Analysis, Reporting & Visualization

ANOVA (Analysis of Variance)

ANOVA (Analysis of Variance) is a statistical method for testing whether the average (mean) of a numeric variable differs across three or more groups. It tells you if group differences are unlikely to be due to random chance.

Box Plot

A box plot (box-and-whisker plot) is a compact chart that shows the distribution of a numerical dataset using five summary values: minimum, first quartile, median, third quartile and maximum, with outliers highlighted. It’s used to compare spread and central tendency across groups at a glance.

Chi-Square Test

A chi-square test is a simple statistical test that checks whether two categorical variables are related (for example, language group and answer choice). It tells you if differences you see in a contingency table are likely to be real or due to random chance.

Chord Diagram

A chord diagram is a circular visualization that shows relationships and flows between categories using arcs (around the circle) and ribbons (connecting them). It highlights which groups are linked and the strength of those links at a glance.

Choropleth Map

A choropleth map is a geographic map that uses colour shading to show how a numeric value (like rates, percentages or averages) varies across predefined areas such as neighbourhoods, districts or counties. It’s commonly used to visualise patterns across regions at a glance.

Cluster Analysis

Cluster Analysis

Cluster analysis groups survey respondents (or responses) into sets that are more similar to each other than to other sets, revealing patterns and segments in your data. It's an exploratory tool used to discover meaningful groups without pre‑defined labels.

Composite Score

A composite score combines several related survey items into a single number that summarizes a concept (for example, overall satisfaction or accessibility). It makes complex answers easier to report, compare and track over time.

Confidence Interval

A confidence interval is a range of values, calculated from survey data, that likely contains the true value for the population measure you care about (for example, the true percentage who support a policy). It expresses the uncertainty around a point estimate using a chosen confidence level (commonly 95%).

Correlation Analysis

Correlation analysis measures how two survey variables move together — for example, whether people who rate service highly also report higher trust. It quantifies the strength and direction of a relationship but does not prove one thing causes the other.

Cronbach's Alpha

Cronbach's alpha is a statistic that measures the internal consistency of a group of survey items — in other words, how well they hang together as a single scale. It's used to decide whether it's reasonable to combine several questions into one summary score.

Cross-Tabulation

Cross-tabulation (or cross-tab) is a way to compare survey responses across two or more variables, showing counts and percentages in a simple table. It helps you see how answers differ by groups such as language, age, location or any other category.

Dashboard Design Principles

Dashboard design principles are a set of guidelines for organising data, visuals and interactions so a dashboard communicates the right story quickly and accurately. Good design makes insights obvious, reduces misinterpretation and supports fast, confident decisions.

Factor Analysis

Factor analysis is a statistical method that groups related survey questions into a smaller number of underlying dimensions (factors) that represent the ideas respondents are really answering about. It helps turn many correlated items into a few interpretable themes.

Heat Map

A heat map is a visual chart that uses colour to show where values are concentrated — higher intensity colours mark areas with more responses, higher scores or more activity. In survey work it makes patterns across locations, questions or respondent groups easy to see at a glance.

Item Response Theory (IRT)

Item Response Theory (IRT) is a family of statistical models that describe how a person’s answer to a survey or test question relates to an underlying trait (like ability, opinion strength or need). IRT models each question by parameters such as difficulty and discrimination to produce fairer scoring and better question diagnostics.

Logistic Regression

Logistic regression is a statistical method that models the probability of a binary outcome (yes/no) from one or more predictor variables. It outputs a probability (0–1) and is commonly used to predict categories like respond/didn't respond or agree/disagree.

Margin of Error

The margin of error is a range around a survey estimate that expresses the uncertainty from sampling — for example, saying 60% ±5% means the true population value is likely within that interval. It depends mainly on sample size, the estimate's variability, and the chosen confidence level.

Net Promoter Score (NPS)

Net Promoter Score (NPS) is a simple metric that measures how likely people are to recommend your organisation, product or service. It summarises customer loyalty on a scale from -100 to +100.

Nonresponse Bias

Nonresponse bias occurs when the people who do not answer a survey differ in important ways from those who do, causing results that are systematically skewed. It can make survey findings misleading even when many people responded.

