Data Analysis in Engineering II

Universidad del Norte

Course Description

  • Course Name

    Data Analysis in Engineering II

  • Host University

    Universidad del Norte

  • Location

    Barranquilla, Colombia

  • Area of Study

    Business, Engineering Science, Industrial Engineering

  • Language Level

    Taught In English

    Hours & Credits

  • Contact Hours

    64
  • Recommended U.S. Semester Credits
    4
  • Recommended U.S. Quarter Units
    6
  • Overview

    Description of Data Analysis for Engineering II

    This course continues to strengthen the study of data analysis tools and methods, essential for the description, control and forecasting of business processes (for the production of both physical goods and services). The aim of this second course is to cover topics such as: non-parametric models, advanced linear regression models, stochastic time series and discrete choice modeling.

    Course Learning Outcomes

    After completing the course, the student must be able to:
    I.    Recognize whether is possible or not to apply non-parametric methods for hypothesis testing for mean.
    II.    Use the appropriate non parametric method for hypothesis testing and construction of confidence intervals.
    III.    Find a linear regression model that accurately describes the relationship between a set of variables.
    IV.   Validate the assumptions for linear regression models and make the required adjustments if applicable.
    V.    Find homoscedastic time series models using the appropriate procedure.
    VI.   Select from several lineal regression models, the one that best describes and predicts the situation under study.
    VII.   Select from several time series models, the one that best describes and predicts the situation under study.
    VIII.  Interpret the results issued by the model.
    IX.    Use statistical software for data analysis.

    Topics Covered:

    • Non-parametrical models (Sign test, Wilcoxon signed-rank test and Wilcoxon Rank Sum Test, Kruskal Wallis Test).
    • Advanced Linear Regression Models (Multiple Linear regression Models, Non- linear regression models, Validating assumptions, Adjustments to avoid violating assumptions, logistics regression model).
    • Stochastic time Series (Stationary and non-stationary time series, Autocorrelation Function, Autoregressive models, Moving Average Models, ARMA and ARIMA models, Box-Jenkins Methodology).