EXIN Data Analytics Foundation study plan

Define data analytics, data science, business intelligence and data mining in your own words and state how the four differ in purpose and typical output.

Distinguish descriptive, diagnostic, predictive and prescriptive analytics and classify ten realistic business scenarios into the correct type.

Compare structured, semi-structured and unstructured data and give two examples of each with the storage format normally used.

Explain the difference between quantitative and qualitative data and between discrete and continuous variables, then label ten sample fields.

Describe what a KPI is and draft three KPIs for a fictional retail or service organisation, including the calculation formula for each.

Explain how a data warehouse, data lake and data mart differ in structure, users and typical content.

Compare OLTP and OLAP systems on purpose, schema design and query patterns.

Describe the purpose of ETL and ELT pipelines and identify at which stage cleaning, transformation and loading occur.

Interpret measures of central tendency and dispersion (mean, median, mode, range, variance, standard deviation) and explain when the median is preferred over the mean.

Explain correlation and causation, and identify three ways a reported correlation could be misleading.

List the phases of a typical data analysis lifecycle and state the key question answered in each phase.

Translate a vague business request into three specific, answerable analytical questions with defined success criteria.

Identify primary and secondary data sources and evaluate two sources for reliability, recency and fitness for purpose.

Distinguish data requirements from functional requirements and write a short requirements statement for a small analysis.

Recognise the main data quality dimensions (accuracy, completeness, consistency, timeliness, validity, uniqueness) and give one failure example for each.

Apply a structured data cleaning routine to a small dataset and document every transformation performed.

Detect and handle missing values, duplicates and outliers, and justify the chosen treatment for each case.

Perform basic data transformation tasks such as normalisation, recoding categories and deriving new calculated fields.

Select an appropriate chart type for a given question and justify why alternatives are weaker.

Interpret a frequency distribution and a simple cross-tabulation to describe a dataset's shape and segments.

Formulate a testable hypothesis and state the corresponding null and alternative hypotheses for a business question.

Explain sampling, sample size and sampling bias, and identify the sampling method used in three published examples.

Interpret p-values, confidence intervals and statistical significance without overstating conclusions.

Explain what a regression model does and interpret slope, intercept and R-squared in plain language.

Distinguish supervised from unsupervised learning and name one clustering and one classification use case.

Match five analytical questions to the most suitable visualisation and justify each choice.

Apply design principles for clarity: correct axis scaling, meaningful ordering, minimal chart junk and accessible colour use.

Critique three charts for misleading design choices and rewrite each caption to state what the chart does and does not show.

Structure a report using an executive summary, findings, evidence and recommendations, and keep the summary under 150 words.

Adapt the same findings for a technical audience and for an executive audience, adjusting vocabulary, detail and emphasis.

Identify the main data privacy principles relevant to analytics work, including purpose limitation, data minimisation and retention.

Classify data by sensitivity and specify handling rules for each class in a short table.

Describe the roles of data owner, data steward and data custodian and assign them for a fictional dataset.

Explain anonymisation and pseudonymisation and state the residual re-identification risk of each.

Explain why data quality management and metadata documentation are governance responsibilities, not only technical tasks.

Evaluate four ethical dilemmas in analytics using a stated decision framework and reach a defensible recommendation for each.

Identify common cognitive and analytical biases, such as confirmation bias and survivorship bias, and describe one control against each.

Explain accountability and transparency obligations when analytics output informs decisions about people.

Consolidate the eight weeks of notes into a single revision sheet covering all four domains.

Complete a timed practice assessment under exam conditions and review every incorrect answer against the source material.