**Why is Statistics Important**

Statistics is concerned with the collection, analysis, interpretation, and presentation of data. More data is being created and gathered now than ever before in human history as technology becomes more prevalent in our everyday lives.

Statistics helps us know what to do with data in predicting, decision-making, and understanding the world better. Below are several reasons why statistics has become so important in the modern world.

**Use of Descriptive vs. Inferential Statistics, Statistic vs. Parameter, Levels of Measurement: Nominal, Interval, ratio, and Ordinal, Population vs. Sample, and Qualitative vs. Quantitative Variables to understand the world.** All the parameters mentioned above are very useful in statistics to ensure that one can summarize charts, tables, and statistics hence giving someone an edge in understanding data. One can also get help in trying to seek out raw data and calculate frequency tables, histograms, and test scores of whatever the task may entail.

**Helps you to be wary of misleading charts**. Since more charts are being produced than ever before in journals, news channels, web pieces, and magazines. Unfortunately, if you don’t grasp the underlying facts, visualizations might be deceiving. An example is when you get a publication releases research that discovers a negative association between students’ performance and joining a good school.

Where a chart showing students with good grades yet cannot join a good college will be deemed misleading since there is a correlation between a student’s good score and being able to join a good college or university.

Such a scenario is often referred to as Berkson’s bias since the relationship between good grades and a good school should be positive. And knowing such concepts helps you escape being the victim of such misleading charts.

**Confounding variables is an important idea that you are bound to in statistics**. These are unaccounted-for factors that can skew experiment results and lead to untrustworthy conclusions.

Assume a researcher gathers data on ice cream sales and shark attacks and discovers that the two variables are substantially connected. Does this imply that increasing ice cream sales lead to an increase in shark attacks?

That is highly unlikely. The confounding variable temperature is the most likely cause. When the weather warms up, more people buy ice cream and swim in the water.

**Using probability in decision making**. Probability is one of the most significant sub fields in statistics. This is the study of how probable events are to occur. You can make better-informed judgments in the real world if you have a basic knowledge of probability.

Assume a high school student understands they have a 10% probability of being accepted to a specific university. Using the formula for the chance of success, this student may calculate the likelihood of being admitted to at least one of the institutions they apply to and alter the number of universities they apply to appropriately.

**Correlation.** Another fundamental term in statistics is a correlation, which describes the linear relationship between two variables. A correlation coefficient’s value is always between -1 and 1, where:

A value of -1 denotes a negative linear correlation between two variables.

0 means that there is no linear association between the two variables.

A correlation coefficient of 1 denotes a positive linear association between two variables.

You may grasp the link between variables in the actual world by studying these values. For example, if the correlation between television advertisement expenditure and income is 0.84, you may deduce that the two variables have a significant positive association. Spending more money on advertising will result in a predictable rise in income.

**Understand assumptions made using statistical tests**. Many statistical tests are based on assumptions about the underlying data. Many statistical tests involve assumptions about the data being studied.

When reviewing the results of research or conducting your own, it’s critical to understand what assumptions must be made for the results to be credible. To better understand the assumption statistical test, one can try checking Normality, equal variance, and independence in statistics.

**Understanding possible biases in studies**. Possible bias is another reason one ought to learn statistics to get familiar with the many sorts of prejudices that might arise in real-world investigations. Some of them include; non-response bias, omitted variable bias, observer bias, under-coverage bias, and self-made bias.

Over-generalization. The concept of generalization comes about when the research participants are not typical of the broader population, making it unsuitable to generalize the study’s findings to the greater population.

An example would be assuming we want to discover what proportion of tutors at a specific institution favor “online teaching” as a method of instructing pupils. If the whole tutor population is made up of 50% males and 50% women, a sample made up of 90% boys and 10% girls may produce biased findings if there are substantially fewer men tutoring students online.

In an ideal world, our sample would represent a “small” of our population. So, if the total tutor population is made up of 50% males and 50% women, our sample would be unrepresentative if it consisted of 90% men and 10% women.

As a result, whether you conduct your survey or read about the results of one, it is critical to understand if the sample data is representative of the overall population and whether the survey’s conclusions can be confidently extended to the population.

**Comprehend P-values in research. **Given that the null hypothesis is true, a p-value is a likelihood of witnessing a sample statistic that is at least as significant as your sample statistic.

An example would be, assuming a firm promises to make batteries weighing on average 100 pounds. An auditor suspects that the real mean weight of batteries produced at this facility is less than 100 pounds, so he conducts a hypothesis test and discovers that the p-value of the test is 0.03.

This p-value can be interpreted as follows:

If the plant does create batteries with a mean weight of 100 pounds, then the effect reported in the sample will be obtained by 3% of all audits, or larger, due to random sampling error. This indicates that acquiring the sample data obtained by the auditor would be extremely unlikely if the firm manufactured batteries with a mean weight of 100 pounds.

Hire one of our online teachers and benefit from their expertise and knowledge. Make yourself capable of solving statistical questions in Aleks by helping you grasp anything you need to know about statistics. You may also receive dependable Aleks statistic assessment solutions to aid you with your Aleks assessment session.