Science

What is statistics? »Its definition and meaning

Table of contents:

Anonim

Statistics, comes from the Latin statisticum collegium (council of state) and its Italian derivative statista (statesman or politician). The German term Statistik, introduced by Gottfried Achenwall (1749), originally designated the analysis of state data, that is, "the science of the state." It was not until the nineteenth century when the term statistics came to designate the collection and classification of data. It is a set of techniques to observe, measure and interpret collective phenomena that occur in human societies, through methods based on the use of large numbers.

What is statistics

Table of Contents

The concept of statistics relates its applications to the analysis of different parameters or data obtained from representative tests, so that all types of changes, dependencies and correlations that a specific physical phenomenon or a natural phenomenon whose occurrences are conditional or conditional can be explained. random. The definitions and concepts that emphasize what is statistics lead to the same conclusion: statistics are present in many types of sciences, especially factual ones because they obtain very new knowledge through observation and expectation. Statistics are used even in government institutions.

In current times, what is statistics and its relationship with factual sciences opens an important door to calculate the exact number of a given population. How is this accomplished? Using various methods to collect as much information as possible, analyze community data and, finally, interpret the results obtained through the mechanisms previously used.

The definition of statistics is closely related to quantitative studies, in fact, it is taken into account because statistics are considered as a completely special science in this branch to calculate collective phenomena. The origin of this science is even more complex, but it has an excellent explanation.

The concept of statistics is based on the fact that this is one of the branches of mathematics whose purpose is to study variability and the process that is generated in it, of course, keeping track of the laws or principles of probability. Because it is a mathematical statistic, the method with which it is studied is totally formal and considered in isolation as a science proper.

The definition of statistics shows it as a deductive element of science, totally dynamic, with continuous developments and own knowledge. In this post, everything related to statistics will be fully explained.

Origin of statistics

In itself, this science began as a marked need of the State to maintain a specific data of its population, this they did through progressive censuses and data collection that later submitted to determined statistical data. The statistical parameter obtained was the total number of inhabitants of a country. Taking this into account, with the passage of time the statistics were used in different areas of studies and known sciences, for example, mathematical statistics, in the graphs of different calculations known as statistical graphs, etc. Although that can be seen later in the types of statistics.

History of statistics

This science has been present in the life of man for many years, in fact, there are documented graphs around the year 3000 BC The history of statistics is really linked with the Babylonians and the first men to live on earth because in the stones and wood found by excavators and researchers were found accounts and calculations of their own population. Over the years, more civilizations joined the use of statistics, among them, the Egyptian, who made use of them even before raising the famous pyramids of Egypt.

During the Middle Ages and ancient times, this science was gaining more force, using statistical graphics not only to know the specific numbers of the population, but to take it in its favor and apply the tax rules more effectively. They were also feasible to calculate the number of subjects that were needed in the ranks of their armies and in the distribution of land in a given territory. Some of the civilizations that used the statistics are as follows.

  • Egypt: during Dynasty I, the pharaohs began to make use of statistics to collect data effectively on their population, so that they could determine how many individuals or slaves they would use to raise the pyramids of Egypt, count the treasures and riches that they possessed and maintain control of the entire territory.
  • Rome: its use began in the Roman Empire, when the rulers of ancient Rome decided that they should keep track of births, deaths, wealth, land and everything that had to do with money at the tax level within their territory. Its implementation marked a before and after in the Roman era and little by little it was used out of habit until today.
  • Greece: they began to be used to establish democracy, that is, the imminent right to vote, but they were also used to implement military service and how many people were needed for these new merits. As with the rest of the civilizations, the rulers of ancient Greece maintained control of their population with the censuses for the distribution of land and wealth.
  • China: it happened in the era of Emperor Yao, approximately in the year 2238 BC to carry an exact calculation of agriculture, commerce and industrial activities in ancient China. In this way, the ruler maintained an order in business.
  • Middle East: The Sumerians kept the inhabitants of what was known as ancient Babylon accounted for, in fact, the total number was 6000 people. Ancient tablets were also found in which the data of the legal procedures of the city, its businesses and wealth were kept.
  • Jewish people: not only was this science used to obtain military data, but also to establish the exact amounts of those who entered the temples.
  • Mexico: in the year 1116, the old King Xólotl gave the order that all his subjects be counted due to the migration that the Chichimeca tribes were carrying out.
  • Spain: from the year 1528, censuses began to be carried out in different places in this country, all with different objectives but yielding favorable results for the rulers of that time.
  • England: the counting of births and deaths had a total increase due to the great plague that devastated that territory during the 1500s. As they obtained results, they began to make different statistical graphs to control the deaths caused by the disease.

