A. Introduction
Every day we are often faced with various symptoms that involve several variables or variables. For example, the growth of rice plants to a certain extent depends on the amount of fertilizer given, employee work motivation to a certain extent depends on the quantity, a baby’s weight to a certain extent is influenced by the amount of nutritional intake he gets from his parents.
From the example above, it can be seen that every day we often encounter these symptoms. In statistics, these symptoms can be explained by regression techniques. Regression and correlation are statistical analysis tools to determine the influence and strength between two variables. The word “regression” itself was first used as a statistical concept in 1877 by Sir Francis Galton. Galton has conducted research which shows that children’s height is affected by “move back or regress” which means the order is reversed, which means there is also an effect with their parents. He then designed that the word regression is a term that describes the general process of predicting one variable (child’s height) from another variable (parent’s height).
The variable that influences this in the regression is called the predictor variable, with the symbol X, while the variable that is affected is called the dependent variable, or the dependent variable, using the symbol Y. This regression is needed by scientists to find out the truth scientifically or based on knowledge, because one The function of science is to predict, to describe, to control and to explain.
In regression, certain requirements are needed. So that regression can be used, certain assumptions are needed. These assumptions are:
- The data used has a normal distribution
- Variable X is not random, while variable Y must be random
- The variables that are linked have as many subjects as the variables that are linked.
- The variables that are linked have an interval or ratio scale.
Regression is a statistical method used to measure the association or relationship between two or more quantitative variables, while to measure the association between two or more quantitative variables the X squared test is used.
B. Simple Linear Regression
In the form of a straight line that represents the relationship between two variables on the X and Y axes with the formula Y = bX + a seta slope = AC / BC.
Formulas:
Where: X = Variable X
Y = Variable Y
Σ = Sigma
n = Number of data pairs
a = Constant
b = Regression coefficient
Steps to answer simple regression questions:
Step 1. Make sure the assumptions and requirements are met
Step 2 Make Ha and H0 in sentences
Step 2. Create H1 and H0 in statistical form
H1 : r ≠ 0
H0 : r = 0
Step 3. Create a helper table to calculate statistical figures
Step 4. Enter the statistical figures from the helper table into the formula
Step 5. Plug the values of a and b into the equation
Step 6. Test significance and linearity using Anova or F Test.
Step 7. Determine the significance level
Its significance is 0.05
Step 8. H0 testing criteria
H0: significant
H1 : not significant
F count ≥ F table, then H0 is accepted
Step 9. Make Conclusions
Source :
RESEARCH STATISTICS: MANUAL ANALYSIS AND IBM SPSS
Authors : Agung Wahyudi Biantoro, Muh. Kholil