Simple Linear Regressions L6

Question 1

Which variable is the predictor, and which variable is the criterion?

Answer 1

X is the predictor and is the independent variable

Y is the criterion and the dependent variable

Question 2

What are the main assumptions of simple linear regressions?

Answer 2

• The relationship between X and Y should be linear
• Y should be measured on a interval or ratio scale, X can be measured on any scale
• for every value of X, the distribution of Y scores should approximately form a normal distribution and follow homoscedasticity assumption

Question 3

What is the equation for regression (what is the better variant?)

Answer 3

Y = a+bx + e

Where a is the intercept
B is the regression coefficient (slope)
E is error

Question 4

What is residual?

Answer 4

Residual or error, is the difference between the predicted and obtained Y for a given X.

Question 5

In regards to regressions, what do the null and alternative hypothesis cause b to equal?

Answer 5

In nul, b=0 where knowing X cannot help us significantly predict Y
In alternative b#0 so knowing X can help us significantly predict Y

Question 6

How in terms of regressions, is Tobt calculated?

Answer 6

B is divided by its standard error

b/SE of b

Question 7

Discuss significance testing in regards to regressions?

Answer 7

Tobt > tcrit means b is statistically significant (we reject our Ho)

Tobt < Tcrit means b is not statistically significant (we accept the Ho)

Question 8

What is the equation for degrees of freedom in regards to t-obtained and t-critical (simple linear regressions)

Answer 8

Df = n-2