Bachelor of Statistical Data Science (BSDS)

Indian Statistical Institute

Statistics I: Data Exploration

---

Course information

• Instructor: Deepayan Sarkar <deepayan@isid.ac.in>
• TA (Bangalore): Suparna Biswas <suparnabsws4@gmail.com>
• TA (Delhi): Deborshi Das <deborshidas6@gmail.com>
• TA (Kolkata): Chirayata Kushari <tuhinkushari@gmail.com>
• Grading scheme
• Quizzes / Assignments: 20%
• Midterm Exam: 30%
• Final Exam: 50%

Please use this Discussion forum on GitHub to ask questions or initiate other discussions (keeping in mind that this is a public forum). If you wish to talk to me individually, please email me to schedule an online meeting.

Tasks

• Fill up this survey by the end of the first week.

• Create an account on GitHub if you do not already have one

• Submit your GitHub id and personal email address by filling up this form.

• Install the R packages HistData and NHANES. We will initially use the data in these packages to explore various statistical concepts.

Quizzes and Tests

• Investment Quiz (tutorial, September 9), Solution

Datasets

• Survey responses: CSV file

• Daily Air Quality at R. K. Puram, Delhi: CSV file (Source: aqicn.org)

Slides

• Orientation / Introduction to R

• Distributions

• Data Collection and Summarization

• Efficiency and Robustness

• Optimization for LAD regression

• Categorical data

• Continuous distributions

R scripts / demos

• Preliminary analysis of survey data

• Summarizing bivariate data

• Optimization for LAD regression

• Density estimation for continuous distributions, sampling distribution of mean and median

Resources

• Introduction to Statistical Thinking (online book)

• Applied Statistics with R (online book)

• Expository material on R (slides)

Assignments

Assignment 0

This is a starter assignment to introduce you to assignments on GitHub. There is no deadline, and do not need to submit anything. However, you do need to click on the assignment, choose your roll number, and follow subsequent instructions. This process will link your GitHub account to your roll numbers.

Please complete this before or during the tutorial on August 29. If you do not know your roll number, ask your TA.

Assignment 1

This assignment asks you to toss a coin and count the number of heads. This trivial assignment is mainly to make sure that we all understand how to submit assignments through GitHub.

Deadline: September 1. This counts as a graded assignment, and you will be penalized if you do not submit the assignment.