What

is Inferential Statistics?

Inferential

statistics is the branch which deals with predictions and making conclusions

about a study. In other words, we use inferential statistics when examination of each member of an entire population is not

convenient or possible. For example, instead of measuring the diameter of every

nail manufactured in a factory, we use a random nail sample. By using its

information we make generalization about the diameters of all nails in the

factory. In this case the nails are called a population. Simply population is

any group of data. The method which is used in inferential statistics is called

sampling. We can relate to another example concerning students, for instance we

can’t get all the results of students living in USA but in fact we can use

inferential statistics to obtain information rather than gathering all their

results.

What are the main types?

And now after we discussed the definition of inferential stat.

we can move on the main types. According to the type of research, we use a

corresponding statistical method. But before we decide we must examine the data

first. If the data is normally distributed then we will go with parametric

tests while if it is not normally distributed then we will choose the non

parametric tests. Below, there are some

of inferential main types and their uses.

Type

of test

Uses

Correlation

Searches for relationship between variables

Pearson correlation

Important for the strength of the relationship between two

continuous variables

Spearman correlation

Important for the strength of the link between two ordinal

variables

Chi-square

Tests for the strength of the connection between two

categorical variables

Paired T-test

Important for the difference between two connected variables

Independent T-test

Important for the difference between two independent variables

ANOVA

Used for the difference between group means after any

other variance in the outcome variable is accounted for

Simple regression

Important for how change in the predictor variable predicts

the level of change in the outcome variable

Multiple regression

Vital for how change in the combination of two or more

predictor variables predict the level of change in the outcome variable