Part II. After collecting the data for part I, the researcher then wonders if it's possible to predict missing SF-36 scores from each participant's reported number of hours (on average) sleep per night over the past 30 days. To answer the question, the researcher decides to conduct a bivariate regression. Using the same Excel and JASP datasets provided from part I, complete each of the following questions and run the appropriate commands for each procedure. (See Regression G*Power, Excel and JASP Videos in Blackboard)

1. What is the research question? Why is a bivariate regression appropriate to answer the research question?

Can the missing SF-36 scores be predicted based on the students reported average amount if sleep. Bivariate regression is appropriate as we ae looking for a linear relationship between two variables.

1. Provide a statistical, symbolic, and substantive hypothesis for the research study.

no significant linear relationship will be found to exist between a of hours spent asleep and SF 36 scores.

a significant linear relationship will be found to exist between a of hours spent asleep and SF 36 scores.

? Ho: r= 0

? H1: r

\fcritical F = 4.02302 0.5 0.4 0.2 Test family.r Statistical test Ftests v Linear multiple regression: Fixed model, Ra deviation from zero Type of power analysis A priori: Compute required sample size given or, power, and effect size Input Parameters Determine =:> Effect size f3 or err prob Power [18 err prob) Number of predictors Output Parameters 0.]5 Noncentralitg.r parameter A 0.05 Critical F 0.8 Numerator df I Denominator df Total sample size Actual power 8.2500000 4.0230l?0 l 53 55 0.8050826