Statistics

Question 1

What is statistical power?

Answer 1

• Statistical power - Statistical power is the probability of a hypothesis test of finding an effect if there is an effect to be found.
• Power is the probability that we will correctly reject the null hypothesis (relates to type 2 error)
• High power (large sample size) - High probability of correctly rejecting the null hypothesis. Two distributions overlap a little
• Low power (small sample size) - Low probability of correctly rejecting the null hypothesis. Two distributions overlap a lot

Question 2

What does R^2 show?

Answer 2

The 𝑅^2 is used to describe the strength of the correlation between the response and explanatory variables (Agresti, 2019, p. 651). Specifically, the adjusted 𝑅^2 is used in order to control against the increase of adding one more explanatory variable to the regression model. 𝑅^2 is always between 0 and 1 but the closer it is to 1, the better the explanatory variables are at predicting the response variable

Question 3

What does beta coefficient show?

Answer 3

The beta refers to the slope of each explanatory variable while controlling for the other variables. A positive beta would, therefore, indicate a positive relationship to the response variable and a negative beta would indicate a negative relationship to the response variable

Question 4

What does a multiple regression show?

Answer 4

Multiple regression analysis is used in order to find out how the mean of the response variable, intention to use, relates to the four explanatory variables, PVO, while holding all other variables constant.

Question 5

What is type 1 and 2 error?

Answer 5

a type I error is the rejection of a true null hypothesis (also known as a “false positive” finding or conclusion, while a type II error is the non-rejection of a false null hypothesis (also known as a “false negative”)