IIBA CBDA Certification in Business Data Analytics

A data analyst is asked to investigate why customer churn increased last quarter. Which type of analytics approach is MOST appropriate to start with?

• APredictive analytics to forecast future churn rates
• BDiagnostic analytics to identify root causes of the churn increase
• CPrescriptive analytics to recommend retention actions
• DDescriptive analytics to summarize overall churn statistics

When formulating a business research question, which characteristic is MOST important to ensure the question is answerable with available data?

• AThe question must align with the organization's strategic objectives
• BThe question must be specific, measurable, and scoped to available data
• CThe question must be approved by senior leadership before analysis begins
• DThe question must reference a hypothesis supported by prior literature

An organization wants to understand whether a new marketing campaign increased sales. What is the BEST way to frame this as a testable hypothesis?

• AThe campaign will improve brand awareness among target customers
• BSales revenue in the post-campaign period exceeds pre-campaign revenue by at least 10%
• CThe marketing campaign was successfully implemented on schedule
• DCustomer satisfaction scores will improve after the campaign

A business analyst is defining the scope of a data analytics project. Which factor is MOST critical to establish before finalizing the research questions?

• AThe visualization tools that will be used to present findings
• BThe stakeholders who will receive the final report
• CThe business objectives and constraints the analysis must address
• DThe statistical methods that will be applied to the data

Which of the following BEST distinguishes a business question from a data question in analytics work?

• AA business question uses domain language; a data question uses technical terminology
• BA business question asks what outcome is desired; a data question asks what data is neede…
• CA business question is for executives; a data question is for analysts
• DA business question focuses on KPIs; a data question focuses on data quality

A retail company notices that online cart abandonment is high. Before beginning analysis, what should the analyst do FIRST?

• APull all available e-commerce transaction data for the past year
• BIdentify whether reducing cart abandonment is a strategic priority and define the specifi…
• CBenchmark cart abandonment rates against industry competitors
• DRecommend A/B testing on the checkout page to reduce abandonment

During stakeholder interviews, an analyst learns that executives want to understand future revenue trends, while operations wants to reduce delivery delays. Which action BEST helps define unified research questions?

• APrioritize executive requests since they have higher organizational authority
• BBuild separate reports for each stakeholder group with distinct research questions
• CFacilitate a collaborative session to align stakeholder needs into coherent, shared resea…
• DProceed with the analysis using all stakeholder questions and let results determine prior…

An analyst is tasked with improving employee retention. Which research question is MOST analytically actionable?

• AWhy do employees leave the company?
• BWhat factors most strongly predict voluntary resignation within the first two years of em…
• CHow can we improve employee satisfaction?
• DWhat is the cost of employee turnover?

A CBDA candidate is reviewing a project brief that states: 'Analyze all available data to find ways to improve the business.' What is the PRIMARY problem with this as a research question?

• AIt does not specify which department owns the data
• BIt is too broad, lacks a specific business outcome, and is not measurable
• CIt does not reference any statistical technique
• DIt fails to identify the data sources that will be used

Which of the following BEST describes the role of assumptions in framing research questions for data analytics?

• AAssumptions should be eliminated by collecting more data before defining the question
• BAssumptions must be explicitly documented so they can be tested or validated during analy…
• CAssumptions are only relevant when external data sources are used
• DAssumptions become irrelevant once a hypothesis is formally stated

Which analytics type focuses on understanding what is likely to happen in the future based on historical patterns?

• ADescriptive analytics
• BDiagnostic analytics
• CPredictive analytics
• DPrescriptive analytics

A business analyst determines that an analytics project has clearly overlapping scope with another team's ongoing initiative. What is the BEST course of action?

• AContinue independently to avoid project delays
• BEscalate the overlap to senior management and await resolution
• CCoordinate with the other team to align research questions and avoid duplicated effort
• DNarrow the research question to exclude the overlapping areas

An analyst is sourcing data for a customer segmentation study. Which criteria should be PRIMARILY evaluated when selecting an internal data source?

• AThe recency, completeness, and relevance of the data to the research question
• BThe cost of extracting data from the internal system
• CWhether the data source has been used in previous projects
• DThe name and position of the data owner in the organization

Which dimension of data quality describes whether data values conform to defined formats, ranges, and business rules for the attribute?

• ACompleteness
• BConsistency
• CValidity
• DTimeliness

A data analyst discovers that customer records in two different systems show different birth dates for the same individual. Which data quality dimension is violated?

• AUniqueness
• BConsistency
• CCompleteness
• DValidity

An analyst is planning to use a third-party data provider for market research. What governance consideration is MOST important before acquiring the data?

• AWhether the provider offers API access for automated ingestion
• BWhether the data license permits the intended use and complies with privacy regulations
• CWhether the provider's data format matches the internal data warehouse schema
• DWhether the cost of the data fits within the project budget

Which technique is MOST effective for identifying missing values, outliers, and distribution patterns in a dataset before formal analysis?

• ARegression modeling
• BData profiling
• CA/B testing
• DCluster analysis

A data analyst receives a dataset where 30% of the values in a critical field are missing. What is the MOST appropriate first step?

