Name | Office hours | Office hour location | |
---|---|---|---|

TA | Siwei Chen | Mon 4:00PM-5:00PM | Comstock B-108 |

Professor | Jacob Bien | Tues 10:00AM-11:00AM | Comstock 1178 |

TA | Christine Diepenbrock | Wed 12:30PM-1:30PM | Comstock B-108 |

TA | David Sinclair | Thurs 2:30PM-3:30PM | Malott 230 |

TA | Xiaojie Mao | Fri 10:00AM-11:00AM | Comstock B-106 |

We encourage you to make full use of office hours. If you have a question about the material or an assignment and cannot make it to office hours, we encourage you to post this question on piazza (your post can be made anonymous to other students, but the teaching staff will be able to see who is posting). For other matters that do not involve the rest of the class, you may send an email to the 6010 staff email address BTRY6010@cornell.edu. We appreciate if you can use this email address instead of emailing a specific member of the teaching staff.

The goal of this course is to introduce graduate students to statistical methods for analyzing data. We will emphasize the basic principles and criteria for selecting the appropriate statistical technique. Students will get hands-on experience applying the topics covered to real datasets using R, a powerful and popular open-source statistical computing language.

Topics covered:

- descriptive statistics & data visualization
- probability
- point and interval estimation
- hypothesis testing
- inference for a single population
- comparisons between two populations
- one- and two-way analysis of variance
- analysis of categorical data
- simple linear regression
- multiple linear regression

In addition to the more standard topics covered in an introductory statistics class, special emphasis will be placed on practices that facilitate reproducible analyses. There has been growing attention in the scientific community to the importance of adopting practices that ensure reproducibility. If you are interested in reading more about this topic, see here or here or here or here or here.

Recently developed tools in R have made it easy to create reports that clearly document the steps taken in an analysis. Labs, assignments, lectures (and even this syllabus!) will all be generated with this tool.

OpenIntro Statistics is a free, online textbook. If you prefer a printed version of the text, it can be purchased for $7.60.

We will be using R Studio, which is an easy-to-use environment for coding in R. The first homework will guide you through installing the necessary software (and if you have any difficulty, feel free to ask a TA during office hours). **We assume no prior knowledge of R in this course.** Labs will gradually introduce you to R. There are also many good resources for R online. For example, this website provides an interactive introduction to R, and A Beginner’s Guide to R, which is accessible for free online through the Cornell library, is a book that may be helpful.

There are two relevant websites for the course. Blackboard will be used for homework submission, recording grades, and posting course materials; Piazza will be used as an online discussion forum. (Students enrolled in the course as of the first week will be added to piazza automatically.) The discussion forum is a good way to ask questions that you think other students would like answered as well. Students may answer each other’s questions, but TAs will do so as well (note that in some cases it may take 24 hours for a TA to respond to a question). For matters that do not belong on a discussion forum, you may send an email to the 6010 staff email address BTRY6010@cornell.edu.

The course has both lectures and lab sessions.

What | When | Where | Who |
---|---|---|---|

Lecture | Tues/Thurs 8:40AM - 9:55AM | Ives Hall 305 | Jacob Bien |

Lab 402 | Tues 1:25PM - 2:40PM | Mann Library B30A | Christine Diepenbrock |

Lab 403 | Tues 2:55PM - 4:10PM | Mann Library B30A | David Sinclair |

Lab 404 | Wed 2:55PM - 4:10PM | Mann Library B30A | Siwei Chen |

Lab 405 | Tues 7:30PM - 8:45PM | Mann Library B30B | Xiaojie Mao |

What | How much |
---|---|

Homework | 9% |

Prelim 1 | 29% |

Prelim 2 | 29% |

Final | 29% |

Exploration | 4% |

The *Exploration* component will be earned through completing “micro-assignments.” These may be more varied, sporadic, or open-ended than homework assignments. Examples of micro-assignments: I might ask you to read and write a short response to a reproducibility-related article, watch an online lecture about a “forensic” statistician (who uncovered major problems in a high-profile biomedical article), read a FiveThirtyEight article (that takes a data-informed view of the news), solve a problem related to lecture, or apply something we’ve learned to data from your field of study. The hope is that micro-assignments will be a fun way to interact with the material in a less structured way than in lecture/lab/homeworks/exams and that they will encourage you to think about what we are learning in a broader, more applied context. Micro-assignments are different in nature from homework. For example, if you don’t do a micro-assignment, it will not have negative consequences on your ability to do well on exams. (This is in contrast to homework assignments, which gives practice on material you will be expected to know on exams.)

We will have weekly homework assignments, which are to be submitted on blackboard. Discussing homework with classmates is encouraged, but you *must* write up your assignments individually. You may also ask course staff for guidance/hints, but **please only ask for help on a homework problem after giving it a serious effort on your own** (which includes reading the relevant sections of the text).

**More detail:** You should start by working on each problem on your own, without anyone else. Then (and only after this first step), when you’ve identified problems that are difficult or require discussion, you may talk with others in the class (or a teaching staff member in office hours) about this. Then, after this discussion you can independently go back to writing your homework. This is very different from doing your homework side-by-side with a classmate. This policy is not just to help us evaluate people separately. Doing homework carefully on your own (which includes spending time being stumped on a problem, looking back at the book and your lecture/lab notes to clarify misunderstandings) is the best way to make sure you are actually internalizing the course material in a deep and lasting way. If you don’t let yourself be stuck on a problem (before getting help), it’s hard to notice areas of material that you actually should be studying more closely. If you find that you have no idea how to do any of the problems on your own, that is a good indication that you should be approaching this class differently and you should come to office hours for guidance in how to go about learning the material in this class more effectively. (Better to realize this while doing a homework than during an exam!)

**Late homework policy:** It can be difficult on the teaching staff to have to decide on a case-by-case basis what constitutes an acceptable or unacceptable reason for a homework to be late. Thus, we will simply not accept any late homework (and give these a 0). At the end of the semester, we will drop the *lowest two* homework scores.

What | When | Where |
---|---|---|

Prelim 1 | Sep 29, 7:30pm-9:30pm | MVR G71 & G73 |

Prelim 2 | Nov 3, 7:30pm-9:30pm | Ives Hall 305 |

Final | Dec 10, 2:00pm-5:00pm | TBA |

It is expected that you will adhere to Cornell’s Code of Academic Integrity. If you are unfamiliar with it, please read “Guidelines for Students” at http://cuinfo.cornell.edu/aic.cfm.

The course staff wants to make sure that we accommodate to your needs. Please provide the professor with a Student Disability Services (SDS) accommodation letter within the first three weeks of the semester so that we can be sure to accommodate accordingly.