Author
Su He
Data Analyst
Author · 17 articles · 18 glossary terms
Explores traffic sources, conversion funnels, and retention, using clear metric definitions and concrete examples to explain what the numbers mean.
Articles by Su He
17 articles
Analytics · Nov 6, 2026 · 6 min read
User status segmentation: new, returning, resurrected and dormant users
User status segmentation classifies users as new, returning, resurrected, at risk or dormant each period. Definitions, the growth accounting identity, actions per status and a weekly example.
Read more
Analytics · Nov 5, 2026 · 6 min read
Pareto analysis: how to find the 20% that drives 80% of results
Pareto analysis finds the few causes behind most of an effect. The 8 steps, a support-ticket example where 4 of 10 reasons caused 80% of tickets, a traffic concentration example, analytics use cases and the mistakes that make the 80/20 rule misleading.
Read more
Analytics · Nov 5, 2026 · 7 min read
Regression analysis for marketers and analysts: a worked example
Regression analysis estimates how an outcome changes with its drivers. A 12-week example shows how leaving out organic traffic inflated the value of ad spend by a third, plus how to read output, check assumptions and avoid common mistakes.
Read more
Analytics · Nov 5, 2026 · 6 min read
Time series analysis for web analytics: trend, seasonality and anomalies
Time series analysis separates trend, seasonality and noise so you can tell a real change from a Monday. A 4-week worked example, the core techniques, forecasting baselines and the mistakes that mislead dashboards.
Read more
Analytics · Nov 4, 2026 · 4 min read
Outliers in Data: How to Find Them and What to Do With Them
An outlier is a value far from the rest of the data. How to find outliers with the IQR rule, z-scores and percentiles, a worked example with 12 orders, and how to decide whether an outlier is an error to remove or a real value to report.
Read more
Analytics · Nov 4, 2026 · 5 min read
Mean vs Median: Which Average to Use for Your Metrics
The mean adds everything up and divides; the median is the middle value. A worked example where one large order doubles average order value, when to use each, and which analytics metrics should be read as medians.
Read more
Analytics · Nov 4, 2026 · 4 min read
How to Check Website Traffic: Your Own Site and Anyone Else's
How to check traffic on your own website with analytics, which five numbers to read first, how estimates for other sites work and how far to trust them, and why tools never agree.
Read more
Analytics · Nov 4, 2026 · 4 min read
What Is a Good Bounce Rate? Judge It by Page Type, Not One Number
There is no single good bounce rate. What bounce rate measures, why a site-wide average misleads, a sample by page type, when a high rate is a real problem, and how to set your own target.
Read more
Analytics · Nov 4, 2026 · 5 min read
Monthly Unique Visitors: How They Are Counted, and Which Number to Quote
Monthly unique visitors are the distinct people (in practice, browsers or devices) who visited at least once in a month. Why summing days overstates it, how the counting method changes it, and how to report it.
Read more
Analytics · Nov 3, 2026 · 5 min read
Micro Conversions: How to Pick the Ones That Actually Predict Sales
Micro conversions are small actions on the way to a purchase or lead. They help only if they predict the main conversion. How to pick candidates, test each one against your sales data, track the keepers as goals, and avoid reporting them as success.
Read more
Analytics · Nov 3, 2026 · 6 min read
Bounce Rate vs Exit Rate: Different Denominators, Different Questions
Bounce rate divides single-page sessions by sessions that started on a page; exit rate divides exits by every view of that page. A worked table, which pages each one fits, and the mistakes to avoid.
Read more
Analytics · Nov 3, 2026 · 6 min read
Website Visitor Tracking: Four Layers and What Each Can See
Website visitor tracking in four layers: aggregate counts, sessions and paths, identified users after login, and company identification. What each layer sees, what it needs, and where privacy changes what you should collect.
Read more
Analytics · Nov 3, 2026 · 6 min read
How to Calculate CTR: One Formula, Four Different Denominators
How to calculate click-through rate for ads, search results, emails and on-site buttons, with worked examples, the denominator each one uses, CTR vs conversion rate, and what inflates the number.
