Chapter 6 Methods

For analyzing the response data, drawing inferences about the underlying distribution and modeling the response to capture the trend or composition or hidden patterns between the study variables, I used several statistical tools as follows-

• Descriptive Statistics: It was used to conduct Exploratory Data Analysis. We saw the average scores, median, mode, etc. We did extensive data visualization and also started to understand the correlation between the items and domains involved in study variables.

• Inferential Statistics: It was used to find out Confidence Intervals, Test Hypothesis, Fit distributions to the data.

• Linear Regression: It was used to model the dependence of one variable on the other variables, understand and find the expected variable score. It captured the composition of the overall pro-environmental attitude.

• Clustering: Heirarchial Agglomerative Clustering was used to cluster the items, domains and respondents to understand the similarity and dissimilarity of study variables and low and high scorers.

• PCA: Principle Component Analysis was used to provide low dimensional summary of the data collected and understand the spread and inclination in the response data.

• Reliability Testing: It was used to find out the reliability of the response data we have collected.