## 95-796, Statistics for IT Managers

### Course Description

This introductory course in data analysis and statistical inference requires no background in statistics. Its objective is to provide individuals who aspire to enter IT management positions with the basic statistical tools for analyzing and interpreting data. The course is divided into three distinct modules: descriptive statistics, statistical inference, and regression analysis. The emphasis of the classes on descriptive statistics is the calculation and interpretation of summary statistical measures for describing raw data. The sessions on statistical inference are designed to provide you with the background for executing and interpreting hypothesis tests and confidence intervals. The final component of the course focuses on regression analysis, a widely used statistical methodology. Throughout the course you will regularly analyze data relevant to IT management using the statistical software package Minitab.

### Course Objectives

Upon completion of this course, the student will be able to:

• Apply techniques for analyzing and interpreting data to real-world datasets relevant to IT management.
• Perform and interpret elementary statistical inferences (such as confidence intervals and hypothesis tests) both by hand and using the statistical software package Minitab.
• Analyze real data relating to online pricing and software cost estimation and describe the analysis results and conclusions.

### Class Schedule

Section A: Wednesdays, 9:00-11:50am, Hamburg Hall 1001
Section B: Mondays and Wednesdays, 3:30-4:50pm, Hamburg Hall 1502
Section C: Tuesdays, 5:30-8:20pm, Baker Hall 136A
Review sessions (all sections): Fridays, 3:30-4:50pm, Doherty Hall 2210

### Textbook

Statistics for Business and Economics, 11th Edition
(McClave, Benson, and Sincich)
*** It's fine to use the 9th or 10th Edition instead, but the section numbers may be slightly different! ***

### Lecture slides

Module I: Descriptive Statistics and Probability (pdf)
Module II: Hypothesis Testing and Inference (pdf)
Module III: Regression (pdf)

Three homework assignments: 30% (10% each)
Two mini-projects: 30% (15% each)
Final exam: 40%

The mini-projects will be done in 2-person teams and will involve the analysis of real data relating to online pricing and software cost estimation. In your 2-3 page mini-project reports you will describe the results of your analyses and your conclusions regarding the issues outlined in the assignment. Teams will be self-selected, and both team members will receive the same grade. The final exam will be held on Wednesday, October 17th from noon-1:20pm. Rooms will be: Section A: HBH 1001, Section B: HBH 1502, Section C: HBH 1000.

### Course Policies

Cheating Policy: We encourage discussion among teams about the mini-projects and among individual students on homework assignments. However, the project and that is submitted for grading must be the work of the 2-person team alone. Similarly, completed homework assignments must be your work alone. Specifically, discussion of results that are identical or nearly identical across projects will be regarded as cheating. Also, your answers on the final exam must reflect your work alone. Sanctions for cheating include lowering your grade including failing the course. In egregious instances, the instructors may recommend the termination of your enrollment at CMU.

Late Work Policy: You are expected to turn in all work on time (at the start of class on the due date). Because we understand that exceptional circumstances may arise, each student will be permitted to turn in one assignment (homework or mini-project) up to 48 hours late. Any other late assignments will not be accepted.

E-mail Questions Policy: To balance the workload fairly among the teaching assistants, and to ensure a reasonable response time for questions received via e-mail, each student has been assigned one TA as a "first contact". This is the person that you should e-mail first with any questions that you might have regarding the course. We will do our best to answer questions within 24 hours, or 48 hours on weekends. If you do not receive a response within this time, or if your first contact is unable to resolve your question, then you should feel free to e-mail another TA or the instructor.

### Assignments and Due Dates

Mini-project 1 due Wednesday 9/12 (Sections A & B), or Tuesday 9/11 (Section C)
Homework 1 due Wednesday 9/19 (Sections A & B), or Tuesday 9/18 (Section C)
Homework 2 due Wednesday 10/3 (Sections A & B), or Tuesday 10/2 (Section C)
Homework 3 due Wednesday 10/10 (Sections A & B), or Tuesday 10/9 (Section C)
Mini-project 2 due Monday 10/15 at 2:15pm (all sections)

### Module I: Descriptive Statistics and Probability (Chapters 1-4)

Lecture 1: Descriptive statistics
(Section A: Wed. 8/29; Section B: Mon. 8/27; Section C: Tues. 8/28)

Course overview
What is statistics (1.1-1.3)
Types of data (1.5)
Random sampling (1.6)
Histograms (2.2)
Measures of central tendency (2.4)
Measures of variability (2.5-2.6)
Box plots (2.8)
Using Minitab for descriptive statistics

Lecture 2: Probability
(Sections A/B: Wed. 8/29; Section C: Tues. 8/28)

Basic probability (3.1-3.4)
Conditional probability (3.5-3.6)
Bayes' Theorem (3.8)
Discrete random variables (4.1-4.3)

Review 1
(All sections: Fri. 8/31)

Minitab and example problems.

