Logistic regression is a statistical
method for analyzing a dataset in which there are one or more
independent variables that determine an outcome. Logistic Regression
models are fit to an S-shared curve, as opposed to straight line of
linear regression, because logistic regression models are binary
classification models (they can only be used to distinguish between 2
different categories). Logistic regression is a common predictive model
in clinical research and other medical and healthcare uses and has a
wide range of applicability to such topics as variable selection,
patient classification and response prediction. In this Discussion, you
will run logistic regression analyses on NHANES data and consider how
the model and results can positively impact social change.
To Prepare
Create a research question using the National Health and Nutrition
Examination Survey (NHANES) dataset that can be answered by multiple
logistic regression. If necessary, you may need to search for the
variable in the NHANES database found here:
Centers for Disease Control and Prevention. (2018). Search variables. https://wwwn.cdc.gov/nchs/nhanes/Search/default.aspx
Links to an external site.
Remember
to select the proper release cycle (2015–2016). Then download the
appropriate file and merge with the file available for download from the
resources.
Review the complex samples file available in the Learning Resources.
Consider a complex samples multiple logistic regression model that answers your research question.
Estimate a complex samples multiple logistic regression model that answers your research question.
This is the assignment below
Post a response in which you:
Identify your research question, and explain the null hypothesis.
Interpret
the Exp (B) coefficients for the model, specifically explaining the
odds ratio and how you decided on the reference category for your
independent variables.
Run diagnostics for the regression model,
explaining what was run. Does the model meet all of the assumptions? Be
sure and comment on what assumptions were not met and the possible
implications. Is there any possible remedy for the assumption
violations?
Create and explain an interaction term from two variables as this will be one of your explanatory, independent variables.
Explain how the model and results can positively impact social change.
References:
You should support your work with evidence from scholarly resources
that are current (e.g., less than five years old). However, there may be
times when it is appropriate to cite seminal papers that helped shape
the field of public health. Properly cite/reference using APA 7th
edition.
