• Time: Tuesday/Thursday 1:35 PM - 2:50 PM
• Location: Neville 002 (NV 002)
• Taeho
Kim / tak422@lehigh.edu
• Office: Chandler-Ullmann 229
• Office Hours:
T 3:30-4:30 pm, R 3:30-4:30 pm or by appointment.
• Web Office Hours: W
1:00-2:00 (PW:012312)
• Syllabus: Download
• Gradescope: LINK
1. Letter Grades for Section 010/011 have been
recorded.
| Exam | Date | Time | Location | Practice Exam | Practice Exam Sol |
|---|---|---|---|---|---|
| Exam I | 10/05 | 1:35-2:50 PM | Neville 002 | [Practice Exam I] / [Template] | [Practice Exam: Sol] |
| Exam II | 11/14 | 1:35-2:50 PM | Neville 002 | [Practice Exam II]/ [Template] | [Practice Exam: Sol] / [NOTE] |
| Final Exam | 12/13 | 8:00-11:00 AM | Drown 210 | [Practice Final Exam] / [Template] | [Practice Exam: Sol]/ [NOTE] |
| Guideline | Due |
|---|---|
| [Project Guideline] | 12/17 (11:00 PM) |
| # | Homework | Release | Due (11:00pm) | Solution |
|---|---|---|---|---|
| 1 | [HW1] / [Template] | 9/1 | 9/8 | [HW1: Sol] |
| 2 | [HW2] / [Template] | 9/8 | 9/15 | [HW2: Sol] |
| 3 | [HW3]/ [Template] | 9/15 | 9/22 | [HW3: Sol] |
| 4 | [HW4]/ [Template] | 9/22 | 9/29 | [HW4: Sol] |
| 5 | [HW5] / [Template] | 9/29 | 10/03 | [HW5: Sol] |
| 6 | [HW6] / [Template] | 10/13 | 10/20 | [HW6: Sol] |
| 7 | [HW7]/ [Template] | 10/20 | 10/27 | [HW7: Sol] |
| 8 | [HW8] / [Template] | 10/27 | 11/03 | [HW8: Sol] |
| 9 | [HW9]/ [Template] | 11/04 | 11/10 | [HW9: Sol] |
| 10 | [HW10] / [Template] | 11/23 | [HW10: Sol] | |
| 11 | [HW11] / [Template] | 12/5 | 12/10 | [HW11: Sol] |
| # | Lab | Due Date (11:00 pm) | Solution |
|---|---|---|---|
| 1 | [Lab 1] | 8/29 | - |
| 2 | [Lab 2] | 8/31 | [Lab 2: Sol] |
| 3 | [Lab 3] | 9/05 | [Lab 3: Sol] |
| 4 | [Lab 4] | 9/07 | [Lab 4: Sol] |
| 5 | [Lab 5] | 9/14 | [Lab 5: Sol] |
| 6 | [Lab 6] | 9/19 | [Lab 6: Sol] |
| 7 | [Lab 7] | 9/21 | [Lab 7: Sol] |
| 8 | [Lab 8] | 9/26 | [Lab 8: Sol] |
| 9 | [Lab 9] | 9/28 | [Lab 9: Sol] |
| 10 | [Lab 10] | 10/10 | [Lab 10: Sol] |
| 11 | [Lab 11] | 10/12 | [Lab 11: Sol] |
| 12 | [Lab 12] | 10/17 | [Lab 12: Sol] |
| 13 | [Lab 13] | 10/19 | [Lab 13: Sol] |
| 14 | [Lab 14] | 10/24 | [Lab 14: Sol] |
| 15 | [Lab 15] | 10/26 | [Lab 15: Sol] |
| 16 | [Lab 16] | 10/31 | [Lab 16: Sol] |
| 17 | [Lab 17] | 11/02 | [Lab 17: Sol] |
| 18 | [Lab 18] | 11/16 | [Lab 18: Sol] |
| 19 | [Lab 19] | 11/21 | [Lab 19: Sol] |
| 20 | [Lab 20] | 11/28 | [Lab 20: Sol] |
| 21 | [Lab 21] | 11/30 | [Lab 21: Sol] |
| 22 | [Lab 22] | 12/04 | [Lab 22: Sol] |
| Date | Topics Covered | Related Material |
|---|---|---|
| 8/29 (Day1) | The course website was checked, and the syllabus was reviewed. Then, R’s fundamental syntax was introduced. Additionally, basic data types and operations were briefly covered. We also installed Rmarkdown to create dynamic documents. At last, Lab 1 was completed. | - |
| 8/31 (Day2) | We continued to discuss basic R syntax. R data structures were introduced, such as vectors, arrays (matrices), data frames, and lists. Four different subsetting approaches were discussed: [, [[, $ operators, and the subset() function. Lastly, we briefly covered reading and writing data in R. | - |
| 9/05 (Day3) | We discussed the method to write our own R function. We also covered control flows: if statement, if…else statement, if…else ladder statement, ifelse(), for loop, and while loop. In the end, we discuss a way of vectorization with matrix or data.frame by using apply() function. | - |
| 9/07 (Day4) | We discussed data visualization in R. Several R functions for different visual displays were introduced: barplot(), plot(), hist(), boxplot(), and curve(). Lastly, we briefly went over the basic idea of ggplot2 packages for fancy visualizations. | - |
| 9/12 (Day5) | We started to review probability. Basin concepts of probability were introduced. We covered several probability distributions up to the normal distribution. Lab 5 was postponed as we could not finish the review. | - |
| 9/14 (Day6) | We finished the probability review. For statistical review, we covered point estimation. | - |
| 9/19 (Day7) | We discussed the interval estimation and hypothesis testing, and finished the statistics review. | - |
| 9/21 (Day8) | We started the topic of random variate generation. We discussed sampling from a finite population using a box model. Then, we talked about the quantile function (inverse CDF) and probability integral transformation. These provide the groundwork for the inverse transform method for random variate generation. | - |
