Author
Emma Collins
Product Analyst
Author · 26 articles · 35 glossary terms
Focuses on event analysis, conversion funnels, and retention, using clear metric definitions and structured analysis to explain product performance.
Articles by Emma Collins
26 articles
Analytics · Nov 7, 2026 · 8 min read
Multi-touch attribution: models compared on one customer journey
Multi-touch attribution shares the credit for a conversion across the touchpoints that led to it. Every common model applied to the same journey with numbers, how channel rankings change between models, what MTA cannot measure, and how to set it up.
Read more
Analytics · Nov 7, 2026 · 9 min read
Product feature analysis: a matrix for keep, improve or retire
Compare feature reach, repeat use, quality and dependencies. Includes a product feature analysis matrix and safeguards against unsupported causal claims.
Read more
Analytics · Nov 7, 2026 · 9 min read
Product adoption dashboard: a template with exact denominators
Build a product adoption dashboard with eligible users, first value, repeat use and cohort windows. Includes a reproducible sample and decision template.
Read more
Analytics · Nov 6, 2026 · 6 min read
Web analytics report: what to include, types and an example
How to write a web analytics report that leads to action: report types by audience, what to include, six steps and a one-page monthly example.
Read more
Product News · Nov 6, 2026 · 6 min read
App retention rate: how to calculate it, read the curve and improve it
App retention rate is the share of new users who come back after N days. The formula, why classic, range and unbounded retention give different numbers, what a healthy curve looks like, and a worked onboarding change measured by cohort.
Read more
Product News · Nov 6, 2026 · 6 min read
What does a product engineer do? Role, skills and a feature end to end
A product engineer owns product outcomes, not just code. How the role differs from software engineers and product managers, daily responsibilities, skills, and a worked feature from support tickets to full rollout.
Read more
Product News · Nov 5, 2026 · 6 min read
Chi-square test explained with conversion and experiment examples
The chi-square test checks whether category counts differ from chance. Two worked examples, conversion by device and a sample ratio mismatch check, with every expected count, degrees of freedom, effect size and the mistakes to avoid.
Read more
Product News · Nov 4, 2026 · 4 min read
What Does a Product Analyst Do? Tasks, Skills and a Real Example
A product analyst turns product usage data into decisions: defining metrics, setting up tracking, answering questions about features and users, and checking whether changes worked. Five recurring jobs, a typical week, a worked analysis and how the role compares with related jobs.
Read more
Product News · Nov 4, 2026 · 5 min read
Bayesian vs Frequentist: The Same A/B Test, Analysed Both Ways
Frequentist and Bayesian statistics answer different questions about the same data. A plain explanation of both, one A/B test analysed each way (p = 0.097 vs a 95% chance B is better), and when to use which.
Read more
Product News · Nov 4, 2026 · 4 min read
How to Calculate a Confidence Interval (With Conversion Rate Examples)
A confidence interval gives the range a true value probably sits in. The formulas for a mean, a rate and a difference between two rates, worked examples with conversion data, and what to do with small samples.
Read more
Analytics · Nov 4, 2026 · 4 min read
Standard Deviation vs Standard Error: The Difference, With Examples
Standard deviation describes how spread out your data is; standard error describes how precise your average is. The formulas, a worked example at three sample sizes, the conversion-rate version and the mistakes to avoid.
Read more
Product News · Nov 4, 2026 · 4 min read
User Segmentation Examples: 12 Segments You Can Build From Event Data
Twelve user segmentation examples a product or growth team can build from event data, each with the rule and what to do with it. Plus a sample comparing two segments and how to keep segments useful.
Read more
Product News · Nov 4, 2026 · 5 min read
How to Do Cohort Analysis: Six Steps and How to Read the Table
A step-by-step guide to cohort analysis: choose the start and return events, the period and the counting mode, then read the table by rows, columns and diagonals. With a sample weekly cohort table.
Read more
Product News · Nov 4, 2026 · 4 min read
Metric Tree: How to Build One and Use It to Explain Changes
A metric tree breaks one top metric into the drivers that produce it. How to build one in five steps, a sample tree with numbers, how to use it to explain a drop, and how to keep it in your analytics.
Read more
Growth & Marketing · Nov 4, 2026 · 4 min read
Customer Churn Analysis: A Five-Step Method With an Example
Customer churn analysis finds who leaves, when, and after what. A five-step method you can run with ordinary event data, the behaviour signals to compare, and a sample that leads to a concrete fix.
