Course Overview
This 2-day data science focused training course explores regression and time-series analysis. At the conclusion of this course, students should be able to do the following:
- Build single and multivariate regression models
- Assess statistical significance and validate models for explanatory power and bias
- Use time-series models to identify seasonality patterns and create forecasts for cyclical data
Schedule
Currently, there are no public classes scheduled. Please contact a Phoenix TS Training Consultant to discuss hosting a private class at 240-667-7757.
![[image]](https://phoenixts.com/wp-content/themes/phoenixts-com/assets/images/temp/image-9@2x.jpg)
Not seeing a good fit?
Let us know. Our team of instructional designers, curriculum developers, and subject matter experts can create a custom course for you.
Learn more about custom training
Course Outline
Introduction to Regression and Time-Series Analysis
- Commercial applications of regression and time-series analysis
- Linear relationships: slope, y-intercept, variable interactions
- Variance and standard deviation
- Covariance and correlation
- Normal distribution and bell curves
Evaluating Your Model
- Distribution of errors: Q-Q plot, heteroscedasticity
- Multivariate regression
- R- and adjusted R-
- p-values and the t-test
- F-test and F-distribution
Identifying the Most Important Variables
- Multicollinearity test
- Heteroscedasticity test
- Model selection: Akaike Information Criterion
- Polynomial regression
- Confidence intervals
Time-Series Analysis Seasonality
- Moving averages
- Seasonality detection: auto-correlation
- Seasonality: additive vs. multiplicative
- Decomposing seasonal data: trend, level and seasonality
- Multiplicative Holt-Winters exponential smoothing
- Forecasting seasonal trends
- LOcal regrESSion: LOESS
Regression and Time-Series Analysis Training FAQs
This course is intended for professionals who have a good working knowledge of R, work with time-series data and want to create forecasts for future trends, need to model cyclical or seasonal data such as sales, customer volumes, web traffic, employee behaviors, etc.;
need a good background in basic statistics and statistical modeling
or want to stand out as data scientists with advanced predictive modeling and time-series analysis skills .
Students should have taken the Introduction to Data Science, R, and Visualization course or should have the equivalent knowledge of data manipulation, cleaning and visualization.