| 9/26 (Day9) | We continued discussing random variate generation, covering the inverse transform method for discrete random variates and the general transformation method. In the discrete case, obtaining the inverse CDF can be challenging, leading to a different implementation compared to the continuous case. | - |
| 9/28 (Day10) | We discussed the Acceptance-Rejection Method. | - |
| 10/03 (Day11) | We reviewed the practice exam and briefly discussed the questions in HW 5, as they are relevant to the exam. | - |
| 10/05 (Day12) | Exam I | - |
| 10/10 (Day 13) | After a brief review of the Exam I questions, we proceeded to the new topic: the Monte Carlo method. In particular, we discussed Monte Carlo Integration. | - |
| 10/12 (Day 14) | We discussed the MC integration for finite bound (a,b). Then, for the infinite boundary, we looked at the example of the standard normal CDF approximation, and handle the situation with three different approaches: Naive-Uniform, Change-of-Variable, and Hit-or-Miss. | - |
| 10/17 (Day 15) | We started to discuss the variance reduction. When we evaluate the quality of approximations in the MC integration, any MC approximations are unbiased, so the variances equal to the MSEs. For different approximation approaches, we can compare their performances in terms of the efficiency derived by empirical variances. The antithetic approach was introduced as the first variance reduction method. | - |
| 10/19 (Day 16) | We discussed two other approaches to reduce the variance of approximations in MC integration. The control variates approach used a function \(s(x)\) and the reduction was achieved when \(cov[g(X),s(X)]^2\) was large in relation to \(var[s(X)]\). The antithetic approach used a new density \(h(x)\) (a.k.a. importance function) to reduce the variance. The \(h(x)\) needs to be chosen in the way that \(w(x)=g(x)f(x)/h(x)\) is flatter than \(g(x)\). | - |
| 10/24 (Day 17) | We started the Monte Carlo in Statistical Inference. The point estimation was discussed with a trimmed mean estimator. The interval estimations were explained with the CI for the variance \(\sigma^2\). | - |
| 10/26 (Day 18) | We discussed the hypothesis testing, and took a look a simple example for z- and t-test. The focus was on the evaluation of the testing procedures based on probabilti of Type-I and -II errors. | - |
| 10/31 (Day 19) | We review the evaluations for the hypothesis testing. Sign test was introduced for the case we have symmetric unknown distribution. The Bootstrap and Jackknife procedure were discussed with the corresponding standard error and bias estimations, respetctively. | - |
| 11/02 (Day 20) | We discussed five resampling CIs: Standard Normal Bootstrap CI, Standard Normal Jackknife CI, Percentile Bootstrap CI, Basic Bootstrap CI, and Bootstrap-t CI. | - |
| 11/09 (Day 21) | We reviewed the practice exam. | - |
| 11/14 (Day 22) | Exam II | - |
| 11/16 (Day 23) | We discussed the histogram as an estimator of density function \(f(x)\). For the histogram, it is important to choose the right bin width \(h\), so we discussed three different approaches: Sturges’rule, Scott’s rule, and Freedman-Diaconis rule. | - |
| 11/21 (Day 24) | We reviewed the questions in Exam II and discussed methods for creating a smoother density estimator, including the Average Shifted Histogram and Kernel Density Estimator. While both are interesting, the kernel density estimator provides a simple yet powerful estimation result. | - |
| 11/28 (Day 25) | We reviewed the form of the kernel density estimator and proceeded to the Markov Chain Monte Carlo. While only a brief introduction was provided for Markov Chain, we focused more on the idea and implementation based on the Metropolis-Hastings Sampler. | - |
| 11/30 (Day 26) | We reviewed the Metrolpolis-Hastings sampler, focusing on its flexbility. The Gibbs sampler was discussed as the secomd approach to implement the MCMC. It is very useful to generate r.v.’s for higher dimensional dist’n when its conditional dist’ns are fully available to us. | - |
| 12/05 (Day 27) | We discussed a special topic, Bayesian Inference. The basic idea was introduced and its connection to the MCMC was explained. We saw that the Metropolis-Hastings Sampler is particularly useful for the Bayesian inference. | - |
| 12/07 (Day 28) | We solved the practice exam together. The course evaluation was done at the end of the class. | - |
Please inform me if you come across any errors.
