This course alone will not be enough to prepare you to teach AP Statistics. From an MET draft document: "it is clear that extensive additional preparation in statistics is required to teach AP Statistics. Several graduate courses in statistics are desirable (chosen in individual consultation with faculty in a graduate statistics program). The minimum preparation would be a good lower-level introductory statistics course, based on the sort of textbooks mentioned above, followed by either a second undergraduate statistics course or a graduate statistics course designed for teachers (see the MET Professional Development website for details about such a course)." http://cbmsweb.org/MET_Document/index.htm
MATH 419W - Introduction to Stochastic Mathematical Modeling (Gen Ed Area I, W--writing intensive) ECON 415 - Introduction to Econometrics STAT 370 - Probability (prerequisite is Calc 2) STAT 460/576 Applied Survey Sampling STAT 461/575 Linear Regression Analysis STAT 462/572 Design and Analysis of Experiments STAT 468 - Introduction to Biostatistics STAT 469 - Introduction to Categorical Data Analysis STAT 474W/574 - Applied Statistics (Gen Ed Area I, W) STAT 571 Mathematical Statistics I: Probability Theory STAT 573 Statistical Data Analysis STAT 577 Applied Multivariate Statistics STAT 578 Nonparametric Statistics.
Tue/Thu 2:00-3:15 Stat 360-1, Pray-Harrold 304, CRN 23138
Stat 360-01 | Prof. Andrew Ross; Tue/Thu 2:00-3:15, Pray-H 304 | CRN 23138 | ||||||||
---|---|---|---|---|---|---|---|---|---|---|
Class# | 2020 | day | unit | Topic | Required Additional Reading | HW Assigned | HW Due | Bonus Tech Material after class | R goals | Data Set |
1 | 1/7 | Tue | 1 | Intro; randomization example; car-insurance advertising; population vs sample, types of data | m360-ch01-data-types.docx | Ch 1 preview | * = deviation from usual 7-day delay | text-to-columns | importing files | Lock5stat Employed ACS (Income by Gender) ; car-insurance activity; TN STAR; Amer.Community Survey; HELPrct; CS data set? |
2 | 1/9 | Thu | 1;2 | Discrete vs Continuous; PivotTables, Bar charts, Dotplots; Ch 2 Bias | Ch 1 | Pivot Tables | Pivot Table in R | survey data for pivoting; CS-sorting, randomizing order vs memory leak | ||
3 | 1/14 | Tue | 2 | Random vs Stratified Samples, etc; Random Rectangles activity | m360-ch02.2-2.3-powerpoint.pptx | Ch 2a; 2b | Ch 1* | left/mid/right and =DATE | handling dates | Random Rectangle data or graphs; TN STAR, what was its design? |
4 | 1/16 | Thu | 3 | Graphical Methods for Describing Data | Ch 3 | Ch 2a* | Kernel Density Estimates (KDEs) | Histogram and KDE in R | histogram data; processing times of sorting same data repeatedly; HELPrct drinks/day, previousrehabs; looks&personality scatter; logistic scatter? | |
5 | 1/21 | Tue | 4 | Center, Variability, Boxplots, Empirical Rule, z-scores, Percentiles & Plots | m360-ch04-notes.docx | Ch 4a and 4b | Ch 2b | Marked Scatterplots | Marked Scatterplots | income; also, above Histogram data |
6 | 1/23 | Thu | 5 | Correlation; Regression | Ch 5a | Ch 3 | plot the percentile curve; dotplot-histogram-crf-etc | fit a linear model; see coeff,r,R^2 | existing spreadsheets | |
7 | 1/28 | Tue | 5 | Assessing fit; Nonlinear Relationships and Transformations | 5b preview | Ch 4a and 4b | vlookup | plot residuals; fit log-transformed models | doctor lifetime estimates (artificial&real) | |
8 | 1/30 | Thu | 5 | 5 wrapup | Ch 5b | Ch 5a | Solver for nonlinear regression | fit polynomials; nonlinear fits; matrix of scatterplots | risk estimation survey data | |
9 | 2/4 | Tue | 6 | Definition and Properties of Prob; Conditional Probability; independence, PIE, Bayes, Prob via Simulation | "m360-ch06a-powerpoint.pptx | |||||
and | ||||||||||
m360-ch06-bayes-table-handout.docx" | Ch 6 | ambulance travel distance simulation | ambulance travel simulation in R | |||||||
10 | 2/6 | Thu | 7 | Random Variables; Discrete and Continuous Distributions; Mean and StdDev; linear functions and sums | m360-ch07a-notes.docx | Ch 7a | Ch 5b | sumproduct | table joins: merge, dplyr, data.table | "rainy days/year; tornadoes/year; true binomial example data? |
shifting&scaling, E[nonlinear], adding blood bank demand" | ||||||||||
11 | 2/11 | Tue | 7 | Binomial, Geometric; Normal; Checking and Transformations for Normality; Binom~Normal; QQ | m360-ch07b-notes.docx | Ch 7b | Ch 6 | dotplot-histogram-crf-qq | pbinom, rbinom, pnorm, qnorm, rnorm; Q-Q | income and Log(income) |
