Hello, I am a Professor of Marketing at Gonzaga University. I teach, conduct research, and consult in areas related to marketing, marketing research, and data analysis. I use this site to occasionally blog about topics that interest me and to create a listing of R-related resources for myself and my students. I have provided the R code for many of my blog posts through GitHub and if you find something missing in them, please contact me. Since Dropbox has stopped rendering web pages and made the public folder private, there may be blog posts where interactive graphs may be missing. Please drop me an email and mention the missing graphs. I will make them available to you.
If you have reached this website searching for the figures and tables published in 2014 article in the Journal of Marketing Analytics, please visit http://patilv.com/2014JMAWebsite/ for them.
Besides creating a course on this topic, I have worked on data visualization projects that have been featured in different fora in Gonzaga University. My blog provides a good glimpse of the power of data visualization and the types of static and interactive graphs and charts that can be created to tell stories based on data.
This stream of work in marketing and marketing strategy stems from my core discipline of marketing in which I apply my data analysis tools.
A questionnaire is not just a collation of individual questions. Its design combines the science and art of creating measurement scales and understanding the effect of the questions on respondents. These serve the ultimate purpose of addressing the key decisions that are being considered and the objectives of the research. In this regard, I have had the opportunity to create questionnaires for non-profits and for-profit organizations.
Statistical analysis and Machine Learning
Over a span of 18 years, I have used a number of statistical models for my personal research and for different clients. Some of the purposes for which I have used these models include testing differences in distributions (e.g., chi-square tests, Wilcoxin signed rank test), differences in means and medians (e.g., t-test, ANOVA, Mann-Whitney test), linear models (e.g, multiple and logistic regression, discriminant analysis), and other methods that study relationships between respondents and scale items (e.