Sten Scores and Their Use in Rescaling Test Scores

An illustration of people composing a bell curve, or the normal distribution of data.

Many times in order to make easy comparisons between individuals, test scores are rescaled. One such rescaling is to a ten point system. The result is called sten scores. The word sten is formed by abbreviating the name "standard ten."

Details of Sten Scores

A sten scoring system uses a ten point scale with a normal distribution. This standardized scoring system has a midpoint of 5.5. The sten scoring system is normally distributed and then divided into ten parts by letting 0.5 standard deviations correspond to each point of the scale. Our sten scores are bounded by the following numbers:

-2, -1.5, -1, -0.5, 0, 0.5, 1, 1.5, 2.0

Each of these numbers can be thought of as z-scores in the standard normal distribution. The remaining tails of the distribution correspond to the first and tenth sten scores. So less than -2 corresponds to a score of 1, and greater than 2 corresponds to a score of ten.

The following list relates sten scores, standard normal score (or z-score), and the corresponding percent of ranking:

Sten scores of 1 have z-scores less than -2 and consist of the first 2.3% of ranked scores.
Sten scores of 2 have z-scores greater than -2 and less than -1.5 and consist of the next 4.4% of ranked scores.
Sten scores of 3 have z-scores greater than -1.5 and less than -1 and consist of the next 9.2% of ranked scores.
Sten scores of 4 have z-scores greater than -1 and less than -0.5 and consist of the next 15% of ranked scores.
Sten scores of 5 have z-scores greater than -0.5 and less than 0 and consist of the middle 19.2% of ranked scores.
Sten scores of 6 have z-scores greater than 0 and less than 0.5 and consist of the next 19.2% of ranked scores.
Sten scores of 7 have z-scores greater than 0.5 and less than 1 and consist of the next 15% of ranked scores.
Sten scores of 8 have z-scores greater than 1 and less than 1.5 and consist of the next 9.2% of ranked scores.
Sten scores of 9 have z-scores greater than 1.5 and less than 2 and consist of the next 4.4% of ranked scores.
Sten scores of 10 have z-scores greater than 2 and consist of the last 2.3% of ranked scores.

Uses of Sten Scores

The sten scoring system is used in some psychometric settings. The use of only ten scores minimizes small differences between various raw scores. For example, everyone with a raw score in the first 2.3% of all scores would be converted into a sten score of 1. This would make the differences among these individuals indistinguishable on the sten score scale.

Generalization of Sten Scores

There is no reason that we must always use a ten point scale. There may be situations in which we would want to have use of more or fewer divisions in our scale. For example, we could:

use a five-point scale, and refer to stafive scores.
use a six-point scale, and refer to stasix scores.
use a nine-point scale, and refer to stanine scores.

Since nine and five are odd, there is a midpoint score in each of these systems, unlike the sten scoring system.

Cite this Article Your Citation

Taylor, Courtney. "Sten Scores and Their Use in Rescaling Test Scores." ThoughtCo, Jun. 25, 2024, thoughtco.com/what-are-sten-scores-3126178. Taylor, Courtney. (2024, June 25). Sten Scores and Their Use in Rescaling Test Scores. Retrieved from https://www.thoughtco.com/what-are-sten-scores-3126178 Taylor, Courtney. "Sten Scores and Their Use in Rescaling Test Scores." ThoughtCo. https://www.thoughtco.com/what-are-sten-scores-3126178 (accessed September 9, 2024).

copy citation Stanine Score Example Example of Bootstrapping How Are the Statistics of Political Polls Interpreted? An Introduction to Queuing Theory Millions, Billions, and Trillions Leap Day Statistics What Is Bootstrapping in Statistics? Statistics Related to Father's Day What Is a Double Blind Experiment? The Probability of Being Dealt a Royal Flush in Poker What Is the St. Petersburg Paradox? Groundhog Day Statistics Analysis of Variance (ANOVA): Definition and Examples Example of Two Sample T Test and Confidence Interval Definition of a Percentile in Statistics and How to Calculate It How to Make a Stem and Leaf Plot

About Us
Advertise
Careers
Privacy Policy
Editorial Guidelines
Contact
Terms of Service
EU Privacy

ThoughtCo is part of the Dotdash Meredith publishing family.

We Care About Your Privacy

We and our 100 partners store and/or access information on a device, such as unique IDs in cookies to process personal data. You may accept or manage your choices by clicking below, including your right to object where legitimate interest is used, or at any time in the privacy policy page. These choices will be signaled to our partners and will not affect browsing data.

We and our partners process data to provide:

Store and/or access information on a device. Use limited data to select advertising. Create profiles for personalised advertising. Use profiles to select personalised advertising. Create profiles to personalise content. Use profiles to select personalised content. Measure advertising performance. Measure content performance. Understand audiences through statistics or combinations of data from different sources. Develop and improve services. Use limited data to select content. List of Partners (vendors)