Read more
Analytics · Nov 3, 2026 · 6 min read
Actionable Metrics: A Test, Rewrites and Decision Rules
How to tell an actionable metric from a vanity metric with five questions, rewrites of common vanity metrics, and the decision-rule format that turns a dashboard number into an action.
Read more
Analytics · Nov 3, 2026 · 7 min read
New vs Returning Users: What the Split Means and Why It Lies
How analytics tools decide whether a visitor is new or returning, why the two groups never add up to the total, what makes returning people look new, and how to use the split.
Read more
Analytics · Nov 3, 2026 · 8 min read
Analytics Metrics: 12 Website Metrics, Formulas and Traps
The 12 website analytics metrics worth reporting, grouped into traffic, engagement, conversion and quality, each with its formula, what it tells you and the trap that makes it misleading.
Read more
Analytics · Feb 12, 2026 · 10 min read
Why analytics tools show different numbers: 8 causes and a reconciliation checklist
Two analytics tools on one site never print the same visitor count. Here are the eight causes, a worked example of where the gap goes, and a checklist to reconcile them.
Read more
Glossary terms by Su He
18 glossary terms
Glossary
Anscombe's quartet: same statistics, different data
Anscombe's quartet is a set of four data sets, published by Francis Anscombe in 1973, that share nearly identical means, variances, correlation and linear regression line but have very different distributions, demonstrating the importance of plotting data.
Learn more
Glossary
Entry page / exit page
The first and last page of a visit.
Learn more
Glossary
Exponential growth: formula, examples and how to measure it
Exponential growth is growth by a constant percentage per period, so the absolute increase gets larger each period.
Learn more
Glossary
False discovery rate
The false discovery rate (FDR) is the expected proportion of false positives among all results declared significant.
Learn more
Glossary
Interquartile range (IQR): how to find it, with an example
The interquartile range (IQR) is the difference between the third quartile (75th percentile) and the first quartile (25th percentile) of a data set.
Learn more
Glossary
Metrics
A metric is a quantitative measure of something over a defined period, such as visitors, sign-ups, conversion rate or average order value.
Learn more
Glossary
Month over month (MoM) growth
Month over month (MoM) growth is the percentage change in a metric from one calendar month to the previous one: this month minus last month, divided by last month.
Learn more
Glossary
Multi-armed bandit
A multi-armed bandit is a testing approach in which traffic is allocated adaptively: options that perform better receive more traffic as results come in, balancing exploration (learning which option is best) against exploitation (using the best option found so far).
Learn more
Glossary
Pages per session
Pages per session is the average number of pageviews in a session, calculated as total pageviews divided by total sessions for the same period and filters.
Learn more
Glossary
Pageview
One load of one page by one browser.
Learn more
Glossary
Retention curve
A retention curve is a chart of the percentage of a user cohort still active after each day, week or month since they started; a curve that flattens shows a stable base of users who keep getting value.
Learn more
Glossary
Sampling bias: types, examples and how to spot it in analytics
Sampling bias is a systematic error that occurs when the method of collecting a sample makes some members of the population more likely to be included than others, so the sample does not represent the population and estimates are skewed regardless of sample size.
Learn more
Glossary
Seasonality
Seasonality is a regular, predictable pattern in time-series data that repeats over a fixed calendar period, such as the hour of the day, the day of the week or the month of the year.
Learn more
Glossary
Selection bias
Selection bias is a distortion that happens when the people or events included in an analysis differ systematically from the population you want to draw conclusions about, because of how they were chosen or chose themselves.
Learn more
Glossary
Session
A group of pageviews and events from one visitor with no gap longer than 30 minutes.
Learn more
Glossary
Session timeout: how analytics splits visits into sessions
In web analytics, a session timeout is the period of inactivity after which the current session ends and further activity starts a new one, commonly 30 minutes.
Learn more
Glossary
Simpson's paradox
Simpson's paradox is a situation in which a relationship that holds in each of several groups disappears or reverses when the groups are combined, because the groups differ in size and in a third factor that affects the outcome.
Learn more
Glossary
Year over year (YoY)
Year over year (YoY) is a comparison of a metric in one period with the same period one year earlier, usually expressed as a percentage change, which removes most of the effect of seasonal patterns.
Learn more