Book contents
- Frontmatter
- Contents
- Preface
- 1 Introduction
- 2 Common uses of multivariable models
- 3 Outcome variables in multivariable analysis
- 4 Type of independent variables in multivariable analysis
- 5 Assumptions of multiple linear regression, multiple logistic regression, and proportional hazards analysis
- 6 Relationship of independent variables to one another
- 7 Setting up a multivariable analysis
- 8 Performing the analysis
- 9 Interpreting the analysis
- 10 Checking the assumptions of the analysis
- 11 Propensity scores
- 12 Correlated observations
- 13 Validation of models
- 14 Special topics
- 15 Publishing your study
- 16 Summary: Steps for constructing a multivariable model
- Index
9 - Interpreting the analysis
Published online by Cambridge University Press: 05 July 2011
- Frontmatter
- Contents
- Preface
- 1 Introduction
- 2 Common uses of multivariable models
- 3 Outcome variables in multivariable analysis
- 4 Type of independent variables in multivariable analysis
- 5 Assumptions of multiple linear regression, multiple logistic regression, and proportional hazards analysis
- 6 Relationship of independent variables to one another
- 7 Setting up a multivariable analysis
- 8 Performing the analysis
- 9 Interpreting the analysis
- 10 Checking the assumptions of the analysis
- 11 Propensity scores
- 12 Correlated observations
- 13 Validation of models
- 14 Special topics
- 15 Publishing your study
- 16 Summary: Steps for constructing a multivariable model
- Index
Summary
What information will the printout from my analysis provide?
All three multivariable techniques will provide two kinds of information: Information about the relationship of all independent variables taken together to the outcome, and information about the relationship of each of the independent variables to your outcome variable (with adjustment for all other independent variables in your analysis). Let's review these in turn.
How do I assess how well my model accounts for the outcome?
As you can see in Table 9.1, there are a variety of methods for assessing how well your model accounts for your outcome.
How do I know if my model (all my independent variables together) accounts for outcome better than I would expect by chance?
All three types of analyses provide a test of whether the independent variables, taken together, are more strongly associated with outcome than would be expected by chance. As is the case with all inferential statistics, you seek to disprove the null hypothesis. The null hypothesis in this case is that there is no relationship between the independent variables and the outcome. A significant relationship between the independent variables and the outcome means that you can reject the null hypothesis.
In multiple linear regression, the F test compares the success of the independent variables in accounting for the outcome compared to the success in accounting for the outcome based on assuming that everyone in the study had the mean value for the outcome.
- Type
- Chapter
- Information
- Multivariable AnalysisA Practical Guide for Clinicians, pp. 117 - 136Publisher: Cambridge University PressPrint publication year: 2006
- 1
- Cited by