IIBA-CBDA practice questions: Source Data

5 free questions from 49 on this area · answer and explanation for each · no sign-up

These 5 questions come from the Source Data section of our IIBA-CBDA bank (49 questions on this area, which carries 15% of the real exam). Every question is original, with the correct answer explained and linked to the source it is drawn from.

Try 6 free IIBA-CBDA questions → All IIBA-CBDA sample questions

Free: 6 questions in study mode, no card. All 49 Source Data questions and the full IIBA-CBDA bank: $15 one-time.

1/5 · Source Data

While profiling a customer table sourced for a marketing campaign, an analyst finds that 18% of the 'email_address' fields are blank. Every email that IS present is correctly formatted and valid, no duplicate customer rows exist, and records are refreshed daily. Which data quality dimension is MOST directly compromised by the blank email fields?

AAccuracy

BUniqueness

CCompleteness

DTimeliness

Answer: C. Data quality is assessed across dimensions including completeness, accuracy, consistency, timeliness, validity, and uniqueness. Missing required values is a completeness problem. The distractors are explicitly ruled out by the scenario: accuracy (present values are valid), uniqueness (no duplicates), and timeliness (daily refresh). Source: IIBA Business Data Analytics Guide — Source Data

2/5 · Source Data

As part of collecting data, an analyst documents, for a key dataset, exactly where the data originates, what transformations are performed on it along the way, and where it is finally stored — in order to help assess its quality. The guide refers to understanding this end-to-end flow as which concept?

AData profiling

BData lineage

CSource-to-target mapping

DData sampling

Answer: B. Within Collect Data, the guide instructs analysts to understand where data comes from, what transformations are performed, and where it is finally stored in order to assess data quality, and explicitly names this data lineage. It is distinct from sampling, profiling, and source-to-target mapping. Source: IIBA Business Data Analytics Guide — Source Data

3/5 · Source Data

While wrangling a freshly collected sensor dataset, an analyst notices a handful of temperature readings of 999 degrees recorded by a malfunctioning probe, far outside any physically possible range. The analyst is preparing the data and must decide how to treat these values. Which action reflects sound judgment at this stage?

AReplace the 999 values with the overall column average immediately, without checking whether the probe was actually faulty.

BLeave all values untouched because altering any collected value is always forbidden and would bias the results.

CInvestigate the 999 values to confirm they are sensor errors, then treat or remove them with the reason documented before analysis proceeds.

DSilently delete every record above the dataset's mean to make the distribution look cleaner.

Answer: C. Outlier handling during data wrangling requires investigation first: determine whether an extreme value is a genuine observation or an error. Here the readings are physically impossible and tied to a known malfunction, so confirming the cause and then treating or removing them — with the rationale recorded for transparency and reproducibility — is correct. Blanket rules ('never alter values' or 'always impute the mean') ignore the investigative judgment the task demands. Source: IIBA Business Data Analytics Guide — Source Data

4/5 · Source Data · hard

An analyst wants to establish whether a new checkout-page layout causes higher conversion, not merely correlates with it. Rather than only observing customers who happen to see the existing page, the team randomly assigns incoming visitors to either the old or new layout and records conversions for each group. Which type of data collection is being used, and what does it enable that pure observation does not?

AExperimental collection, which through randomized assignment supports stronger causal inference than observational data.

BPassive collection, which removes the need to define any business question first.

CSecondary data collection, which reuses an external dataset instead of generating new data.

DObservational collection, which through randomized assignment proves causation directly.

Answer: A. Randomly assigning visitors to old/new layouts is experimental data collection (an A-B test). The intervention plus randomization balances confounding factors across groups, which is what permits causal inference — establishing that the layout causes the conversion change. Observational data merely records what occurs naturally and supports correlation, not causation. The collection is active and primary, not passive or secondary. Source: IIBA Business Data Analytics Guide — Source Data

5/5 · Source Data · hard

A subscription business wants to predict next-quarter churn. An analyst decides to pull customer behavior data going back several years, reasoning that more history is always better. A senior colleague cautions that very old behavior may reflect a different product, pricing, and customer base than today's, while too short a window may miss seasonal patterns. What sourcing decision does this exchange most directly highlight?

ADeciding between primary and secondary data sources, based on which of the two would be quicker and cheaper to obtain for the churn model

BChoosing an appropriate time horizon so the data sourced is relevant to current conditions yet long enough to capture meaningful patterns

CSelecting the correct unit of analysis for the churn model, so the customer behavior data is sourced in one consistent structure

DAssessing the velocity of incoming data, so the churn model receives customer behavior events fast enough to predict next-quarter churn

Answer: B. Determining the data needed includes deciding the time horizon, or look-back window — how far back the data should extend. Too long risks including history that no longer represents current conditions; too short risks missing seasonality or trends. This is a distinct sourcing decision from unit of analysis, source origin, or data velocity. Source: IIBA Business Data Analytics Guide — Source Data

Try 6 more free IIBA-CBDA questions → See the whole IIBA-CBDA bank

Other IIBA-CBDA areas

The same kind of free sample for every other section of the IIBA-CBDA bank:

Analyze Data49 q Interpret and Report Results51 q Secure, Manage and Document Data49 q Identify the Research Questions52 q

Practise IIBA-CBDA with instant feedback

6 free questions in study mode · no card · full IIBA-CBDA bank with area filters and the error log: $15 one-time · no dumps, no ads.

Start IIBA-CBDA free →