12 | 2/13 | Thu | 8 | Statistics and Sampling Variability; Sampling Distribution of a Mean | example Proposals and Reports | 8 preview | Ch 7a | What-If Data Tables, 1-dim | randomization with replacement | Billionaire incomes and ages |
13 | 2/18 | Tue | 8 | Central Limit Theorem; Sampling Distribution of a Proportion | Ch 8 | Ch 7b | What-If Data Tables, 2-dim | for-loops | ||
14 | 2/20 | Thu | 9 | Point Estimation; Confidence Interval for a Proportion | Ch 9a | Ch 8 | conditional formatting | North Carolina birth records | ||
2/25 | Tue | break week | ||||||||
2/27 | Thu | break week | ||||||||
15 | 3/3 | Tue | 9 | Confidence Interval for a Mean (incl. t-distrib) | Ch 9b | sparklines | CIs for groups, plotting | estimators-dotplot-histo-crf-qq ; baseball win/loss by game, or weather precip/not; fake data showing trend or dependence; pivot&errorbars | ||
16 | 3/5 | Thu | midterm | midterm | ||||||
17 | 3/10 | Tue | 10 | Hypotheses and Test Procedures; Errors in Hypothesis Testing; Proportion | m360-ch10a-powerpoint.pptx | Ch 10a | Ch 9a | parallel axis plots | parallel axis plots | Detroit Tigers data |
18 | 3/12 | Thu | 10 | Hypothesis Tests for Population Mean; Power and Probability of Type II error | Ch 10b; midterm corrections | Ch 9b | countif, sumif, averageif | generating artificial data | ||
19 | 3/17 | Tue | 11 | 2-sample t-test for means (indep); 2-sample t-test for means (paired); skipping 2-proportions | Ch 11 | Ch 10a | generating random numbers | t.test (low-priority) | don't choose tail after; don't test max or min to see if "significant" or outlier. | |
20 | 3/19 | Thu | 12 | Categorical Association part a | handout | Ch 12a; Proposal | Ch 10b | Pivot Tables | contingency table from data; mosaic plot | survey like in univ101 |
21 | 3/24 | Tue | 12 | Categorical Association part b | handout | Ch 12b | Ch 11; midterm corrections | chisq.test | ||
22 | 3/26 | Thu | 12 | Categorical Association part c | handout | Ch 12c | Ch 12a; Proposal | Pasting into Word/ ppt: live or dead copies? | Rmarkdown? | Entering freshmen by gender (? race?) vs graduating seniors, perhaps just CS or STEM or MathEd |
23 | 3/31 | Tue | 13 | Linear Regression and Correlation: Inferential Methods | m360-ch13-notes.docx | Ch 13 | Ch 12b | Excel Regression Tool | CI on slope | PA school district data |
24 | 4/2 | Thu | Multiple Testing; Regression to the Mean; Covariance; PDF/CDF methods | m360-ch99-calculus-supplement | Ch 12c | LiveRegression | Detroit 911 or Bank call center; WiFi; earthquake; shootings; emich webserver | |||
25 | 4/7 | Tue | PDF/CDF-based methods; Poisson Processes | ch99calc or alternate | Ch 13 | What-If Goal Seek | dexp, pexp, dpareto, ppareto, etc | |||
26 | 4/9 | Thu | PDF/CDF, Poisson; presentation tips | example Presentations | ch999datafest | Project Report | SQL | |||
27 | 4/14 | Tue | present. | Presentations | Project Presentation and ch99calc or alternate | |||||
28 | 4/16 | Thu | present. | Presentations | ||||||
4/21 | Tue | 1:30-3:00 final exam, HALF-HOUR EARLY! | ch999datafest |
3 credit hours.
Class meetings will be mostly interactive lectures, with some time to work on problems in class, but hardly ever time to go over problems from the homework; that is best done in office hours or by email before the HW is due.
I expect that you will work on Stat 360 for 6 to 10 hours per week outside of class.Mon/Wed: 11:00-12:00 grant meeting (Wednesdays) 1:00- 2:00 office hours 2:00- 3:15 Math 319, room TBA 3:15- 4:30 office hours Tue/Thu: 10:30-11:00 office hours 11:00-12:15 Math 110, Pray-Harrold 406 1:00- 2:00 office hours 2:00- 3:15 Stat 360, Pray-Harrold 304 3:15- 4:30 office hours Fri: No official office hours, but I'm often on campus. E-mail me to make an appointment, or drop by. 11:00-12:00 department colloquium (once a month) 12:30-2:30 department meeting (once a month) 2:30-3:30 research meeting
I am also happy to make appointments if you cannot come to the general office hours. Please send me e-mail to arrange an appointment. However, I am not available when I am teaching other classes (see above).
The Mathematics Student Services Center (or "Math Lab") is also here to help you, in Pray-Harrold 411 Their hours are posted here. Please give them a call at 734-487-0983 or just drop by.
