To complete the Certificate, you must pass five modules. These modules and their associated
learning objectives are provided below. Please note that all work is completed using
R version 3.1.0 (or newer).
Module 1: Foundations in Statistical Analysis
- Understand and identify the different types of variables and the general format of
a data table.
- Understand and utilize the R programming environment.
- Get data into an R data frame.
- Work within the R environment to generate and manipulate datasets and variables.
- Use and create functions to execute combinations of calculations or transformations.
- Generate and interpret appropriate statistical graphics for different types of variables.
- Summarize data with descriptive statistics and frequency & contingency tables
- Apply concepts to a specified dataset.
|
Module 2: Statistical Methods I
- Develop Confidence Intervals for Parameters.
- Develop Confidence Intervals for Proportions.
- Determine an appropriate sample size to achieve a desired margin of error.
- Develop a hypothesis testing matrix.
- Understand the implications of Type 1 and Type 2 errors.
- Identify when and how to correctly execute a
- Hypothesis test:One Sample Proportion (z-test)
- Two Sample Proportion (z-test)
- One Sample Parameter (t-test)
- Two Sample Parameter (t-test)
- Paired Sample Parameter (t-test)
- Apply the concepts to a specified dataset
|
Module 3: Statistical Methods II
- Identify when and how to correctly perform one-way ANOVA
- Select an appropriate Post-Hoc test for significance
- Correctly test for normality and execute transformations where needed
- Understand, calculate and interpret Power calculations.
- Identify when and how to correctly utilize Non-
- Parametric Methods, including:Wilcoxon Rank
- Sum/Mann Whitney
- Wilcoxon Signed Rank
- Kruskal Wallis
- Execute a basic regression model.
Identify when and how to correctly execute a Chi-Square test.
- Apply the concepts to a specified dataset.
|
Module 4: Advanced Topics in Regression
- Understand the simple linear regression model, the usage and the assumption
- Understand the method of least squares, know the least square estimate (LSE) and the
properties of the fitted line
- Know the relationship between LSE and MLE under Normal model
- Know how to make and interpret
- inferences/predictions in Simple Regression
- Understand the difference between Correlation Model and regression model
- Apply graphic methods as well as formal statistical tests for studying the appropriateness
of a model
- Understand the need for joint estimation and simultaneous inferences
- Be aware of the additional remedial measures to deal with unequal error variances,
a high degree of multicollinearity, and influential observations.
- Apply the concepts to a specified dataset.
|
Module 5: Nonlinear Regression
- Introduction to categorical data analysis:
- Obtain and interpret relative risk, odds ratios, and confidence intervals for odds-ratios.
- Binary Logit Models I:
- Fit and interpret a simple and multiple logistic regression model.
- Assess model fitness & classification rates.
- Perform model diagnostics & selection.
- Survival Analysis
- Develop nonparametric estimates of the survival function.
- Fit and interpret Cox Proportional Hazards models.
- Assess model fitness
|
|
|