency Correct answer.
  4. Replace all values with their average

Explanation

Comparing monetary values across countries requires a common scale, so currency conversion is needed before comparison. Deleting, over-rounding, or replacing values with an average would destroy information.

Question 43Data analytics concepts and fundamentals

Which design choice best improves a dashboard's usefulness for executives?

  1. Placing the most important indicators prominently at the top Correct answer.
  2. Refreshing the dashboard only once a year
  3. Using as many colours as possible
  4. Including every available data field

Explanation

Executives need to see the most important indicators quickly, so prominence and clear hierarchy improve usefulness. Clutter, excessive colour, and stale data reduce clarity.

Question 44Data analytics concepts and fundamentals

A customer's age is recorded as 250 in a database. Which data quality issue does this illustrate?

  1. Inconsistent formatting
  2. Missing data
  3. Duplicate data
  4. Invalid data Correct answer.

Explanation

An age of 250 falls outside a plausible range for a human, so the value is invalid even though it is present. Validity checks often use allowed ranges or business rules.

Question 45Data analytics concepts and fundamentals

A model estimates the probability that a customer will cancel a subscription next month. Which type of analytics is this?

  1. Descriptive analytics
  2. Predictive analytics Correct answer.
  3. Prescriptive analytics
  4. Diagnostic analytics

Explanation

Predictive analytics uses historical data and models to estimate future outcomes such as cancellation risk. It differs from describing past events or recommending actions.

Question 46Data analytics concepts and fundamentals

A machine learning model performs very well on training data but poorly on new data. What is the most likely problem?

  1. Multicollinearity
  2. Data leakage
  3. Underfitting
  4. Overfitting Correct answer.

Explanation

Overfitting occurs when a model learns patterns and noise specific to the training data, so it generalises poorly to unseen data. Underfitting would typically perform poorly on both training and new data.

Question 47Data analytics concepts and fundamentals

A disease affects 1% of a population. A test is 99% sensitive and has a 5% false positive rate. For a person who tests positive, which statement is true?

  1. The probability of disease is exactly 99%
  2. The probability cannot be estimated from the information given
  3. The probability of disease is lower than 99% because the disease is rare Correct answer.
  4. The probability of disease is exactly 1%

Explanation

When a disease is rare, many positive results can come from false positives even with a fairly accurate test. The posterior probability is therefore much lower than the test's sensitivity and must account for the base rate.

Question 48Data analytics concepts and fundamentals

In k-means clustering, what does the value of k represent?

  1. The number of iterations
  2. The number of clusters Correct answer.
  3. The distance metric
  4. The number of features

Explanation

In k-means, k is the chosen number of clusters that the algorithm will form. The algorithm then assigns observations to the nearest cluster centre and updates the centres iteratively.

Question 49Data analytics concepts and fundamentals

An A/B test shows a 2% lift in conversion with a p-value of 0.30. What is the most reasonable interpretation?

  1. The result is statistically significant
  2. The test proves the new version is better
  3. The sample size is too large
  4. The observed lift may be due to chance Correct answer.

Explanation

A p-value of 0.30 is above conventional significance thresholds, so the observed difference is compatible with random variation. It does not provide strong evidence that the new version is better.

Question 50Data analytics concepts and fundamentals

In a star schema, what is the role of a fact table?

  1. To hold unstructured documents
  2. To replace all dimension tables
  3. To store measurable events and foreign keys linking to dimension tables Correct answer.
  4. To store only descriptive attributes

Explanation

A fact table stores quantitative measures for events and foreign keys that connect to dimension tables. The dimension tables provide descriptive context for those measures.