# [[EDUC 7215 ]]Assignment 6 Jethro Jones Also available online at [drjethro.com/7215ass6](https://drjethro.com/7215ass6) # Assignment ## Research Question: How are the variables Pro-Environmental Behavior (PEB), New Environmental Paradigm (NEP), Personal Norms (PN), and Ascription of Responsibility (AR) related? We will use a type I error rate of 5% or 0.05 to define statistical significance. ## Methods for Correlation Analysis: I used Tasks and Utilities -> Tasks -> Statistics -> Correlation Analysis. I selected our PEB dataset from the library. Under Roles, I selected PEB, NEP, PN, and AR as the Analysis variables. Under the Options tab, I chose Selected Statistics under Statistics and checked the Correlations and Display p-values boxes. I also checked the box for Spearman’s rank-order correlation under Nonparametric Correlations. For Plots, I selected Matrix of scatter plots and checked the Include histograms box. I clicked the Run icon and opened the file in a new window. Then I screenshotted and saved the files using an AI naming tool. ## Results The matrix of scatterplots show a positive relationship between all of them! PEB and AR and NEP and AR are the weakest. The rest of them seem stronger. The histograms show bell-shaped curves for PEB and NEP, but not bell-shaped curves for PN and AR. I don't see any extreme outliers for any scatterplots. ![[2025-03-17 ScatterPlotMatrix.png]] As you can see from the Pearson Correlation Coefficients below, all relationships are significant at <.0001! **PEB** has moderate positive correlations with **NEP (0.48)** and **PN (0.54)**, and a weaker correlation with **AR (0.331)**. **PN** and **AR** showed the strongest correlation (**0.568**), suggesting personal norms strongly relate to ascription of responsibility, which makes a lot of sense to me. ![[2025-03-17 PearsonCorrelationTable.png]] The Spearman Correlation Coefficients again show a significant relationship with all p values p<.0001. These tests closely mirrored the Pearson results, which shows consistency. ![[2025-03-17 Spearman Correlation Coefficients.png]] ## Summary: PEB moderately correlates with NEP and PN but weakly with AR. The strongest relationship is PN and AR, which makes me think that people with strong personal norms also strongly ascribe responsibility to themselves. The results from Pearson and Spearman suggests linear relationships and that there aren't major effects from outliers. ## Assignment Requirements: Assignment 6 (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.  You will recall that PEB is the arithmetic mean of 20 questions from of the pro-environmental behavior scale developed by Markle (2013). In Assignment 5, you will again use PEB as one analysis variable, but you will also analyze three additional ratio scale variables: NEP (New Environmental Paradigm), PN (Personal Norms), and AR (Ascription of Responsibility).  NEP is the arithmetic mean of 15 questions from the hypothesized facet scale developed by Hawcroft & Milfont (2010).  PN is the arithmetic mean of 9 questions from the personal normative scale developed by Steg et al. (2005).  AR is the arithmetic mean of 6 questions from the scale of environmental responsibility also developed by Steg et al. (2005).  You can read more about each of the questions that comprise these scales in the Coding Description worksheet within the EDUC7215 Assignment Dataset workbook.  These four analysis variables (PEB, NEP, PN, AR) are related in the sense that together they define our environmental behavior.  So, we would expect them to be correlated to some degree.  We learned about correlation analysis in Chapter 11, which allows us to objectively quantify the correlation between ratio scale continuous variables.  We will use correlation analysis to determine the degree of correlation between these four variables. 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 perform a correlation analysis of PEB, NEP, PN, and AR.  A broad research question for this analysis could be, “How are the variables PEB, NEP, PN, and AR related?”  Since correlation analysis is a data exploration tool, we will not test formal hypotheses beyond determining if the correlations are significant or not.  You will calculate Pearson’s Correlation Coefficient and Spearman’s Rank Correlation Coefficient and report their p-values.  You will also create a scatterplot matrix and interpret the relationships between the four analysis variables.  Use the Chapter 11 Example Problems document as a guide for how I want your assignment to appear. # Just for Fun Just for fun, I uploaded the data to ChatGPT and asked it to run this assignment for me. While it couldn't create the graphs, it did give me the code to put into python or R to make it run and produce the graphs, but I didn't need that anyway. Fascinating where there were a couple errors here. **Research Question:** *How are the variables Pro-Environmental Behavior (PEB), New Environmental Paradigm (NEP), Personal Norms (PN), and Ascription of Responsibility (AR) related in the given dataset?* --- ### Methods: - Data from the provided Excel dataset (*EDUC7215_Assignment_Dataset.xlsx*) was imported into SAS Studio. - A correlation analysis was conducted to evaluate Pearson’s correlation (parametric) and Spearman's rank-order correlation (nonparametric). - Scatterplot matrix visualizes relationships among these variables. --- ### Results: #### Scatterplot Matrix Interpretation: - The scatterplots visually indicate positive relationships between all variables (PEB, NEP, PN, and AR). - No extreme outliers or non-linear patterns were prominently observed. --- ### Pearson Correlation Analysis: | Variables | PEB | NEP | PN | AR | |-----------|------------|------------|------------|------------| | **PEB** | 1.000 | | | | | **NEP** | 0.474** | 1.000 | | | | **PN** | 0.525** | 0.525** | 1.000 | | | **AR** | 0.331 | 0.405** | 0.568** | 1.000 | - **All correlations significant at p < 0.001 level.** - **PEB** has moderate positive correlations with **NEP (0.47)** and **PN (0.53)**, and a weaker correlation with **AR (0.331)**. - **PN** and **AR** showed the strongest correlation (**0.568**), suggesting personal norms strongly relate to ascription of responsibility. --- ### Spearman Correlation Analysis: | Variables | PEB | NEP | PN | AR | |-----------|------------|------------|------------|------------| | PEB | 1.000 | | | | | NEP | 0.474** | 1.000 | | | | PN | 0.526** | 0.497** | 1.000 | | | AR | 0.356** | 0.413** | 0.553** | 1.000 | - **All correlations significant at p < 0.001 level.** - Spearman correlation results closely mirrored Pearson results, indicating consistency. --- ### Interpretation & Summary: - **PEB (pro-environmental behavior)** moderately correlates positively with **NEP (environmental paradigm)** and **PN (personal norms)**, and weakly with **AR (responsibility)**. - The strongest relationship observed is between **PN and AR**, suggesting individuals with stronger personal norms also strongly ascribe responsibility to themselves regarding environmental issues. - Correlation consistency across Pearson and Spearman suggests linear relationships without substantial effects from outliers.