Syllabus

Title
5178 Research/Methods Seminar in Applied Statistics with Emphasis on Regression and Forecasting
Instructors
Univ.Prof. Johannes Ledolter, M.S.Ph.D.
Contact details
Type
PI SE
Weekly hours
2
Language of instruction
Englisch
Registration
02/13/15 to 04/15/15
Registration via LPIS
Notes to the course
Dates
Day Date Time Room
Tuesday 05/12/15 05:00 PM - 08:00 PM TC.4.14
Tuesday 05/19/15 05:00 PM - 08:00 PM TC.4.14
Tuesday 06/02/15 05:00 PM - 08:00 PM TC.4.14
Tuesday 06/09/15 05:00 PM - 08:00 PM TC.4.14
Contents
Regression analysis is important in applied research as it leads to statistical models that describe the relationships among variables. Regression allows us to validate established theories on available data. It can also guide the development of new theories, assess the impact on the response of changes in policy variables, and lead to predictions of future values of the response variable.

Forecasting plays a central role in business decision making. Accurate forecasts are needed when making decisions about investments, resource allocations, schedules and inventory levels. We give an overview of useful quantitative forecasting tools, such as exponential smoothing, autoregressive time series methods, and regression/time series models which incorporate into the forecasts any additional information such as sales promotions and price reductions.



Learning outcomes

This course will help you with the quantitative component of your dissertation. The objective of this course is to cover the basic ideas behind regression analysis and statistical forecast methods, assign readings that extend what we cover in the lectures, and provide one-on-one coaching on how to apply these methods in your dissertations research.

Teaching/learning method(s)

Detailed lecture notes and supplementary materials are sent to students prior to the course. Students are required to read needed background materials prior to the lectures. Basic concepts are explained during the lectures, and case studies and computer software for efficient data analysis is presented. Students practice the concepts on homework assignments and they complete a paper that ties this course to their anticipated dissertation topic.


Assessment

Attendance; homework; paper on a topic selected by the student (to be submitted by July 31, 2015).

Prerequisites for participation and waiting lists


Readings
1 Author: Abraham, B. and Ledolter, J.
Title: Introduction to Regression Modeling

Publisher: Duxbury Press
Year: 2006
Content relevant for class examination: No
Content relevant for diploma examination: No
Recommendation: Reference literature
Type: Book
2 Author: Draper N. and Smith, H.
Title: Applied Regression Analysis 

Publisher: John Wiley
Edition: 3rd
Year: 1998
Content relevant for class examination: No
Content relevant for diploma examination: No
Recommendation: Reference literature
Type: Book
3 Author: Weisberg S.
Title: Applied Linear Regression

Publisher: John Wiley
Edition: 3rd
Year: 2005
Content relevant for class examination: No
Content relevant for diploma examination: No
Recommendation: Reference literature
Type: Book
4 Author: Fox J.
Title: Applied Regression, Generalized Linear Models and Related Methods

Publisher: Sage
Edition: 2nd
Year: 2008
Content relevant for class examination: No
Content relevant for diploma examination: No
Recommendation: Reference literature
Type: Book
5 Author: Abraham B. and Ledolter J.
Title: Statistical Methods for Forecasting

Publisher: Wiley
Year: 2005
Content relevant for class examination: No
Content relevant for diploma examination: No
Recommendation: Reference literature
Type: Book
6 Author: Ledolter J.
Title: Time Series Forecasting

Publisher: Encyclopedia of Research Methods for Social Sciences (Lewis-Beck M., Bryman A., and Liao T. editors)
Remarks: p.397-402
Year: 2003
Content relevant for class examination: No
Content relevant for diploma examination: No
Recommendation: Reference literature
Type: Journal
7 Author: Montgomery D.C., Jennings C.L., and Kulahci M.
Title: Introduction to Time Series Analysis and Forecasting

Publisher: Wiley
Year: 2008
Content relevant for class examination: No
Content relevant for diploma examination: No
Recommendation: Reference literature
Type: Book
Recommended previous knowledge and skills

A solid introduction to statistics that covers discrete and continuous probability distributions and how to work with them, statistical inference including confidence intervals and standard tests of hypotheses, regression analysis, and a working knowledge of statistical software (such as Excel, Minitab, SAS, SPSS, or R).

Availability of lecturer(s)
johannes-ledolter@uiowa.edu
Other

Prior to the start of the course, instructor and participants will interact via e-mail about readings and prerequisites. Interested students should contact the instructor via e-mail prior to May 1.

Recommendations on Computer Software
  • R Statistical Computing Software (free software; quite extensive; requires writing of instructions, as compared to the “click/paste” listed packages below)
  • Minitab Statistical Software: Six-months license (US $ 29.99) available at http://www.minitab.com/education/semesterrental/ Official statistical software of Six Sigma. Good overall capabilities. Easy to use modules for statistical process control and design of experiments.
  • SPSS (supported through WU)


Last edited: 2014-10-28



Back