Attendance
Attendance at lectures is required. Announcements will often be made in
class and students are responsible for the contents of every lecture.
The instructor will check attendance.
Labs
Students will have short labs (10 – 25 mins) after lectures during class
time. In these labs, students will be able to run the R code
examples illustrated in the lectures and write their own R code
for similar questions. The labs will be graded for completion
completion and correctness. Students are required to submit their
compiled PDF and the .Rmd file to Gradescope by 11:00 pm on
their assigned dates. Clear comments to the R code are required.
No late labs will be accepted except in the case of a documented
University Excused Absence. The lowest lab score will be
dropped.
Project
Graduate students will have one project for this class. It will be an
individual project related to the material covered in the class. The
details will be provided after the second exam. Undergraduate students
don’t have a project.
Homework
Homework assignments will be posted on the course website, usually every
Friday. Those are typically due a week later unless otherwise announced.
Homework assignments must be submitted via Gradescope by 11:00 pm on
their perspective due dates. The entire set of homework solutions must
be compiled using R Markdown. You must upload a compiled PDF of
your solutions and the .Rmd file. No late homework will
be accepted except in the case of a documented University Excused
Absence. The lowest homework grade will be dropped when
computing your course grade. You may discuss assigned problems with
fellow students, but you MUST write the solutions up yourself
independently. Copying solutions (from another student’s work
or another source) constitutes academic dishonesty. Content generated by
an Artificial Intelligence third-party service or site (AI-generated
content) without proper attribution or authorization is another form of
plagiarism. Graders have been instructed to alert instructors if they
suspect a student has copied solutions. Depending on the cases, a
complaint may be initiated against the student(s) involved through the
LU Judicial System.
It you ever have questions about drawing the line between others’ work
and your own, ask me and I will give you guidance or you may visit
Lehigh Library’s Proper Use of
Information.
Midterm
Midterms will take place during the regular class time, in the normal
classroom location. The detailed format of the midterms will be
announced later. There will be assigned seating for the Midterms. The
midterms are tentatively scheduled for October 5 and November
9.
Final Exam
The final exam is cumulative. The final exam is to be held during the
scheduled time by Registrar’s office.
| Component | Section 010 | Section 011 |
|---|---|---|
| Attendance & Labs | 15% | 10% |
| Project | - | 10% |
| Homework | 20% | 20% |
| Midterm I | 20% | 20% |
| Midterm II | 20% | 20% |
| Final Exam | 25% | 20% |
| Total | 100% | 100% |
| Grading Scale | Range | Grading Scale | Range |
|---|---|---|---|
| A | 94-100 | A- | 90-93.9 |
| B+ | 87-89.9 | B | 83-86.9 |
| B- | 80-82.9 | C+ | 77-79.9 |
| C | 73-76.9 | C- | 70-72.9 |
| D+ | 67-69.9 | D | 60-66.9 |
| F | <60 |
If you must miss a scheduled exam, contact your instructor before the test date and time. Make-ups will only be offered to students with a valid justification. To qualify for a make-up exam due to a health issue, personal emergency event, or the death of a family member, the following three things must hold:
This schedule is subject to change depending on progress during the
semester.
