Related Experiment Video
Updated: Aug 7, 2026
15:17
Colorectal Cancer Cell Surface Protein Profiling Using an Antibody Microarray and Fluorescence Multiplexing
Published on: September 25, 2011
Testing for spatial correlation in nonstationary binary data, with application to aberrant crypt foci in colon
Tatiyana V Apanasovich1, Simon Sheather, Joanne R Lupton
1Department of Statistics, Texas A&M University College Station, Texas, USA. tanya@stat.tamu.edu
Biometrics
|February 19, 2004
Summary
This study investigated spatial correlations in aberrant crypt foci (ACF) to understand colon cancer development. Findings indicate localized damage from carcinogens and radiation, supporting the use of new statistical methods for analyzing such data.
Area of Science:
- Oncology
- Biostatistics
- Spatial Statistics
Background:
- Colon carcinogenesis involves the development of aberrant crypt foci (ACF), which are precursors to colon cancer.
- Understanding the spatial distribution of ACF can indicate localized damage from carcinogens and radiation.
Purpose of the Study:
- To develop and evaluate statistical methods for testing spatial correlation in binary data representing ACF presence.
- To determine if ACF locations are spatially correlated, suggesting localized damage in the colon.
Main Methods:
- Development of score-type statistical methods based on Matern and conditionally autoregressive (CAR) correlation models.
- Incorporation of nonstationarity and development of robust versions of the methods.
- Comparison with a generalization of Moran's test for continuous outcomes.
Main Results:
- Simulations showed the developed methods have potential for increased statistical power compared to existing tests.
- Application of the methods to experimental data revealed significant spatial correlation in ACF.
- The results indicate localized damage to the colon from carcinogen and radiation exposure.
Conclusions:
- The developed statistical methods are effective for detecting spatial correlation in ACF data.
- The findings support the hypothesis of localized colon damage due to combined carcinogen and radiation exposure.
- This research provides a robust framework for analyzing spatial patterns in precancerous lesions.
