I saw a number in the news
A step-by-step article on checking a percentage, a ranking or a "study" from the news or an advert.
An independent guide to ratings, polls and statistics. Not affiliated with the former website on this domain, with politicians, parties or government authorities; this is not campaign material.
a guide to ratings, polls and statistics
Numbers are everywhere: in school and city rankings, in marketplace reviews, in news stories about poll results, in adverts full of percentages and stars. Many of them are honest, but almost any number can be presented so that it looks more convincing than it really is. This site collects calm, practical explanations: how polls work and where the margin of error comes from, how the mean differs from the median, why a chart can mislead, why correlation does not mean causation, and where to find official data. No rankings of our own, no advertising and no assessments of specific people or organisations.
A number on its own proves nothing. It becomes useful once you know who produced it, how, and what exactly it measures.
A step-by-step article on checking a percentage, a ranking or a "study" from the news or an advert.
A reading list on how to read ratings and reviews before you buy, and what not to rely on.
Short answers about sampling, margin of error and why 1,000 people can speak for millions.
A glossary: sample, margin of error, median, correlation, Simpson's paradox and other concepts.
A map of the guide: polls, ratings and reviews, averages and charts, official data.
How to check a number from the news or an advert, step by step, plus a catalogue of upcoming articles.
Short answers about polls, ratings, reviews and basic statistical concepts.
Reading paths: getting started, before you buy, numbers in the news.
A glossary: sampling and polls, descriptive statistics, charts and data.
A dated feed of the guide's publications.
All materials by date and topic, plus a note on the domain's former addresses.
The author, the commissioning party and the data source are the first things to look for. A ranking compiled by a seller of its own products reads differently from an independent comparison.
"Best" is not a metric. Look at the criteria used to score the entries and how those criteria were weighted.
A survey, customer reviews, official statistics or expert opinion — every source has its own weak spots.
If places in a ranking are separated by fractions of a point, the order may be down to chance. A small difference does not always mean real superiority.
If another independent source paints a similar picture, you can trust the ranking more. If the picture is completely different, look for how the methods differ.
No. Zasobyanina is an independent guide. We explain how to read other people's rankings and polls, but we do not carry out our own research, rate products or services, or publish unverifiable reviews.
Sample size is not the main thing. With a simple random sample of 1,000 people, the margin of error is about ±3.1 percentage points. What matters more is how participants were selected and how the questions were worded.
The arithmetic mean is pulled strongly by extreme values, such as a few very high incomes. The median is insensitive to them and better shows what a "typical" person earns.
No. The current guide is not connected to the former website, does not reproduce its materials and does not cover political topics.
Zasobyanina is an independent reference project. The domain was apparently once used for a political project; the current guide is not connected to it, does not reproduce its materials and does not cover political topics. The site is not campaign material and does not pose as the former project or as any government authority.
We write about things that are useful to anyone who comes across numbers in everyday life: how to read rankings of products, services, schools and cities, how to understand the results of opinion polls and their margin of error, how the mean differs from the median, how to spot a misleading chart and where to find official data. The numerical illustrations on the site are hypothetical examples, not the results of real studies.
Information is current as of the preparation date. Research methods, official statistics releases and the standards of professional associations change over time, so always check the latest data in the original sources.