IAI Actuarial Core Principles · Actuarial Statistics
Purpose and Function of Data Analysis in Actuarial Statistics
Data analysis is the process of collecting, checking, summarising and modelling data so that you can answer a defined question and support a decision. To solve exam questions, state the aim, follow the process steps in order, name the data type and source, flag quality issues, and pick descriptive, inferential or predictive methods.
What this chapter covers
This chapter sets the frame for the whole Actuarial Statistics module. It does not ask you to run heavy calculations. It asks you to think like an actuary who receives a messy data set and a vague request. You must say what the analysis is for, how the work will proceed, what kind of data you hold, whether you can trust it, and which type of analysis fits the question.
The chapter covers five connected ideas. First, the purpose and aims of analysis, such as describing a population, testing a hypothesis or forecasting. Second, the steps of the process, from defining the objective to communicating results. Third, types of data and sources, such as primary and secondary, cross-sectional and longitudinal, discrete and continuous. Fourth, data quality, cleaning and ethics. Fifth, the split between descriptive, inferential and predictive analysis.
The later chapters build on these ideas. Data analysis methods, distributions, inference, regression and Bayesian methods all assume you have already framed the problem and checked the data. Questions in the written section often wrap a numerical task inside a short scenario. Marks go to the student who first frames the problem in plain language. The syllabus gives Data analysis a 10% topic weighting for CS1, so treat it as a compact, high-return chapter.
This chapter is mostly words, not calculations, so it is where well-organised students pick up marks that others lose. Multiple-choice questions can test definitions and distinctions quickly, and written questions often ask you to list steps, comment on data quality or justify a method for a given scenario. The same thinking also improves your answers in later chapters, because every model you fit rests on a clear aim and usable data. The Data analysis topic carries a 10% weighting in the 2026 CS1 syllabus, and the effort needed is small compared with the topics that follow.
Purpose and function of data analysis: topics in the order to study them
- 1Purpose and Aims of Data AnalysisStart here because every later idea, from steps to method choice, depends on knowing what the analysis is meant to achieve.
- 2Steps in the Data Analysis ProcessOnce you know the aim, learn the sequence of work that turns a question into a conclusion; it becomes the skeleton for written answers.
- 3Types of Data and SourcesNext you need the vocabulary to describe what you hold, because data type decides which summaries and models are allowed.
- 4Data Quality, Cleaning and Ethical ConsiderationsWith data types clear, study what can go wrong in them and how to treat it, including privacy and fair use.
- 5Descriptive, Inferential and Predictive AnalysisFinish with the three analysis types, because they tie the aim, the data and the method together and preview the rest of the paper.
How to prepare Purpose and function of data analysis
Plan for short, repeated sessions. This chapter suits phone study, because most of it is definitions, lists and short scenarios. The goal is to recall each idea in your own words and apply it to a situation.
- Read each topic once and write a one-sentence definition of every key term in your own words. Use plain language first, then tighten it.
- Memorise the process steps as a sequence you can reproduce from memory. For each step, add one example of what you would actually do in an insurance or pension setting.
- Build a small table in your notes of data types: primary or secondary, discrete or continuous, cross-sectional or longitudinal, and so on. Give one actuarial example for each.
- List common data quality problems, such as missing values, duplicates, outliers, inconsistent formats and bias. Next to each, write how you would detect it and how you would treat it.
- Take five short scenarios, for example a motor claims file or a pension scheme member list. For each one, state the aim, the data type, the likely quality issues and which analysis type applies.
- Practise multiple-choice questions on the distinctions, then write two or three full answers under time limits, checking that you stated assumptions and justified every choice.
- Revisit the chapter a few days later with a blank page and recall every list before checking your notes.
Common mistakes in Purpose and function of data analysis
Jumping straight to a method without stating the aim of the analysis.
Fix: Begin every written answer with one sentence on the objective, then link each later choice back to it.
Listing the process steps as a memorised list with no application to the scenario.
Fix: For each step, add a specific action tied to the data in the question, such as which fields to check or which source to use.
Confusing data types, such as treating a categorical code as numeric or calling a count continuous.
Fix: Ask what the values mean, not how they are stored. Check whether the values can be meaningfully averaged or ordered.
Treating outliers and missing values as errors to delete automatically.
Fix: Investigate first. An outlier may be a genuine large claim. Explain the treatment you choose and its likely effect on results.
Ignoring ethical and data protection points in scenario questions.
Fix: Whenever personal data appears, add a line on consent, confidentiality, security and avoiding unfair or biased use.
Mixing up inferential and predictive analysis.
Fix: Inferential analysis asks what is true about a population or relationship. Predictive analysis asks what outcome to expect for new cases. Decide which question is being asked.
Last-day revision: Purpose and function of data analysis
- Data analysis turns raw data into information that supports a stated decision or question.
- Always state the aim first; the aim drives the data needed and the method used.
- The process runs from defining the objective through collecting, cleaning, analysing and interpreting to communicating results.
- Primary data is collected by you for this purpose; secondary data already exists and was collected for another purpose.
- Discrete data takes countable values; continuous data can take any value in a range.
- Cross-sectional data is taken at one point in time; longitudinal data follows the same units over time.
- Check data for missing values, duplicates, outliers, errors and inconsistent definitions before analysing.
- Cleaning choices must be recorded and justified, and their effect on results should be considered.
- Data protection, confidentiality and fair use matter, especially with personal health or financial data.
- Descriptive analysis summarises the data you have; inferential analysis draws conclusions about a wider population; predictive analysis forecasts new or future outcomes.
- Always state your assumptions and the limits of the data in your conclusion.
Purpose and function of data analysis practice questions
- A motor insurer's claims file has 2,000 records. A check shows 120 records with a missing vehicle age, 40 exact duplicate records, and 60 re…
- Which of the following best describes the key distinction between inferential and descriptive analysis?
- A pension fund wants to estimate average retirement age among its 50,000 members. It lists members by employer: 40,000 work for large firms …
- A pension fund analyst reports that members who attended financial education sessions have higher savings than those who did not, and conclu…
- Which of the following best distinguishes inferential analysis from predictive analysis in an actuarial setting?
- In the data analysis process followed in actuarial work, which of the following best describes the purpose of the first stage, before any da…
- A pension fund analyst finds that, in a dataset of 2,000 members, the average salary rise is higher for members who attended a training prog…
- An actuary at a Chennai health insurer is reviewing a claims dataset. Which of the following best describes a reason to carry out explorator…
Purpose and function of data analysis in other exams
The same ground in other exams, if you are preparing for more than one or want another angle on it.
Purpose and function of data analysis: frequently asked questions
How much of CS1 comes from the data analysis chapter?
The 2026 CS1 syllabus gives Data analysis a 10% topic weighting. It is the smallest block in CS1 at 10%, but it is the easiest to prepare because it is mostly conceptual. It also supports your answers in every other topic.
Do I need to calculate anything in this chapter?
Very little. The focus is on definitions, process steps, data types, quality checks and choosing the right type of analysis. You may still be asked to apply these ideas to a scenario, so practise writing short, structured answers.
How should I write a written answer on the data analysis process?
State the objective, then walk through the steps in order and tie each one to the data in the question. Mention data quality and ethical points, and finish with your assumptions and limitations. Keep each point short and specific.
What is the difference between descriptive, inferential and predictive analysis?
Descriptive analysis summarises the data you already have. Inferential analysis uses a sample to draw conclusions about a wider population. Predictive analysis uses patterns in past data to forecast outcomes for new or future cases.