Basic concepts in descriptive statistics

As we have seen previously, statistics is the branch of mathematics that studies variability, as well as the process that generates it following probability laws and models. We know that and It is necessary both to do research and to understand how research is currently being done, beyond the conclusions of any study. But what basic concepts are included in statistics?

Thus, to focus on the basic concepts in statistics, we have to go to descriptive statistics. This deals with the description of experimental data, more specifically the collection, organization and analysis of data about some characteristic of certain individuals belonging to a population or universe. (1)

According to Professor Ignacio Cascos, from the Carlos III University of Madrid, these are some of the basic concepts in statistics that we need to know.

1. Population

The population is a well-defined set on which a certain characteristic is or can be observed.

This characteristic can be finite or infinite. Thus, the population size is the number of individuals it has, denoted by N. (1)

If the population is very large, it becomes very expensive and, in some cases, impossible to consider each individual and a selection is made called sample.

2. Individual

An individual is called each element of the population. These elements do not necessarily have to be people, although in psychology it is the most common.

3. Sample, size

A sample is a set of individuals in the population that reflects its characteristics as best as possible. If the characteristics are well reflected, the sample is said to be representative. The sample size is the number of individuals it has, we denote it by n.

If the sample and population coincide, it is said that a census is available.

4. Variable, data

A variable (X) is a symbol that represents a characteristic to study in the population. We call data (r) the value (numerical or not) that the variable takes on a specific individual in the sample.

Variable types

Something important to keep in mind in statistics is that there are various types of variables.

Qualitative variable

This type of variable It takes values ​​that correspond to non-quantifiable qualities of individuals. It cannot be said that one category is more than another.

An example of this type of variable is sex. They are called qualitative because the differences between their categories are qualitative.

Ordinal variable

These are variables that are prone to be divided into categories. Compared to a purely qualitative variable, in this type of variables we could order the categories.

Let’s think about school grades, for example. An outstanding is more than a grade and a grade is more than a pass.

Quantitative variable

The quantitative variable takes values ​​in a prefixed set of numerical values. This means that it can be measured, scaled. Within the quantitative variable we find two types:

Discreet. The set is finite or countable. For example, him number of children in a family.Keep going. The set is infinitely uncountable. This means that it contains some interval. An example could be time.

Position measurements

In statistics, we can determine the position of our data from position measurements. We present some of them:

Measures of central tendency

Averages or measures of central tendency are typical or representative values ​​of a data set. Thus, they aim to summarize all the data into a single value.

These are very basic concepts in statistics and there are three that are most used: the mode (qualitative variables), the median (categorical variables) and the mean (quantitative variables).

Fashion. Is he value with the highest frequency, the one that is repeated the most. If there is more than one of these values, the variable is called multimodal and can be calculated for any type of variable.Median. It is calculated for categorical variables. It’s about a number such that at least 50% of the data is less than or equal to the median and at least 50% is greater than or equal to. Thus, if there is more than one median, we take the midpoint between the largest and smallest median. These will be the data that appear in the sample and serve as medians. The mean: This is the most commonly used statistic. It is calculated for quantitative variables. It is, so to speak, the geometric center or gravity in the data. It’s curious, because a phenomenon happens with fashion. It may not represent the sample, but it may not actually represent anyone in this sample: no one may have that value in the variable.

There are many more concepts used in statistics, but these are perhaps the most basic. Thus, with the help of these concepts, descriptive statistics is responsible for purifying, organizing and calculating statistics and representations of data to offer the researcher, and by extension the scientific community, a complete map of what has happened in your studio.

You might be interested…