|
Homework: Understanding Your Stats Name: ___________________________ Title of Research Paper: ____________________________________________________ ___________________________________________________________________________________ Instructions: If you did comparisons of 2 or more groups, you need to do the following for EACH comparison. 1. Briefly describe the variables involved. For example: "We compared males and females on their levels of self-esteem". Or, "we compared the experimental group (those who filled out the questionnaire on yellow paper) to the control group (those who filled out the questionnaire on white paper) on their self-esteem scores. 2. Provide the means (X), Standard deviations (SD), and number of subjects (N) for each group. 3. Provide the t-value, df, and p-value for the comparison. Report as t(df) = 2.34, p = .04 (If you predicted ahead of time what you expected to find, use the p-value from a "one-tailed" test. If not, use the p-value from a "two-tailed" test.) 4. Interpret the results. For example: "The comparison was statistically significant. Males had significantly higher self-esteem scores than females". Or, "The comparison was not statistically significant. There was no significant difference in self-esteem scores based on whether subjects took the questionnaire on yellow or white paper". Instructions: If you correlated two variables, you need to do the following for EACH correlation. 1. Briefly describe the variables involved. For example: "We correlated self-esteem scores and GPA's of freshmen girls". 2. Provide the means (X) and standard deviations (SD) for both variables. Also indicate how many subjects were involved in the correlation (N). 3. Provide the correlation coefficient (r) and p-value for each correlation. Report as r = .64, p = .02. (If you predicted ahead of time what you expected to find, use the p-value from a "one-tailed" test. If not, use the p-value from a "two-tailed" test.) 4. Interpret the results. For example: "There was a moderate positive correlation between freshman GPA and self-esteem. This correlation was statistically significant. Higher levels of self-esteem were associated with higher GPA's in freshman girls". Or, "The correlation was not statistically significant. There seemed to be very little relationship between GPA and self-esteem in freshman girls". Instructions: If you are comparing percentages of two or more groups, you need to do the following for EACH correlation. 1. Briefly describe the variables involved. For example: "We compared the percentage of males who preferred Pepsi to the percentage of females who preferred Pepsi over Coca Cola". 2. Provide the percentages (%) for all variables and the ratios involved. For example: "Of the 45 male subjects, 26 (57.78%) preferred Pepsi and and of the 43 female subjects, 19 (44.19%) preferred Pepsi. 3. Provide the z-value and p-value for the comparison. For example: Report as z = 1.275, p = .10. (If you predicted ahead of time what you expected to find, use the p-value from a "one-tailed" test. If not, use the p-value from a "two-tailed" test.) 4. Interpret the results. For example: "The comparison was not statistically significant. While more males preferred Pepsi than females, this was probably due to chance error and not to an actual abilitiy to tasting ability in the two groups. However, this comparison was approaching statistical significance. Remember, you must answer questions 1-4 for EACH comparison or correlation.
|
|
|