Measures of Central Tendency
A summary measure, also known as a measure of central tendency, a measure of center, or a measure of central placement, aims to characterize the entirety of a collection of data with a single number that corresponds to the middle or center of its distribution. The article by Dubé (2019) uses a central tendency measure as one of the primary research methods. In this study, the author examines the VSTM task that the GCM’s random walk extension, EBRW, was expanded to account for Sternberg scanning; the study contains a brief overview that aims to explore the background and major findings demonstrating that prototypes have an obligatory impact on visual short-term memory responses (Dubé, 2019).
On some unpublished Sternberg scanning data, the author presents a novel model that integrates such “central tendency representations” in memory along with several other regularities from the literature. They then compare their predictions and post-predictions to those of the GCM. This study employs the mean as the measure of central tendency.
Types of Central Tendency Measures
The mode, the median, and the mean are the three primary indicators of central tendency. The typical or core value in the distribution is shown differently by each of these metrics (Australian Bureau of Statistics, n.d.). When values are listed in either ascending or descending order, the median is the value that is in the middle of the distribution.
Since it may be computed for both numerical and categorical non-numeric data, the model has an advantage over the median and mean. This measure is simply the number that appears most frequently in a dataset (Australian Bureau of Statistics, n.d.). Thus, each of the central tendency measures is appropriate in some cases.
Measures of Dispersion
Each score is condensed into a single number when data are represented by a measure of central tendency, mainly mean, median, or mode. A measure of dispersion is frequently included to support and amplify reports of central tendency (“Measures of dispersion,” n.d.). The differences between the measures of dispersion you have just examined will help you choose the one that will be most helpful in a certain circumstance.
In terms of range, it is the most straightforward to ascertain all the dispersion parameters. It is frequently employed as an early predictor of dispersion. However, it has limited use because it only considers scores that fall between the two extremes.
In contrast to the range, quartile scores are based on more data and are unaffected by outliers. They are not as simple to compute as the range, and they lack the mathematical characteristics that make standard deviation and variance so valuable. As a result, they are only sometimes employed to illustrate dispersion.
Both the variance, or s2, and the standard deviation, or s, are more comprehensive measurements of dispersion that account for all of the scores in a distribution (The Investopedia Team, 2022). The other dispersion measurements often discussed are based on significantly less data. However, a single outlier has a stronger influence on the amount of the variance than does a single score close to the mean, since variance depends on the squared differences of scores from the mean. When there is cause to question the validity of some of the extreme scores in the dataset, some statisticians see this trait as a weakness of variance as a measure of dispersion.
References
Australian Bureau of Statistics. (n.d.). Statistical language – measures of central tendency.
Dubé, C. (2019). Central tendency representation and exemplar matching in visual short-term memory. Memory & Cognition, 47, 589–602.
Measures of dispersion. (n.d.).
The Investopedia Team. (2022). Standard deviation vs. variance: What’s the difference?