Open-Ended Coding

Open-ended coding is the process of turning free-text survey answers into labeled categories (codes) so you can analyse and report on themes. It’s how qualitative responses become quantifiable insight.

Post-Stratification

Post-stratification is a weighting technique applied after data collection to make a survey sample better match known characteristics of the target population (for example age, gender, region or language). It adjusts each response so summary results reflect the population proportions.

Rasch Analysis

Rasch Analysis

Rasch analysis is a psychometric method that turns survey item responses into a consistent measurement scale, letting you compare people and questions on the same metric. It helps check whether a questionnaire measures one thing reliably and whether items behave the same way for different groups (for example, language groups).

Regression Analysis

Regression analysis is a set of statistical methods used to quantify the relationship between one outcome (dependent) variable and one or more predictor (independent) variables. It helps you estimate how changes in predictors—like language, age or survey length—are associated with changes in an outcome, such as satisfaction or response rate.

Response Rate

Response rate measures the share of people who complete (or submit) a survey out of everyone invited or reached. It shows how many people engaged with your questionnaire and is used to judge reach and representativeness.

Sample Weighting

Sample weighting adjusts survey results so the responding group better matches the population you care about. It gives more or less influence to individual responses to correct for known differences between your sample and the target population.

Sankey Diagram

A Sankey diagram is a flow chart where the width of each arrow or band represents the size of a flow between nodes. It visually shows how quantities move between states, categories or stages.

Scale Reliability

Scale reliability describes how consistently a multi-item survey scale measures a single concept — that is, whether the items hang together to give a dependable score. High reliability means the composite score is stable and interpretable; low reliability means the scale is noisy and may mislead decisions.

Segmentation Analysis

Segmentation Analysis

Segmentation analysis is the practice of dividing survey responses into meaningful subgroups (segments) — for example by language, age, location or response pattern — and comparing results across those groups. It reveals differences in needs, experiences or opinions within a larger population.

Sentiment Analysis

Sentiment analysis is an automated way to detect whether written responses feel positive, negative or neutral. It helps teams quickly see how people feel about a service, question or topic across many open-text answers.

Small Multiples

Small multiples are a set of small, consistently-styled charts arranged in a grid, each showing the same type of data for a different subgroup or time period. They make it easy to compare patterns across segments at a glance.

Statistical Significance

Statistical significance is a way to judge whether an observed difference or relationship in data is likely to be real rather than a result of random chance. It uses probability thresholds to help decide whether to trust an apparent pattern in survey results.

Text Analytics

Text analytics is the set of techniques that turns open‑text answers into measurable insights — e.g., themes, sentiment and keywords — so teams can understand what people actually say at scale. It combines language processing, pattern detection and simple statistics to summarize free‑text responses.

Thematic Analysis

Thematic analysis is a flexible method for identifying, analysing and reporting common patterns (themes) across qualitative data such as open-text survey answers. It turns many individual responses into a small set of meaningful insights you can act on.

Time Series Analysis

Time series analysis examines data points collected in chronological order to reveal trends, patterns, seasonality and sudden changes over time. It helps you understand how survey metrics — like response rates, sentiment or participation by language — evolve.

Top-Box Scoring

Top-box scoring reports the share of respondents who choose the highest (most positive) response option on a rating question. It’s a simple, easy-to-understand measure of strong positive sentiment.

Topic Modeling

Topic modeling is an automated way to find common themes in large sets of text by grouping similar responses into topics. It helps surface what people are talking about without reading every answer.

Treemap

A treemap is a compact, visual way to show hierarchical or part‑to‑whole data using nested rectangles whose sizes represent numeric values and whose colors can encode categories or metrics. It's useful for seeing which parts of a dataset are biggest or smallest at a glance.

Trend Analysis

Trend analysis is the process of tracking changes in survey or feedback data over time to identify patterns, improvements or emerging problems. It shows whether key measures (like satisfaction, response rates or sentiment) are rising, falling or staying stable.

Violin Plot

A violin plot visualises the distribution of a numeric variable across one or more groups by combining a box plot with a mirrored density curve. It shows where values cluster and how spread-out or multi-peaked a set of responses is.

Word Cloud

A word cloud is a visual summary of text data where words appear larger when they occur more often. It gives a quick, informal view of the main topics or keywords in open‑text responses.