Statistical classification

It has already become clear that this science is isolated, that it does not belong to the rest of the exact sciences because it only yields probabilities, it is reflected in numerical characters that are not exact, not at least for a long time, since different causes can arise that generate slight or drastic changes, for example, the accounting of a population, which may be altered according to the number of births and deaths that are registered monthly or annually in a given territory. However, the classification of statistics is divided into two aspects that will be explained below.

Descriptive statistics

It is about the evaluation of a certain phenomenon or problem by observing it, then it is presented through graphs and statistical data that not only manage to find the details of the phenomenon, but also monitor its behavior. For this aspect to proceed, a series of steps must be carried out, first the statistical data is collected through previously observed samples, then all those samples obtained are analyzed to categorize them, this last process is nothing more than the grouping of the statistical parameter or the different data obtained during the investigation.

Inferential statistics

Regarding this aspect, it is a specific study of the behavior carried out by the population that is being subjected to the census.

With the study, certain samples are located that serve as tests that allow determining the reason for that behavior or phenomenon that has developed in that community, population or territory. For this aspect of the classification of statistics to be logical and to proceed, it is really imperative to know what a population is and to know how to differentiate it from a sample. The hypothesis is one of the fundamental pillars of this aspect, creating a referential means of the results obtained.

To clear up the doubts that generally appear after the mention of inferential statistics, population is a concept that refers to a set of people whose universal characteristic is grouping. The sample, on the contrary, is the collection made from the same population and that will later be subjected to different studies to finally begin a categorization.

Thanks to both, inferential statistics manages to develop a series of hypotheses and theories applicable in the conjugation of the circumstances and the alternatives that can be used in it. With all this clear, it goes without saying that the conclusions are imminent for this aspect.

Statistical methods

At this point it tends to be quite general, since the statistical method is nothing more than the study of the data obtained, so that they are verified and evaluated to know if they will be accepted or later discarded.

To arrive at the statistical method, one needs to make use of induction, deduction and hypothesis. There are 3 aspects that are triggered by these methods and that have weight in different areas of science, among them, their application in the different existing scientific branches, the types of statistical graphics and the statistical control of processes.

Application of statistics in different branches

Also known as applied statistics and its main objective is, through inferential statistics, to know the behavior of a certain community, concluding with a statistical sampling of different parameters. This can be applied in branches outside the statistics itself, for example, psychology, biology, history, medicine… Even in football statistics.

Statistical sampling is taken into account because of the assumptions that arise from it, here also applies the statistical mode, median statistics and what is known as a variable statistical Why? because statistical packages are used in educational programs.

Statistical chart types

The best way to capture the results and data obtained from different studies is by means of graphs, although it is clear that each one has its differences and specific uses, for example, bar graphs are used to capture percentages or specify the information provided by a determined population.

The sectorial graphs are used solely and exclusively to express population percentages, either of schools or of large territories. The pictograms are illustrations, ie drawings. They are generally used in topics related to fashion. The histograms represent a statistical variable through proportional bars to values.

Finally, the frequency polygon is based on linear graphs that represent the sudden changes that have been generated in a certain population due to the incidents produced in a specific period of time. This graph is born from the points that join in the bases that are in the upper levels of the bars of a diagram. This type of calculation can also be used in histograms, however, this is the best way to carry an accounting at the graphical level.

What is statistical process control

It is about the correct use of graphs for differences in the data obtained in the different investigations and studies carried out on a certain population. The statistical control of processes is in charge of differentiating the variations of the important phenomena investigated, collecting the parameters, samples and measurements of the entire process, making it clear that the power of this control is based on the ability to get to monitor the center of phenomena. It is related to statistical quality control because many techniques and methods are used to achieve optimal results.

Among these methods are experimental studies and the observation of each of them. These work thanks to the investigation of the causality of each investigation and of the conclusions that are obtained by means of independent values ​​and variables of the statistical studies of the population that is being intervened. In both experimental and observational studies, infinite monitoring is carried out on all the variables that the community phenomena present. These methods are effective and imperative in the analysis of the information that is being carefully managed.

On the other hand, there are the measurement levels. There are 4 types of these levels and each one with different degrees of application in statistics. The level of measurement of the ratio is more flexible and is used to carry out different analyzes of the collected parameters.

