Designing Big Data Healthcare Studies, Part Two

Course details

To perform accurate healthcare data analysis, you need to understand epidemiology and basic study design—covered in part one of this training series. But you also have to be able to conduct descriptive and regression analysis and defend your decisions regarding model selection, interpretation, and presentation. Part two of our series on Designing Big Data Healthcare Studies covers the logistics of planning and executing analysis on the analytic data set prepared in the previous course. Instructor Monika Wahi shows how to conduct the analysis and interpret the final model in context of your original hypothesis. Along the way, she teaches about best practices for code naming and arrangement, stepwise selection modeling, odd and prevalence ratios, and relative risk. Using these tutorials, you should be able to design great healthcare studies that take advantage of all that big data has to offer.

Learning objectives
Differentiate between modular code and spaghetti code and explain when to use each.
Explain the data-set transformation approach.
Assess the right time to remove identifiers from the data set.
Cite the considerations for categorical outcomes.
Recognize that with large data, even small differences are statistically significant.
Determine when using a stepwise model is appropriate.

Concepts

0. Introduction

01 - Welcome
02 - What you should know
03 - Using the exercise files

1. Logistics of Creating the Analytic Dataset

04 - Code arrangement
05 - Dataset transformation approach
06 - Applying qualification criteria
07 - Finalizing the analytic dataset

2. Conducting the Analysis

08 - Descriptive vs. regression analysis
09 - Considerations for categorical outcomes
10 - Structure of descriptive table - Table 1
11 - Descriptive table example
12 - Stepwise modeling to answer a hypothesis
13 - Establishing the working model - Part 1
14 - Establishing the working model - Part 2
15 - Documenting model metadata
16 - Selective stepwise modeling - Breaking the working model
17 - Considering model fit
18 - Selecting and interpreting the final model

3. Interpreting the Final Model

19 - Regression interpretation review
20 - Interpreting regression parameter estimates
21 - The 2x2 table revisited - Relative risk
22 - Final model presentation
23 - Talking about your analysis - Introduction and methods
24 - Talking about your analysis - Results and discussion

Conclusion

25 - Review of the course series
26 - Next steps