Lecture 1 - Introduction - Statistical Sciencekkl13/courses/sta102F13/lec/Lec1.pdf · 2013-08-26 · Lecture 1 - Introduction Statistics 102 Kenneth K. Lopiano August 26, 2013 adapted

Lecture 1 - Introduction

Statistics 102

Kenneth K. Lopiano

August 26, 2013

adapted from Professor Colin Rundel’s Lecture Slides

Statistics 102 (Kenneth K. Lopiano) Lecture 1 - Introduction August 26, 2013 1 / 27

Syllabus & Policies

1 Syllabus & PoliciesSyllabus Redux

2 Why (Bio)StatisticsScientific MethodHistorical ConnectionsSelected Biology Applications

3 Other ApplicationsCell Phone CommunitiesBasketballPolitics, Journalism and Sports

Statistics 102

Lecture 1 - Introduction Kenneth K. Lopiano

Syllabus & Policies Syllabus Redux

General Info

Professor: Dr. Kenneth Lopiano - [email protected] Chemistry 223E

Teaching Shirley Liao - [email protected]: Taylor Popisil - [email protected]

Lecture: Monday and Wednesday, 11:45 am - 1:00 pmOld Chem 116

Lab Sections: 01L - Tuesdays 1:25 - 2:40 pm02L - Tuesdays 3:05 - 4:20 pm03L - Tuesdays 4:40 - 5:55 pmOld Chem 101


mailto:[email protected]




Course goals & objectives

1 Recognize the importance of data collection, identify limitations in data collectionmethods, and determine how they affect the scope of inference.

2 Use statistical software to summarize data numerically and visually, and to performdata analysis.

3 Have a conceptual understanding of the unified nature of statistical inference.

4 Apply estimation and testing methods to analyze single variables or therelationship between two variables in order to understand natural phenomena andmake data-based decisions.

5 Model numerical response variables using a single explanatory variable or multipleexplanatory variables in order to investigate relationships between variables.

6 Interpret results correctly, effectively, and in context without relying on statisticaljargon.

7 Critique data-based claims and evaluate data-based decisions.

8 Complete an independent research project employing what you learn in this class.



Major topics

Introduction to data: Observational studies and non-causal inference,principles of experimental design and causal inference, exploratorydata analysis: description, summary and visualization.

Probability and distributions: The basics of probability and chanceprocesses, Bayesian perspective in statistical inference, the normaldistribution.

Framework for inference: Central Limit Theorem and samplingdistributions

Statistical inference for numerical variables

Statistical inference for categorical variables

Simple linear regression: Bivariate correlation and causality,introduction to modeling

Additional Topics: Multiple regression, logistic regression, survivalanalysis



Course materials

Textbook (Required) Statistics for the Life SciencesSamuels, Witmer, SchaffnerPearson, 4th Edition, 2012ISBN: 978-0-321-65280-5

Calculator (Optional) Four function calculator [one that cando square roots is enough but there is no limitationon the type of calculator you can use]



Webpage

http:// www.stat.duke.edu/∼kkl13/ courses/ sta102F13/

Announcements, slides, assignments, etc. will be posted on the website.


http://www.stat.duke.edu/~kkl13/courses/sta102F13/


Support

Office hours Mondays 2:00 - 4:00 pm or by appointment.

SECC TBAThe statistics education center has upper level statis-

tics students available to help you. For more informa-

tion and a schedule see http:// stat.duke.edu/ courses/

resources-students .

You are highly encouraged to stop by with any questions or commentsabout the class, or just to say hi and introduce yourself.

Most problem sets due on Wednesday - I strongly recommend at leastattempting all problems to make the most of office hours.


http://stat.duke.edu/courses/resources-students

http://stat.duke.edu/courses/resources-students


Grading

Homework - 15% Midterm 1 - 15%Labs - 10% Midterm 2 - 15%Quizzes - 5% Final - 25%Research Project - 15%

Grades will be curved at the end of the course after overall averageshave been calculated.

Average of 90-100 guaranteed A-.Average of 80-90 guaranteed B-.Average of 70-80 guaranteed C-.

The more evidence there is that the class has mastered the material,the more generous the curve will be.



Homework

Objective: Help you develop a more in-depth understanding of thematerial and help you prepare for exams and the project.

Questions from the textbook and outside sources.

Due at the beginning of class on the due date.

Show all your work to receive credit.

You are encouraged to work with others, but turn in your own work.

∼11 problem sets - lowest score will be dropped.

Excused absences do not excuse homework.



Labs

Objective: Give you hands on experience with data analysis using astatistical software and provide you with tools for the project.

http:// beta.rstudio.org

A gmail account is needed to register your Rstudio account, add yourgmail address using the quiz on Sakai.

∼11 labs - lowest lab score will be dropped.

Write ups due the following week - most can be completed in class.

You must attend the lab you are enrolled in, if you do not attend in agiven week you are eligible for at most 50% credit on that lab.

Online quiz in the first 10-15 mins of Lab (may only be taken duringin Old Chem 101).


http://beta.rstudio.org


Research Project

Objective: Give you independent applied research experience using realdata

Open ended semester long research project.