Interval measurements have distances that are subject to interpretation between one measurement and another, but in the end, they have a meaningless zero value, such as in IQ calculations. The ordinal measurements contain marked and imprecise differences between the values ​​classified as consecutive, however, the order obtained is interpretable.

Finally, there is the nominal measurement and it is considered the lowest level scale because it is based on categorizing or grouping the elements according to their classes. If you pay attention to this, it becomes clear that ordinal measurement orders numbers and intervals has the unit of constant and common measurements. They are all different even when they belong to the same level categorization. Now, the zero factor on the equal interval scale is totally arbitrary and does not affect or reflect any absence in the quantities being measured.

These scales, in addition to containing general characteristics of ordinal measurements, manage to determine the density, magnitude and extent of the distance between each element of the levels. The ratio measurement is considered as the highest level of all measurements because it has a zero factor of its own origin, which is why it differs from the intervals, because its zero factor defines the absence of the magnitude being evaluated. If a total lack of ownership is observed throughout the investigation, then the unit of measure is used to achieve the desired effect.

If there are identical variables in the numbers that have been assigned, then identical variables correspond in the degrees of the attributes that are present in the object of the investigation. To all this are added the statistical analysis techniques, which are essential tests and procedures in the investigations of this science, it is the analysis of accumulated frequency, regression, variance, confirmatory and exploratory factor analysis, correlation, which is classified in Spearman's correlation analysis and Pearson's correlation analysis. Added to this are other important studies.

These are the statistical frequencies, statistical graphs, iconography of the statistical relationships studied and subsequently used, the chi-squared tests, Fisher's least significant difference test, Student's t test and the Mann-Whitney U test. Each of these tests and analyzes are used in statistical methods to obtain favorable and comparative results, so that they can be used in the different existing populations. Thanks to all of them, you can have a fairly clear idea of ​​what this science is, how it works, the correct way to approach it and, most importantly, how to use it on a daily basis.

What is the statistical population

As mentioned before, the statistical population is a group of people, elements and even objects that are grouped according to a series of special characteristics. Their grouping significantly differentiates them from the rest of the world's populations or communities.

It is possible to determine a statistic in them thanks to different censuses and, generally, some samples are taken to carry out investigations according to their behavior or phenomena. The statistical variance is proportional to the graphs captured in each investigation. In schools, activities are carried out to calculate the population of a specific site, for which they use the 911 statistics format.

When the samples are subjected to a rigorous and exhaustive analysis, the results are applied to the rest of the community to begin to make the statistical hypothesis and reaction theories, this is called statistical inference.

The statistical range calculated, like the statistical frequency, is nothing more than the estimate of the data of a community previously selected, studied and finally census. This population has a series of important elements that cannot be ignored either in this science or in any of its isolated branches. These elements will be fully explained in the next section.

Elements of the statistical population

Within the statistics are the parameters or data, the population that will be the object of study and the samples, which are taken to begin with the investigations, comparisons and application of results. Now, when it comes to population, there are a series of elements that cannot be ignored. Why? because without them there would not be a community or a specific group of people or objects for research or census. In statistics, an element is not only a person, it is a something whose existence is real, be it a property, an object, money, jewelry, even time or temperature.

Taking this into account, the following important point can be passed: Its characteristics. Yes, each element has a different characteristic and this is because, being a varied element and not only conforming to humanity but also to objects and movable and immovable property, it is necessary to collect a series of characteristics that allow its correct grouping. For example, in the case of people, the characteristics to collect are age, weight, sex, height, body tone, hair color, eye color, educational level, profession, culture, and even religion.

Each of these aspects helps to categorize each element and allows us to proceed to the next point: qualities and number of elements.

For example, a finite population, which is identified by containing a number of determined elements (Students of a mathematics class or people interned in a medical institution) Now, there is the infinite population, which is characterized by having a number of uncertain elements, a clear example of this are the products that may become in the online or physical market. There are so many of these basic or common products that they are literally said to be infinite.

It is important to highlight the fact that in statistical studies, one rarely works with the total elements of a population precisely because of the previous point (finite or infinite), so here the sample takes a lot of prominence, which is considered as a subset of the statistical population. The sample is taken from the elements that share extremely similar characteristics and, after that, they are compared with other elements that have absolutely nothing in common. The modality of these elements, subjects or objects are subject to evaluation throughout the research process.