Lecture 3: Random variables
(Sections A/B: Wed. 9/5; Section C: Tues. 9/4)

(Tuesday class will meet from 5:30-6:50pm; Wednesday morning class will meet from 9:00-10:30am)
Continuous random variables (4.5)
The Uniform distribution (4.9)
The Normal distribution (4.6)

Review 2
(All sections: Fri. 9/7)

Minitab, example problems, and questions on mini-project 1.

Lecture 4: Normal distributions and sampling
(Section A: Wed. 9/12; Section B: Mon. 9/10, Section C: Tues. 9/11)

The Normal distribution, continued (4.6)
Sampling distributions (4.10)
Central Limit Theorem (4.11)
Using Minitab for random variables and sampling

### Module II: Hypothesis Testing and Inference (Chapters 5-7)

Lecture 5: Confidence intervals
(Sections A/B: Wed. 9/12; Section C: Tues. 9/11)

Large-sample confidence intervals for the mean (5.2)
Small-sample confidence intervals for the mean (5.3)
Large-sample confidence intervals for the population proportion (5.4)
Determining the sample size (5.5)
Using Minitab for confidence intervals

Review 3
(All sections: Fri. 9/14)

Minitab, example problems, and questions on HW 1.

Lecture 6: Hypothesis testing
(Section A: Wed. 9/19; Section B: Mon. 9/17, Section C: Tues. 9/18)

Introduction to hypothesis testing (6.1-6.2)
Large-sample hypothesis tests for the mean (6.3)
Small-sample hypothesis tests for the mean (6.5)
Large-sample hypothesis tests for the population proportion (6.6)

Lecture 7: More hypothesis testing
(Sections A/B: Wed. 9/19; Section C: Tues. 9/18)

Type I and Type II errors (6.1)
p-values (6.4)
Using Minitab for 1-sample hypothesis testing

Review 4
(All sections: Fri. 9/21)

Minitab, example problems, and questions on HW 2.

Lecture 8: Comparing two populations
(Section A: Wed. 9/26; Section B: Mon. 9/24, Section C: Tues. 9/25)

Comparing two population means (7.2)
Comparing two population proportions (7.4)
Using Minitab for 2-sample hypothesis testing

Lecture 9: Comparing two populations, continued
(Sections A/B: Wed. 9/26; Section C: Tues. 9/25)

Comparing two population means using paired differences (7.3)
Using Minitab for paired differences

Review 5
(All sections: Fri. 9/28)

Minitab, example problems, and questions on HW 2.

### Module III: Regression (Chapters 10-11)

Lecture 10: Simple regression
(Section A: Wed. 10/3; Section B: Mon. 10/1, Section C: Tues. 10/2)

Linear models (10.1)
Least squares linear regression (10.2)
Estimating the error of the model (10.3)
Making inferences using the model (10.4)

Lecture 11: More simple regression
(Sections A/B: Wed. 10/3; Section C: Tues. 10/2)

Coefficients of correlation and determination (10.5)
Using the model for estimation and prediction (10.6)
Using Minitab for simple regression

Review 6
(All sections: Fri. 10/5)

Minitab, example problems, and questions on HW 3.

Lecture 12: Multiple regression
(Section A: Wed. 10/10; Section B: Mon. 10/8, Section C: Tues. 10/9)

Multivariate linear models (11.1)
Least squares linear regression (11.2)
Estimating the error of the model (11.2)
Multiple coefficient of determination (11.3)
Making inferences using the model (11.3)

Lecture 13: More multiple regression
(Sections A/B: Wed. 10/10; Section C: Tues. 10/9)

Using the model for estimation and prediction (11.4)
Advanced topics in model building (11.5-11.7)
Using Minitab for multiple regression

Review 7
(All sections: Fri. 10/12)

Review for final exam, and questions on mini-project 2.

Final exam: Wednesday October 17, noon-1:20pm.