Final Exam Study Guide(1)

PY 211: Final Exam Study Guide Important information  The final exam is worth 100 points.  Final exam scores will not be dropped, replaced, or otherwise altered. The final exam scores will not be used to replace any of the semester exam scores.  The exam will be held in our classroom on Thursday, 12/14 at 8:00am.  The exam is cumulative. ______________________________________________________________________________ Formulas and tables will be provided. NOTE: The purpose of this study guide is to help you focus on the material I expect you to know for the final exam. The point values listed below are only estimates. I have not provided specific questions that will appear on the exam. I recommend studying related homework items and items we discussed during class. Chapters 1-4 (15% of final)  Be able to create a frequency table (6 points)  Identify a histogram based on a frequency table (1 point)  Identify left-skewed, right-skewed, and normal distributions (3 points)  Use the 50% - 34% - 14% rule (3 points)  Conceptually, what does it mean to get a p < .05 while hypothesis testing? (2 points) Chapters 5-8 (25% of final)  What is the difference between a population mean and a distribution of means? (2 points)  When is it reasonable to assume that a distribution of means will follow a normal curve? (2 points)  Be able to identify type I and type II errors (4 points)  Be able to identify when to use a one sample t test, dependent samples t test, and independent samples t test (5 points)  Be able to identify the purpose of using a Levene’s test (2 points)  Be able to conduct an independent samples t test (10 points) Example: A communication researcher randomly assigned 77 volunteers to one of two experimental groups. Fifty were instructed to get their news for a month only from television, and 27 were instructed to get their news for a month only from the Internet. After the month was up, all participants were tested on their knowledge of several political issues. The researcher did not have a prediction as to which news source would make people more knowledgeable. That is, the researcher simply predicted that there is some kind of difference. Results of the study: TV group: M = 23, S 2 = 5; Internet group: M = 25, S 2 = 3. Using the .05

level, what should the researcher conclude? Let Population 1 be people who get their news only from television and let Population 2 be people who get their news only from the Internet. Notes: - TV: N 1 = 50; M 1 = 23, S 2 1 = 5 - Internet: N 2 = 27; M 2 = 25, S 2 2 = 3 State the hypotheses: - NH: The null hypothesis is that the mean test score of people in Population 1 is equal to that of people in Population 2. - RH: The research hypothesis is that the mean test score of people in Population 1 is different from that of people in Population 2. Find the cutoff score(s): - Significance level is .05 - Test is two-tailed - df 1 = N 1 - 1 = 50 – 1 = 49 - df 2 = N 2 – 1 = 27 – 1 = 26 - df total = 49 + 26 = 75 - cutoff scores are -1.99; 1.99 Determine the sample’s score: - S 2 pooled = df 1 / df total (S 2 1 ) + df 2 / df total (S 2 2 ) = (49/75)(5) + (26/75)(3) = 4.31 - S 2 M1 = S 2 pooled /N 1 = 4.31/50 = .086 - S 2 M2 = S 2 pooled /N 2 = 4.31/27 = .160 - S 2 Difference = S 2 M1 + S 2 M2 = .086 + .160 = .246 - S Difference = √ S Difference 2 = √ .246 = .496 - t = (M 1 – M 2 )/S Difference = (23 – 25)/.496 = -4.03 Should we reject the null? - Compare our t score, -4.03, to the cutoff scores (-1.99; 1.99)

 Understand the limitations of a correlation (e.g., correlation does not equal causation) (2 points)  Be able to identify predictor and criterion variables (2 points)  Be able to determine the linear prediction rule (4 points)  Understand what the symbols represent for ^ Y = a + b (X) (2 points)  Be able to calculate the regression coefficient and the regression constant (4 points):  Use answers to generate the linear prediction rule (2 points)  Determine the standardized regression coefficient (2 points):  Be able to select graphs with the appropriate regression lines (2 points)  If given an SPSS output for correlation and or regression, be able to determine whether to reject the null hypothesis (3 points)