Shorter Answers (25 MARKS TOTAL in this section): Q1. Briefly explain which is more important: Internal or External validity. (2 marks) Q2. Identify the 7 steps in NHST. (2 marks) Q3. What information does a correlation coefficient provide with respect to the nature of the relationship between two variables? (2 marks) Q4. Identify the components of the GLM as discussed in class and briefly explain (using words) the inter- relationships among them. (2 marks) Q5. What is our primary purpose when conducting data analysis? (1.5 marks) Q6. How do we accomplish our primary purpose? (1.5 marks) Q7. What do we conclude if our computed t-value is greater than the critical t-value? (2 marks) Q8. Identify the four basic assumptions that underlie all parametric statistical analyses. (1 mark) 29. Briefly explain the methods we have discussed to assess the four assumptions identified in Q8. (2 marks Q10. Briefly distinguish between SS and SP. (2 marks) Q11. Briefly explain the Central Limit Theorem and why it is important to our work in data analysis. (3 marks) Q12. Briefly distinguish between VARIABILITY and VARIANCE. (2 marks) Q13. Briefly explain the concept of statistical power, and briefly explain the factors that influence it and how they influence it (increasing or decreasing power). (2 marks)PSY 2106 - Fall 2021 - Take-home Midterm Longer Computation Questions (50 MARKS TOTAL in this section): Q14. For the data in DATA SET A, compute the following sums - show your work (7 marks TOTAL): a) EX + 3 (1 mark) b ) E ( X + 2 ) (1 mark) 1=1 c) Ex (1 mark) d) E( x + 1) (1 mark) 1=3 e) Ex - Ex (1 mark) 1) (Ex? ) - 7 (1 mark) 8 ) E(1) (1 mark) DATA SET A X1 7 X6 8 X2 9 X7 7 X3 8 X8 10 X4 7 15 X5 7 X10 12 Q15. Using DATA SET B, compute the following (6 marks TOTAL): a) SS (1 mark) b) Median (1 mark) c) Mode (1 mark) d) Mean (1 mark) e) Standard Deviation (1 marks) f) Variance (1 mark) DATA SET B A W L U W W N - - N auVia Awa - N WQ16. Using DATA SET C, determine the following: (7 marks TOTAL): a) The z-score for a raw score of 29. (1 mark) b) The percentile rank for a raw score of 90. (2 marks) C) The stanine for a raw score of 56. (1 mark) d) The z-score for a percentile rank of 50%. (2 marks) e) The closest raw score for a z-score of -0.79. (1 mark) DATA SET C 32 19 45 83 29 56 12 13 11 39 7 85 98 18 5 90 53 25 9 82 20 47 80 49 34 4 65 2 5 47 16 82 43 27 64 34 50 53 79 Q17. Using DATA SET D, compute the following: (8 marks TOTAL) a) Covariance of J and K. (4 marks) b) Correlation between K and L. (4 marks) DATA SET D K 10 7 7 12 10 13 10 9 10 11 9 13 9 11 10 11 8 Q18. Use the NHST method when answering this question. You have discovered what appears to be a new form of inch-worm. The observed mean length for the group of 392 specimens collected is 3.25cm, with a standard deviation of 0.8. If the population mean length for inch-worms is 2.54cm, does your data support the claim that you have discovered a new species? (9 marks) Q19. Use the same information provided in Q18 (above). Would your answer change (and how) if we know that the population standard deviation for inch-worms is 0.76? (4 marks)Q20. We want to identify PSY students who will do well in Graduate School based on their marks in PSY 2106, which happen to be normally distributed. Students with scores in the top 2% of the distribution are deemed most likely to succeed. If we have scores for 3,500 students in PSY2106, the average mark is 70, and the standard deviation is 9.5, what is the cut-off score to identify students most likely to succeed? Show your work. (9 marks) BONUS Worth up to 3 marks. Answer the following questions using the correlation table presented as DATA SET E. (3 BONUS marks) a) Are there any unexpected values in the table? If so, identify it/them. (1 mark) b) Is there anything else that doesn't make sense? (2 marks) DATA SET E Variable J Variable K Variable M Variable J 1.00 0.89 0.92 Variable K 1.00 0.25 Variable M 0.98 End of Midterm - Enjoy the Study Break