Zasobyaninaa guide to ratings, polls and statistics

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.

Reference

Reference

This section explains the terms that anyone who reads news, rankings and reviews will come across. The definitions are short and free of formulas wherever we can do without them. Specific numbers are given only from verified facts; everything else is described in general terms.

The word "study" in a headline can mean a careful random-sample survey or a dozen reviews. Knowing the terms helps you tell one from the other.

— Editor's note

Sampling and polls

Population
The whole group you want to draw conclusions about: for example, all adult residents of a country or all buyers of a particular product.
Sample
The part of the population that was actually surveyed or measured. How it was selected determines whether the results can be generalised to the whole group.
Margin of error
The range within which the true value lies with a given probability. For a simple random sample at a 95% confidence level and a proportion of around 50%, it is roughly ±0.98/√n: about ±4.9 points with 400 respondents, ±3.1 with 1,000 and ±2.2 with 2,000.
Representativeness
The extent to which a sample reflects the make-up of the population. A large but biased sample can give a worse result than a small but well-designed one — the classic example dates from 1936 and the Literary Digest magazine.
Methodology disclosure
The information a sound poll publishes: who commissioned and who conducted it, the dates, the survey method, the size and composition of the sample, the exact question wording and the margin of error. AAPOR (Transparency Initiative) and ESOMAR (International Code) set disclosure standards.

Descriptive statistics

Arithmetic mean
The sum of the values divided by their number. It is sensitive to extreme values: a single very large number noticeably shifts the mean.
Median
The value that splits an ordered series in half. Extreme values barely move it, which is why incomes and house prices are often reported as medians.
Percentage point
The difference between two values expressed as percentages. A rise in a share from 10% to 15% is 5 percentage points, but 50 percent relative growth.
Correlation
Two quantities changing together. Correlation does not imply causation: the quantities may move together because of a third factor or by chance.
Simpson's paradox
A situation in which a trend within each group disappears or reverses when the groups are combined. The classic example is the 1973 graduate admissions data from the University of California, Berkeley.

Charts and data presentation

Truncated axis
A vertical chart axis that does not start at zero. It is useful for showing small fluctuations, but it visually exaggerates differences if the reader does not notice it.
Absolute and relative values
An absolute value is a quantity in units, money or people; a relative value is a share or a change in percent. Relative growth from a small base looks impressive even if it is small in absolute terms.
Time series
Values of an indicator over consecutive periods. The start and end points can greatly change the impression of a trend, so look at the whole period available.
Official statistics
Data published by authorised statistical agencies. In Russia this is Rosstat, the Federal State Statistics Service. Because of the pandemic, the 2020 All-Russian Population Census was held from 15 October to 14 November 2021.

Materials on the topics in this section

  • Practical articles

    How to check a number from the news or an advert, step by step, plus a catalogue of upcoming articles.

  • Questions and answers

    Short answers about polls, ratings, reviews and basic statistical concepts.

  • Reading lists

    Reading paths: getting started, before you buy, numbers in the news.

  • Guide sections

    A map of the guide: polls, ratings and reviews, averages and charts, official data.

Sources

  • Rosstat (Federal State Statistics Service)
  • AAPOR — Transparency Initiative
  • ESOMAR — International Code
  • Textbooks on statistics and survey methodology
  • Encyclopaedic sources

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.