• ADelete all rows with missing values to ensure data cleanliness
• BInvestigate the cause and pattern of missingness before deciding on a handling approach
• CReplace all missing values with the column mean to preserve sample size
• DFlag the dataset as unusable and request a new data pull

Which of the following scenarios represents a data governance violation in a business analytics context?

• AAn analyst uses anonymized customer data to build a churn prediction model
• BAn analyst shares identifiable customer purchase records with an external vendor without…
• CAn analyst documents data lineage for all inputs used in a financial model
• DAn analyst requests approval from the data steward before accessing a restricted dataset

An analyst is evaluating whether a survey dataset can be used for a customer behavior study. The survey was conducted three years ago. Which concern is MOST relevant?

• AThe survey may not have used a probabilistic sampling method
• BThe data may lack timeliness and may not reflect current customer behavior
• CThe survey questions may not have been validated by psychometricians
• DThe dataset may contain too many variables for efficient processing

Which term describes the documented history of a data element's origin, movement, transformation, and storage throughout its lifecycle?

• AData dictionary
• BData lineage
• CData catalog
• DData schema

A business analyst is selecting data sources for a supply chain optimization project. Internal inventory data is available but incomplete. An external logistics provider offers complementary data. What is the BEST approach?

• AUse only the internal data to maintain data governance control
• BUse only the external data since it is from a specialized provider
• CAssess both sources against research requirements, then integrate them with appropriate q…
• DRequest IT to build a new data collection system before proceeding

What is the PRIMARY purpose of data cleaning in the analytics process?

• ATo reduce the size of the dataset for faster processing
• BTo ensure the data is accurate, consistent, and suitable for analysis
• CTo transform raw data into visualizations for stakeholders
• DTo secure data against unauthorized access

An organization has structured transaction data in a relational database and unstructured customer feedback in emails. The analyst needs both for the project. What is this combination called?

• AFederated data
• BMixed-methods data
• CHeterogeneous or multi-source data
• DPrimary and secondary data

Under data privacy best practices in analytics, which technique replaces personally identifiable information with artificial identifiers to enable analysis while protecting individual identity?

• AEncryption
• BAggregation
• CPseudonymization
• DData masking

A business analyst applies a Z-score calculation and identifies values more than 3 standard deviations from the mean. What is the MOST likely purpose of this step?

• ATo normalize the data for machine learning model training
• BTo detect potential outliers that may distort analysis results
• CTo segment customers into high-value and low-value groups
• DTo calculate the statistical significance of a hypothesis test

Which measure of central tendency is MOST resistant to the influence of extreme outliers in a dataset?

• AMean
• BVariance
• CMedian
• DStandard deviation

An analyst runs a Pearson correlation between marketing spend and sales revenue and finds r = 0.85. What does this value indicate?

• AMarketing spend causes a 0.85% increase in sales revenue
• BThere is a strong positive linear relationship between marketing spend and sales revenue
• C85% of the variance in sales revenue is explained by marketing spend
• DThe probability that this relationship occurred by chance is 15%

A retail analyst wants to group customers with similar purchasing patterns into segments without specifying the number of groups in advance. Which technique is MOST appropriate?

• ALinear regression
• BK-means clustering
• CHierarchical clustering
• DLogistic regression

A p-value of 0.03 is obtained in a hypothesis test using a significance level of α = 0.05. What is the CORRECT interpretation?

• AThere is a 3% probability that the null hypothesis is true
• BThe result is statistically significant; reject the null hypothesis
• CThe effect size is 3% of the observed difference
• DThe test has a 97% confidence level

Which type of analysis examines how different combinations of input variable values affect an output to understand sensitivity and risk?

• ARoot cause analysis
• BSensitivity analysis
• CRegression analysis
• DTime-series analysis

An analyst builds a predictive model that performs well on training data but poorly on new data. What is this phenomenon called?

• AUnderfitting
• BOverfitting
• CMulticollinearity
• DHeteroscedasticity

A business analyst is comparing average transaction values across four regional sales teams. Which statistical test is MOST appropriate?

• AChi-square test
• BOne-way ANOVA
• CPaired t-test
• DLinear regression

Which analytics technique is BEST suited for identifying patterns in customer text feedback to classify sentiment as positive, neutral, or negative?

• ALogistic regression on structured purchase data
• BNatural language processing with sentiment analysis
• CTime-series decomposition
• DAssociation rule mining

An analyst decomposes a sales time series into trend, seasonal, and residual components. What is the PRIMARY business value of this decomposition?

• ATo identify which customers contributed most to sales variance
• BTo separate predictable patterns from random fluctuations and support more accurate forec…
• CTo determine the statistical significance of month-over-month sales differences
• DTo identify the optimal pricing strategy for each season

A data analyst creates a confusion matrix for a binary classification model. The matrix shows 200 true positives, 50 false positives, 30 false negatives, and 720 true negatives. What is the model's precision?

• A80.0%
• B87.0%
• C86.9%
• D92.0%

Which of the following BEST describes the purpose of exploratory data analysis (EDA) in the analytics process?

• ATo confirm a pre-defined hypothesis with statistical testing
• BTo deploy a predictive model into a production environment
• CTo understand data characteristics, identify patterns, and generate hypotheses before for…
• DTo present final insights to executive stakeholders