| Topic | Chapter |
|---|---|
| Introduction to R, RStudio, R Markdown and Basic Syntax | 1 |
| Probability and Statistics Review | 2 |
| Methods for Generating Random Variables | 3 |
| Midterm I | - |
| Monte Carlo Method in Integration | 6 |
| Monte Carlo Method in Inference | 7 |
| Bootstrap and Jackknife | 8 |
| Midterm II | - |
| Markov Chain Monte Carlo (MCMC) Method | 11 |
| Probability Density Estimation | 12 |
| Visualization of Multivariate Data | 5 |
| Final Exam | - |
During orientation, first-year students sign a pledge to abide by the Undergraduate Student Senate’s affirmation of the Code of Conduct. At the first-year convocation, a representative of the Student Senate presents a binder containing those signatures to the President. This symbolic ritual highlights the core values of honesty and integrity in Lehigh’s culture. The Provost for Teaching and Learning developed seven short vignettes describing cases where student actions bring into question issues of academic integrity and community standards. These vignettes are available at http://www.lehigh.edu/lts/official/Academic_Integrity_Vignettes.pdf. These vignettes on academic dishonesty cases are all based on actual cases that have come before the University Committee on Discipline. Various university web resources also provide material to help understand the student Code of Conduct’s expectations, way to report violations of the Code, and the thoughtful adjudication of Code violations to which the Dean of Students Office is committed. The Undergraduate and Graduate Student Senates have affirmed students’ responsibility to uphold academic integrity by creating student statements of academic integrity (http://go.lehigh.edu/integrityresources).
Students are expected to check email on a regular basis. Even if a student fails to check email for messages, the student is still responsible for any announcements made using email.
Lehigh University is committed to maintaining an equitable and inclusive community and welcomes students with disabilities into all of the University’s educational programs. In order to receive consideration for reasonable accommodations, a student with a disability must contact Disability Support Services (DSS), provide documentation, and participate in an interactive review process. If the documentation supports a request for reasonable accommodations, DSS will provide students with a Letter of Accommodations. Students who are approved for accommodations at Lehigh should share this letter and discuss their accommodations and learning needs with instructors as early in the semester as possible. For more information or to request services, please contact Disability Support Services in person in Williams Hall, Suite 301, via phone at 610-758-4152, via email at indss@lehigh.edu, or online at https://studentaffairs.lehigh.edu/disabilities.
Lehigh University endorses The Principles of Our Equitable Community. We expect each member of this class to acknowledge and practice these Principles. Respect for each other and for differing viewpoints is a vital component of the learning environment inside and outside the classroom.
Lehigh University upholds The Principles of Our Equitable Community and is committed to providing an educational, working, co-curricular, social, and living environment for all students, staff, faculty, trustees, contract workers, and visitors that is free from harassment and discrimination on the basis of age, color, disability, gender identity or expression, genetic information, marital or familial status, national or ethnic origin, race, religion, sex, sexual orientation, or veteran status. Such harassment or discrimination is unacceptable behavior and will not be tolerated. The University strongly encourages (and, depending upon the circumstances, may require) students, faculty, staff or visitors who experience or witness harassment or discrimination, or have information about harassment or discrimination in University programs or activities, to immediately report such conduct. If you have questions about Lehigh’s Policy on Harassment and Non-Discrimination or need to report harassment or discrimination, contact the Equal Opportunity Compliance Coordinator (Alumni Memorial Building / 610.758.3535 / eocc@lehigh.edu)
To meet the challenge of teaching and learning during the COVID-19
pandemic, Lehigh instructors and students will be adopting new forms of
instruction and interaction; following new guidelines around classroom
behaviors; enhancing communications; and doing our best to be patient,
flexible, and accommodating with each other.
In remote synchronous meetings, students are expected to attend class
just as they would any other Lehigh class. Zoom classes work best when
all students come to class ready to participate and follow the
instructor’s guidelines regarding use of web-cameras. You may be asked
to turn your camera on during active learning sessions in Zoom. If you
have a strong preference not to do so, please contact me to let me know.
Students should respect the in-classroom privacy of their instructors
and fellow students by not taking screenshots or recording class
sessions.
If you are having trouble understanding lectures, textbook material, or assignments, and feel you are behind in understanding the course topics, please ask questions in class, see me after class and at my office hours, talk to your recitation section TA, and/or send email to me ASAP. Do not be embarrassed by feeling you are not grasping basic material. Everyone struggles with some aspect of every subject. Study groups with fellow students are often very helpful as well. College can be demanding whether you are a freshman or an upperclassman and time management is very important, and getting behind in a course makes time management more difficult. For these reasons, consider making use of the Academic Transitions, Center for Academic Success, Disability Support Services and other offices at Lehigh’s Division of Student Affairs. See https://studentaffairs.lehigh.edu/. In addition, your mental health should not be neglected. There are university counseling services that can help in managing stress and any life issues that you find overwhelming. In particular, Student Affairs has a Counseling & Psychological Services (UCPS) office with staff members who are trained and available to assist all students.