A demonstration of modeling count data with an application to physical activity
2006

Modeling Count Data in Physical Activity Research

Sample size: 357 publication 10 minutes Evidence: moderate

Author Information

Author(s): Slymen Donald J, Ayala Guadalupe X, Arredondo Elva M, Elder John P

Primary Institution: San Diego State University

Hypothesis

How can we effectively analyze count data related to physical activity among Latina women?

Conclusion

The study found that the zero-inflated Poisson model provided the best fit for analyzing days of vigorous physical activity among Latina women.

Supporting Evidence

  • 82.4% of participants reported no days of vigorous physical activity.
  • Poor self-reported health was associated with no vigorous physical activity.
  • Less assimilation to Anglo culture was linked to lower levels of vigorous physical activity.

Takeaway

This study looked at how many days Latina women do vigorous exercise and found that many reported doing none. It showed a better way to analyze this kind of data.

Methodology

The study used five regression models to analyze predictors of vigorous physical activity among Latina women.

Potential Biases

Potential bias due to self-reported health and physical activity measures.

Limitations

The study did not include income as a predictor due to missing data for some participants.

Participant Demographics

Participants were Latina women aged 18 to 65, primarily married, with varying levels of education.

Statistical Information

P-Value

<0.0001

Confidence Interval

95% CI: 1.06, 2.08

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1742-5573-3-3

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication