# [[EDUC 7215]] Assignment 2 Jethro Jones Can also be viewed at https://drjethro.com/Assignments/EDUC+7215+Assignment+2 ## Assignment Research Question: Does the internal locus of control equal the global rate of (adjusted) 4.095? I loaded the data from the EDUC7215 Assignment Dataset called "Behavior" into SAS, and selected t-test from the tasks. Under options, I chose two-tailed test, with an alternative hypothesis mu^=4.095 I selected tests for normality and non-pararmetric tests (sign test and Wilcoxon signed rank test.) I left plots as "default plots." The distribution of Control is shown below. ![[distribution of control.png]] The test for normality shows that because the p values are less than .05 (my type 1 error rate), we can reject the null hypothesis. ![[7215ass2testsfornormality.png]] Since it is not quite a normal distribution, the t-test should be used with caution. The Q-Q Plot of Control, below looks a little strange, with plateaus for each response on the likert scale, as you mentioned. And there is significant deviation from the line especially at the top end of the results, the likert scale response of 7. ![[7215ass2qqcontrol.png]] For the histogram, I selected the same data set as above, chose Histogram from Tasks and Utilities, and selected Control as the analysis variable. I left the scale as percent. Under appearance, I chose the normal density curve and the kernal density estimate, then clicked run. This produced the same graph as shown above. For the box plot, I chose box plot from Tasks and Utilities, and then chose the same data set, changed the plot orientation to horizontal, and chose the analysis variable as Control. This produced the following box plot. ![[7215ass2boxplot.png]] This references the mean from the t test that appears close to 4.095, but is reported as 5.0106. The standard error is .0690, which means that 4.9416 is the lowest likely score, which is higher than the locus of control reported in the global study. ![[7215ass2mean.png]] Conclusion: Missourians in this study report a higher locus of control than the global data set. We reject the null hypothesis that the Missourians would be the same as the global data set. Congratulations Missouri! ## Assignment Directions Assignment 2 (20 points) The dataset used for this assignment (and subsequent assignments) was created from a Value-Belief-Norm (VBN) Theory-based survey designed to assess the factors that influence pro-environmental behavior in the Missouri area.  Mostafa (2016) analyzed data from the World Values Survey, which surveys people globally every 5-6 years.  He found 58,379 respondents on a Likert scale with a range of 1 to 10 that the mean score for internal locus of control was 5.85. Internal locus of control refers to a belief that one’s actions can bring about an outcome whereas an external locus of control refers to one’s belief that they are powerless to affect an outcome.  So, higher values on this scale indicate a sense of control while lower values indicate a sense of powerlessness.  In our survey, we used the same question as Mostafa (2016), though he measured it on a 10-point Likert scale, and we measured it on a 7-point Likert scale.  The variable name in the Coding Description is CONTROL.  So, his mean value = 5.85 converts to 4.095 on our scale.  We want to compare the mean value of CONTROL in our survey of Missouri respondents to the expected value of 4.095 from the global value survey.    Note: the measurement scales for the questions in this survey are Likert scales. There is debate whether Likert scale data are ordinal or interval.  I take the position for the purpose of these assignments that the Likert scale data are ordinal.  Import the data (repeated from Assignment 1): The dataset is an Excel file named: “EDUC7215_Assignment_Dataset.xlsx”.  You will find under Modules -> Assignments on our Canvas page. You need to upload it into your SAS Profile Folder in the Cloud so SAS Studio can access it.  There are three worksheets in the Excel workbook: Final Data, ReadMe, and Coding Description.  The ReadMe and Coding Description worksheets contain details about all the variables in the dataset. The Final Data worksheet contains the data, and you need to type “Final Data” in the “Worksheet Name” box in the Import Data pane.  Also, you can change the Output Data name from “Import” to whatever you choose; I chose “Behavior”. Once you click the Run icon, the dataset will be loaded into SAS Studio (these are the same steps that I described in the lecture ppt & video for Chapter 5).  There are many variables in the dataset, but we will only use a few of them for this assignment.  Now you are ready for data analysis! For this assignment, I want you to analyze internal locus of control (CONTROL) by comparing it to the expected value of 4.095.  Describe the distribution of CONTROL using the summary statistics as well as the Histogram and Box plot.  Test for normality using the normality statistics and the Q-Q plot.  Use a one-sample t-Test and a Wilcoxon signed rank test to test the hypothesis: •    Ho:  CONTROL = 4.095   •    Ha: CONTROL ≠ 4.095 Develop an appropriate Research Question, and formally state all testable hypotheses (i.e., the normality test and the t-test/Wilcoxon test). You should also include your type 1 error rate, decision rules, and conclusion interpretations.  You should also include a Methods paragraph.  I recommend that you use the Chapter 7 Example Problem document as a guide for completing this assignment.  Note: The Q-Q plot will look unusual because the circles are grouped by the discrete Likert scale values.