Skip to main content

Advertisement

Table 6 Summary of the factors used to predict if the design change was likely to impact on the time series

From: Inclusion of mobile telephone numbers into an ongoing population health survey in New South Wales, Australia, using an overlapping dual-frame design: impact on the time series

Health indicators 50% or more different for non-landline frame Association between phone usage and indicator Sig diff 2011 and 2012 (dual- frame) Sig diff 2011 and 2012 (landline frame) Change in significance between sampling designs Change in direction between sampling designs
Five or more drinks of alcohol in a day     
More than two alcoholic drinks in a day     
Recommended fruit intake     
Recommended vegetable intake    
Current smoking  
Adequate physical activity       
Positive self-reported health status     
Current asthma       
Ever diagnosed with diabetes       
Overweight or obese