Choose a research question, find data, analyze it, write up yourresults.

More details in the near future.



Exams

Midterm 1: Wednesday, October 9th

Midterm 2: Wednesday, November 20th

Final: Wednesday, December 11th 2-5pm (Cumulative)

Exam dates cannot be changed. No make-up exams will be given. Ifyou cannot take the exams on these dates you should drop this class.

You may bring a calculator to the exams (no cell phones, iPods, etc.)and you may also bring one sheet of notes (“cheat sheet”). Thissheet must be no larger than 8 1

2 ” × 11” and must be prepared by you(no photocopies). You may use both sides of the sheet.



Email

I will regularly send announcements via email, make sure to checkyour email daily.

While email is the quickest way to reach me outside of class, notethat it is much more efficient to answer most questions in person.



Students with disabilities

Students with disabilities who believe they may need accommodations inthis class are encouraged to contact the Student Disability Access Officeat (919) 668-1267 as soon as possible to better ensure that suchaccommodations can be made.


http://www.access.duke.edu/students/requesting/index.php


Late Work Policy

For homework and lab write ups:

late but during class: -10 ptsafter class on due date: -20 ptsnext day: -30 ptslater than next day: -100 pts

For research project: -10 pts / day late

There will be no make-up quizzes.



Other Policies

The final exam must be taken at the stated time and you cannot passthis class if you do not take the final exam.

You must score at least 30 / 100 on the research project to pass thisclass.

Regrade requests must be made within one week of when theassignment is returned, and must be submitted in writing.



Academic Dishonesty

Any form of academic dishonesty will result in an immediate 0 on thegiven assignment and will be reported to the Office of Student Conduct.Additional penalties may also be assessed if deemed appropriate. If youhave any questions about whether something is or is not allowed, ask mebeforehand.

Some examples:

Use of disallowed materials (including any form of communicationwith classmates or looking at a classmate’s work) during exams.

Plagiarism of any kind.

Use of outside answer keys or solution manuals for the homework.


http://www.studentaffairs.duke.edu/conduct


Tips for success

1 Complete the reading before each lecture, and review again at the endof each chapter.

2 Be an active participant during lectures and labs.3 Ask questions - during class or office hours, or by email. Ask me, the

TAs, and your classmates.4 Do the problem sets - start early and make sure you attempt and

understand all questions.5 Start your project early and allow adequate time to complete the

necessary components.6 Give yourself plenty of time time to prepare a good cheat sheet for

exams. This requires going through the material and taking the timeto review the concepts that you’re not comfortable with.

7 Do not procrastinate - don’t let a week go by with unansweredquestions as it will just make the following week’s material even moredifficult to follow.


Why (Bio)Statistics




Statistics 102


Why (Bio)Statistics Scientific Method

Statistics and the Scientific Method

From Universe Today - http:// www.universetoday.com/ 74036/ what-are-the-steps-of-the-scientific-method/


http://www.universetoday.com/74036/what-are-the-steps-of-the-scientific-method/

Why (Bio)Statistics Historical Connections

R.A. Fisher

“I occasionally meet geneticists who ask me whether it is true that thegreat geneticist R.A. Fisher was also an important statistician.” - L.J.Savage (Annals of Statistics, 1976)

Source: http:// www.swlearning.com/ quant/ kohler/ stat/ biographical sketches/ Fisher 3.jpeg


http://www.swlearning.com/quant/kohler/stat/biographical_sketches/Fisher_3.jpeg

Why (Bio)Statistics Historical Connections

R.A. Fisher cont.

Biology:

Heterozygote advantage

Population genetics (Modernevolutionary synthesis)

Fisherian runaway selection

...

Statistics:

Analysis of Variance

Null hypothesis

Maximum Likelihood

F distribution

Fisher’s Exact test

Fisher Information

Randomization testing

...


Why (Bio)Statistics Selected Biology Applications

Next Gen Sequencing

44

Data workflow

Images are analysed closer to the instrument (on the instrument control PC), then base-calls are transferred to a secondary analysis server.

Real-Time Analysis

Images Intensities Base calls

Secondary Analysis

Alignments Visualisation etcserver

GA and PEM

http:// www.ebi.ac.uk/ industry/ Documents/ workshop-materials/ newsequence291009/ Basecalling-Klaus Maisinger.pdf


http://www.ebi.ac.uk/industry/Documents/workshop-materials/newsequence291009/Basecalling-Klaus_Maisinger.pdf


Crab Abundance Estimation



Grafted Tomato Plants



Knee Osteoarthritis


Other Applications




Statistics 102


Other Applications Cell Phone Communities

Communities in Dominican Republic

Caughlin et al. - Place-Based Attributes Predict Community Membershipin a Mobile Phone Communication Networkhttp:// dx.plos.org/ 10.1371/ journal.pone.0056057Statistics 102 (Kenneth K. Lopiano) Lecture 1 - Introduction August 26, 2013 25 / 27

http://dx.plos.org/10.1371/journal.pone.0056057

Other Applications Basketball

Basketball Analytics


Other Applications Politics, Journalism and Sports

The most famous statistician in the world ...

Nate Silver - Now at ESPN
