Clustering in Northern Territory perinatal data for 2003-2005: implications for analysis and interpretation
Summary
Clustering in Australian perinatal data, particularly repeat births, impacts statistical analysis. Accounting for this clustering increases variance by 4-7%, crucial for accurate interpretation, especially for Aboriginal mothers.
Area of Science:
- Perinatal Epidemiology
- Biostatistics
- Public Health
Background:
- Clustering in perinatal data, such as repeat births and multiple pregnancies, can violate statistical independence assumptions.
- Routinely collected Australian perinatal data analysis requires understanding the extent and implications of this clustering.
- Few studies have specifically addressed repeat birth rates in Australian perinatal datasets.
Purpose of the Study:
- To examine the extent and implications of clustering in the Northern Territory Midwives Collection (NTMC) data from 2003-2005.
- To calculate design effects for birth weight, considering clustering due to multiple and repeat births.
- To inform accurate statistical analysis and interpretation of Australian perinatal data.
Main Methods:
- Analysis of 7,741 mothers and 8,707 babies from the NTMC (2003-2005).
- Identification of clusters: multiple pregnancies and repeat singleton births.
- Calculation of design effects for birth weight in Aboriginal and non-Aboriginal newborns.
Main Results:
- 46.1% of mothers were Aboriginal. Repeat singleton births were higher in Aboriginal mothers (13.2%) than non-Aboriginal mothers (8.7%).
- Multiple pregnancies occurred in 0.4% of Aboriginal and 1.2% of non-Aboriginal mothers.
- Design effects were 1.07 for Aboriginal and 1.04 for non-Aboriginal newborns, indicating a 4-7% increase in variance when accounting for clustering.
Conclusions:
- Clustering due to repeat and multiple births is present in Australian perinatal data.
- Statistical analysis of NTMC data requires accounting for clustering, especially for Aboriginal populations and when using multi-year data.
- Ignoring clustering can lead to underestimated variance, impacting the interpretation of perinatal health outcomes.
Related Concept Videos
01:20Cluster Sampling Method
11.0K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
11.0K
01:25Statistical Methods for Analyzing Epidemiological Data
1.3K
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
1.3K