HW2 Tell a data story;
As the instructor for this class, I would like to know more about the backgrounds of my students and adapt my teaching to better fit needs of the class. So I designed a survey to gather student information, including:
• Students’ basic demographics: gender
• Students’ prior knowledge on data analysis: the number of data science courses taken (objective measure), self-assessment of data mining efficacy (subjective measure).
• Students’ future career goal: level of interest in data analyst job and expected salary
• Students’ geo-location and preference for 1×1 virtual meeting
The survey can be accessed from
The survey will be closed at 06/15 11:59pmEST. The survey data will be available to the class on the next day.
Analyze the survey data using knowledge you learned so far in the course (which may include but are not limited to: identify potential data issues and perform data cleaning methods, if necessary, to prepare analysis dataset; check appropriate descriptive summary statistics depending on different types of variables; explore bivariate relationship; etc.) and report any interesting patterns that you may find. Add useful visualization to help you tell your data story. Write a summary of your findings which may inform the instructor to adjust the course contents and delivery methods accordingly.
You can choose whichever tools you might feel most comfortable with for this analysis task. It could be any statistical programming language or software (such as R, SAS, SPSS, STATA, MINITAB, EXCEL, etc.). Because this is not a statistical programming course and the students in this class come from a diverse background, I will not grade based on your experience and familiarity with certain programming tools. The focus is to for the students to apply the principles and essence of data preprocessing and exploration to real world data tasks and able to effectively and accurately communicate findings and provide evidence-based policy recommendations to your audience.
Be concise and precise. Remember your report serves three purposes: (1) to convince people that your finding is valid, and (2) to provide enough information for people to repeat your analysis. (3) to provide data-driven suggestions to influence decision making.
– At least 12-point Arial or Times New Roman
– At least 1-inch margins on all sides.
– Submit a data analysis report (up to three pages)