First, our ability to adjust for important non-need determinants of utilization was limited.
Purging the effects of need factors on utilization of bias resulting from non-need determinants is critical to estimating need from utilization data[ 5, 18].
For Approach 2, we included multiple independent variables, in addition to age and sex, as indicators of need and non-need determinants of health care utilization [Additional file 1].
The first step, using individual-level data representative of the target population, estimates a model of the form: (1) where y i is the utilization for individual i, A ij is a vector of age-sex dummies, X ik is a vector of additional needs indicators, Z il is a vector of non-need determinants of utilization, and the R im are dummy variables for regions.
Similarly, the fourth factor of motivation (intrinsic needs) determinants also includes unrelated factors.
Ideally, the utilization model should include both need and non-need determinant of utilization in order to get unbiased estimates of the coefficients of the need variables [ 5, 9, 13].
The regression analysis showed that change in the number of unmet needs (determinant variable) was significantly associated with QoL at T1, a decrease in the number of unmet needs predicts higher QoL T1 scores.
Discussions were addressing the topics of: general aspects of quality in primary health care; possibilities to receive/provide PHC services based on both parties needs; determinant factors of accessibility to PHC services; patient centeredness.
It also enables a closer focus on socioeconomic disadvantage and health need as determinants of utilization.
Studies such as intervention and prognostic studies can be performed in cohort and case-control designs, but need more determinants and confounding variables in their analyses.
Thus, for the first term of (65) we only need the determinant |R ML |which is the product of the eigenvalues, and the MDL criterion becomes m ∑ i = 1 k log ( λ ̂ i ) + m ( n − k ) log 1 n − k ∑ i = k + 1 n λ ̂ i + κ 2 log ( m ) (71).