Read more
Product News · Nov 4, 2026 · 4 min read
Customer Journey Analytics: From Journey Map to Measured Paths
Customer journey analytics measures how people actually move from first visit to purchase and beyond. The four analyses it is built from, which question each answers, and a sample from trial to paid.
Read more
Product News · Nov 4, 2026 · 7 min read
How to Calculate Statistical Significance for an A/B Test
Statistical significance tells you whether a difference between two conversion rates is bigger than chance would usually produce. The five steps of a two-proportion test, a worked example by hand and in code, and how to size the test before you start.
Read more
Product News · Nov 4, 2026 · 6 min read
Type 1 vs Type 2 Error: What They Mean for Your A/B Tests
A type 1 error is a false positive: you call a winner that is not real. A type 2 error is a false negative: you miss an effect that is real. A worked set of 100 A/B tests shows how many winners are wrong, and why low power makes it worse.
Read more
Product News · Nov 4, 2026 · 7 min read
Correlation vs Causation: How to Tell Them Apart in Your Analytics
Correlation means two numbers move together; causation means one makes the other happen. A worked analytics example where a "video triples conversions" claim mostly comes from traffic source, four checks to run on any correlation, and how to test for cause.
Read more
Product News · Nov 3, 2026 · 5 min read
Behavioral Analytics: Five Questions, Five Analyses, and How to Start
Behavioral analytics looks at what people do on your site or product, in what order and how often, rather than how many arrived. Five questions it answers, the analysis for each, what you need tracked, and a one-week plan to start.
Read more
Live Chat · Nov 3, 2026 · 6 min read
Does Live Chat Increase Conversions? How to Measure It Honestly
Visitors who chat usually convert several times more often, but much of that is who chooses to chat. How to measure live chat's real effect on your site, from a same-day comparison to a time-split test of proactive invites.
Read more
Analytics · Nov 3, 2026 · 6 min read
Customer Segmentation Analysis: Five Steps from Question to Action
Customer segmentation analysis in five steps: start from a decision, choose variables you can observe, compare segments on the same KPI, check size and stability, then act and measure again.
Read more
Growth & Marketing · Nov 3, 2026 · 6 min read
Product Health Metrics: A Weekly Scorecard That Includes Quality
Product health metrics in five areas (growth, engagement, retention, quality, satisfaction) on one weekly scorecard, with thresholds that turn a number amber or red and a routine for reviewing it.
Read more
Growth & Marketing · Nov 3, 2026 · 6 min read
Churn Rate vs Retention Rate: When They Add Up and When They Do Not
Churn and retention look like two sides of one number, but they only add up to 100% in one case. Worked scenarios for customers, revenue and user cohorts, plus net revenue retention and annual churn.
Read more
Growth & Marketing · Nov 3, 2026 · 6 min read
Retention Metrics: Which Rate to Use and How to Calculate It
The retention metrics that actually differ, how to calculate retention rate with a worked example, the counting choices that change the number, and which metric fits which business.
Read more
Analytics · Jan 20, 2026 · 9 min read
Conversion funnel optimization: find the step that matters and fix it
A five-step method for conversion funnel optimization: measure the funnel correctly, find the step that matters, size the gain, diagnose why people leave, then fix and verify.
Read more
Glossary terms by Emma Collins
35 glossary terms
Glossary
ARPU
Revenue over a period divided by the number of active users in that period.
Learn more
Glossary
Average order value
Revenue divided by number of orders over a period.
Learn more
Glossary
Base rate fallacy: definition, examples and how to avoid it
The base rate fallacy is the error of judging the probability of an event from specific evidence while ignoring how common the event is overall (its base rate).
Learn more
Glossary
Behavioral cohort
A behavioral cohort is a group of users defined by an action they did or did not take within a time window, used to compare retention or conversion and find behaviors linked to long-term success.
Learn more
Glossary
Bonferroni correction
The Bonferroni correction is a method for multiple comparisons: when you run m tests, you call a result significant only if its p-value is below α divided by m, which keeps the chance of any false positive across all tests at or below α.
Learn more
Glossary
Bounce rate
The share of visits that end after a single page with no further interaction.
Learn more
Glossary
Central limit theorem: definition, formula and a worked example
The central limit theorem states that the means of sufficiently large independent random samples are approximately normally distributed around the population mean, with standard deviation σ/√n, regardless of the shape of the original data, provided its variance is finite.
Learn more
Glossary
Churn
The share of users or customers who stop coming back, or cancel, in a period.