Another resource on campus is the Holman Success Center, formerly the Holman Learning Center.Some assignments in this course will be in the form of papers, which I want to be well written. Please consult with The Writing Center for help in tuning up your writing.
I am a very applied mathematician. Applied, applied, applied. Not pure. Impure. I try to focus on real-world problems, rather than artificial drill problems (though I do recognize the need for some drill). My classes spend much more time on formulating problems (going from the real world to math notation and back) than on proving theorems. If you want the theoretical basis for anything we are discussing, please ask!
My general math interests are in Industrial Engineering and Operations Research (IEOR). In particular, I do research in applied probability and queueing theory, the mathematics of predicting how long it takes to wait in line for service. You can learn more about this in Math 319 and 419W when I teach them. I also enjoy teaching about cost-minimizing/profit-maximizing methods called Non-Linear Programming (NLP) in Math 560, Optimization Theory.
Textbook: Introduction to Statistics & Data Analysis, 4th edition, by Peck, Olsen, and Devore amazon link. We do actually use the textbook, fairly heavily in fact. For Winter 2020 we will still use the 4th edition; if it's hard to find a cheap (under $40) used copy online, email me ASAP.
A lot of our work will be done on computers, usually in Excel or a similar spreadsheet. If you had been waiting for a good reason to buy a laptop, this is it. Spreadsheets other than Excel (such as OpenOffice/LibreOffice, Google Docs, etc.) work reasonably well for most things in the class, but some things really don't work well without name-brand Excel. Fortunately, it's available free to EMU students (as of Fall 2016). Email me to ask for details.
In the long run, most math/stats/compsci/data-science people should learn either Python or R or both. If we have time this semester, we will try to introduce some Python (via Notebooks) or R/Rstudio and Rmarkdown. These might be particularly helpful for projects. The good news is that these programs are all free!
Some course files are posted on my home page, but most files (homeworks, homework solution keys, some handouts) are only in Canvas
We will use on-line homework submission and gradebook via EMU Canvas to keep track of grades. You are expected to keep an eye on your scores using the system, and get extra help if your scores indicate the need.
The department's list of Student Learning Outcomes for this course are as follows: Students will be able to
Regular attendance is strongly recommended. There will be material presented in class that is not in the textbook, yet will be very useful. Similarly, there are things in the textbook that are might not be covered in class, but are still very useful. If you must miss a class, arrange to get a copy of the notes from someone, and arrange for someone to ask your questions for you. If you are stuck on occasion without your usual child care, you may bring your child to class, and need not even get advanced permission (this is my personal policy--I don't know if EMU has a policy). Please be considerate to your classmates if your child becomes disruptive.
My lectures and discussions mostly use the document camera, along with demonstrations in Excel and other mathematical software. I do not usually have PowerPoint-like presentations, and thus cannot hand out copies of slides.
Homework will be assigned about twice per week, usually 2 assignments per chapter. All homework should be submitted via the Canvas dropbox. The policy is: if it isn't in Canvas, it doesn't exist for grading purposes. Any assignments emailed to me will be treated as drafts, and I will try to respond to them with helpful advice. Most homework will be graded simply on completion, and solution keys released (in Canvas) the day after the homework is due. It is your responsibility to check your answers against the solution keys and ask questions about things you do not yet understand (email about that is welcome!).
I am open to doing contract honors for this class for students in the Honors College. Please contact me if you are interested in doing so.
There will be a midterm exam and a final exam. Quizzes might also occur, announced or not, during the semester.
I tend to print most handouts and exams in a small font to save paper. If you would like a larger font, or a dyslexia-friendly font, please let me know and I will be happy to work with you. I am also happy to work with other learning-difference needs.You will do a project where you create a question, decide how to study it, design a data collection method, collect data, and analyze it. You will write a project proposal so I can be sure you are on the right track, and a final report, which is usually about 5 to 10 pages long (could be as short as 3 pages, if aiming to submit it to a national competition). The grade breakdown for the project is roughly:
On average, students should spend a total of about 30 minutes in office hours discussing the project. Plan for this in advance! Teams of 2 are allowed/encouraged, but no team bigger than 2 is allowed (with rare pre-approved exceptions).
There is no systematic grade-dropping method like "lowest 2 scores will be dropped". In the unfortunate event of a need, the appropriate grade or grades might (at the instructor's discretion) be dropped entirely, rather than giving a make-up. You are highly encouraged to still complete the relevant assignments that were dropped, and consult with me during office hours to ensure you know the material. If a student falls hopelessly behind in the homeworks (aside from the project), they may request a grand make-up assignment (which might be done at home or in the math testing room, at the instructor's discretion). This request might or might not be granted, at the instructor's discretion. Note that the students who relied on this option recently did very poorly on the grand make-up.
Your final score will be computed as follows:0 to <52: F 52 to <56: D- 56 to <60: D 60 to <64: D+ 64 to <68: C- 68 to <72: C 72 to <76: C+ 76 to <80: B- 80 to <84: B 84 to <88: B+ 88 to <92: A- 92 to infinity: Athough if absolutely necessary, a curve might be applied.