Regressions were utilised to predict variances in intention, planning and behaviour.
In turn, social norms independently accounted for more than twice the variance in vaccination planning than did intention, and vaccination planning accounted for more variance in vaccination uptake than did intention.
Greater adherence to social norms (β = 0.70), higher vaccination intention (β = 0.31) and higher anticipated regret (β = 0.19) were associated with more vaccination planning, together accounting for 67% of variance in vaccination planning.
Social norm (β = 0.70), anticipated regret (β = 0.19) and vaccination intention (β = 0.31) were positively associated with, and accounted for 70% of variance in vaccination planning, which, in turn subsequently predicted self-reported vaccination uptake (β = 0.36) accounting for 36% of variance in reported vaccination behaviour.
Freitas et al. (2009) examined hemispheric differences in the variability of joint configurations during upper extremity reaching tasks and found bilateral variance in motor planning and execution [ 6].
Care provider type accounted for 84.2% (adjusted R) of the variance in attitudes towards planned home birth.
The care provider variable was then entered into a linear regression model, with the 17 item PAPHB- m scale score as the outcome variable, to determine how much variance in attitudes towards planned home birth could be accounted for by type of care provider alone.
The power of any particular experimental design can be enhanced by increasing sample size, increasing acceptable Type I error risk, and, in analysis of variance, specifying planned means comparisons.
In such a situation, it was important to verify that our design did not unduly inflate variance estimates in the planned analyses.
Using an estimated variance in a power analysis of a planned intervention study will therefore more often lead to too "optimistic" (small) predictions of the necessary study size than to too "pessimistic".