Learn more
Glossary
Clickstream data
Clickstream data is the time-ordered sequence of page views, clicks and other events that a visitor generates while using a website or app, usually stored as one row per event with a timestamp, a session or user ID and properties.
Learn more
Glossary
Cohort
A group of users defined by when they did something — signed up in March, first bought in week 12.
Learn more
Glossary
Confounding variable
A confounding variable is a third factor that influences both the thing you think is the cause and the outcome you measure, creating a link between them that is partly or wholly not causal.
Learn more
Glossary
CUPED
CUPED (Controlled-experiment Using Pre-Experiment Data) is a variance-reduction technique for A/B tests that adjusts each user’s outcome using a correlated measurement from before the experiment, which makes the treatment effect easier to detect without biasing it.
Learn more
Glossary
DAU / WAU / MAU
Daily, weekly and monthly active users — the number of distinct people who did a qualifying action in that window.
Learn more
Glossary
Diagnostic analytics
Diagnostic analytics is the type of analysis that explains why something happened, by breaking a change in a metric down by segments, time and related events to find the factors that caused it.
Learn more
Glossary
Effect size: what it is, formulas and why p-values are not enough
Effect size quantifies how large a difference or relationship is, independent of sample size.
Learn more
Glossary
Event analytics
Event analytics is analysis built on events: records of individual actions, each with a name, a timestamp, the person or device that did it and properties that describe it.
Learn more
Glossary
Experimenter bias: definition, examples and how to avoid it
Experimenter bias (observer-expectancy effect) is a distortion of research results caused by the researcher’s expectations influencing how an experiment is designed, conducted, measured or interpreted, often unconsciously.
Learn more
Glossary
First response time
How long a visitor waits between starting a chat and receiving the first reply from a person.
Learn more
Glossary
Funnel
An ordered set of steps — view product, add to cart, start checkout, pay — with the number of people who reached each one.
Learn more
Glossary
Guardrail metrics: what they are, examples and how to choose
Guardrail metrics are measures a team commits to protect while it optimises a primary metric.
Learn more
Glossary
Inferential statistics: definition, examples and common tests
Inferential statistics use data from a sample to draw conclusions about a larger population or process, quantifying uncertainty with tools such as confidence intervals, hypothesis tests and p-values.
Learn more
Glossary
LTV
The revenue a customer brings over their whole relationship with you.
Learn more
Glossary
Margin of error: formula, examples and how to calculate it
The margin of error is the range above and below a sample estimate within which the true value is expected to fall at a given confidence level.
Learn more
Glossary
Minimum detectable effect (MDE): what it is and how to calculate it
The minimum detectable effect (MDE) is the smallest true difference between variants that an experiment is designed to detect at a chosen significance level and power.
Learn more
Glossary
P-hacking: what it is, examples and how to avoid it
P-hacking is the practice of running many analyses, such as peeking, adding metrics or segments, changing windows or excluding data, and reporting only those that reach statistical significance, which inflates the false positive rate far above the nominal level.
Learn more
Glossary
P-value
A p-value is the probability of getting a result at least as extreme as the one you observed, assuming there is really no difference or effect (the null hypothesis).
Learn more
Glossary
Path analysis
The sequences of pages or events people actually follow, drawn as a flow from a starting point.
Learn more
Glossary
Power user
In product analytics, a power user is someone who uses a product much more often or more deeply than typical users, for example active on most days of the month or using the core feature many times a week.
Learn more
Glossary
Qualitative data
Qualitative data is non-numerical information that describes qualities, opinions, reasons and experiences, recorded as words, images, audio or categories.
Learn more
Glossary
Regression to the mean
Regression to the mean is the statistical tendency for a measurement that is unusually high or low, partly because of chance, to be followed by a measurement closer to the average, even when nothing has changed.
Learn more
Glossary
Retention / day-1 retention
The share of a cohort that comes back after a given time.
Learn more
Glossary
Segment
A saved group of users or visits defined by properties and behaviour — paid visitors from Germany who added to cart twice.
Learn more
Glossary
Statistical power
Statistical power is the probability that a test will find a statistically significant result when a real effect of a specified size exists; it equals 1 minus the probability of a type II error (a false negative).
Learn more
Glossary
T-test
A t-test is a statistical test that compares a mean, or the difference between two means, with the spread of the data to judge whether the difference is likely to be more than random noise.
Learn more
Glossary
Web analytics
Web analytics is the collection, measurement and analysis of data about how people find and use a website (visits, sources, pages, clicks and conversions) in order to understand and improve the site.
Learn more