Linear Regression Analysis Unit 8 Assignment 1 PSL8106 Capella University 3/5/2017 LaTisha Horton 1. To what extent do gender, exam anxiety, and time spent revising predict exam performance for students? R2 gives the extent of prediction. It indicates extent to which the dependent variable is predictable. From the model summary table, R2= 0.209. It implies that gender, exam anxiety, and time spent revising can predict 20.9% of the variance in exam performance for students. 2. Analyze and explain the significant findings and directional relationships (positive versus negative coefficients). Looking at the p-value of the t test for each predictor, we can see that Time spent Revising (p = .180) and Gender (p = .823) do not contribute to the model. They are not statistically significant since their p-values are greater than 0.05. Exam anxiety significantly predicts Exam performance (p = .014). It contributes to the model. The coefficients of the Gender and Exam anxiety are negative. This shows that they negatively affect the exam performance. Time Spent Revising had a positive coefficient, implying that the more time is spent revising, the higher the exam performance, after controlling for the other variables in the model. From the Anova table, we can see that the overall regression model is significant, F(3,99) = 8.721, p = .00. There is linear relationship between the variables in the model. 3. Analyze the hypotheses based on the findings. The null hypothesis states that all the coefficients are equal to zero while the alternative states that at least one is not zero. From the Anova table, F(3,99) = 8.721, p = .00, the model is significant. There is a linear relationship between the variables in the model. The null hypothesis is rejected. 4. How are these findings similar to or different from the simple independent samples nonparametric t-test analysis from Unit 7? The test that the distribution of Exam performance (%) is the same across Gender by the Independent samples Mann-Whitney U test led to failing to reject the null hypothesis. This indicated that exam performance and Gender are independent. These findings are similar to the ones gotten from the regression analysis. Gender did not significantly predict exam performance, p = 0.823. a. What do the findings suggest about the data and the research questions? The findings suggest that exam anxiety significantly affect exam performance. Its coefficient is - 0.481. This implies that for every unit increase in the exam anxiety level, exam performance drops by 0.481. The overall model was significant. The multiple correlation coefficient, R = 0.457. This measure the quality of the prediction of the dependent variables. This is not a fairly good prediction. Linear Regression Modeling Using SPSS Linear Regression Modeling Using SPSS 1. Write at least three sentences that answer your predictive research question, based on your data analysis. 2. Discuss and analyze significant findings and directional relationships (positive versus negative coefficients). 3. a. How are these findings similar to or different from the linear regression analysis from Unit 8? b. What do the findings suggest about the data and the research questions? Exam Anxiety in Students (Exam Anxiety.sav dataset): To what extent do gender, exam anxiety, and time spent revising predict exam performance for students? Linear Regression Modeling Using SPSS