Hello Malihe Khoramdad

Have you used the regression model? For example, logistic regression model?

Hello Abolfazl

yes, I have used the logistic regression model, and I have Projected Individualized Probabilities of Developing Breast Cancer for Iranian Females

Calibration of weights is a technique for using the whole cohort in the analysis of a subsample. The name 'calibration' is unfortunate since it is used for so many unrelated techniques across statistics. Calibration is also likely to be valuable when self-reported data of exposure for the whole cohort is available.

You can use semiparametric and nonparametric methods to evaluate novel risk prediction markers through case-control designs. It can be used to evaluate a continuous risk prediction marker that accommodates case-control data. Small sample properties are investigated through simulation studies.

The predictiveness curve was proposed by Pepe and others and Huang and others to evaluate a risk prediction marker or model. It characterizes the performance of a risk prediction model by displaying the population distribution of risk endowed by the model. Arguments for displaying the risk distribution have also appeared recently in the clinical literature. A binary outcome D is considered here such as the presence of disease or occurrence of an event within some specified time period. We write D = 1 for cases, subjects with a bad outcome, and D = 0 for controls, subjects with a good outcome. Let Y be a vector of predictors of interest, and let Risk(Y) = P(D = 1|Y) be the risk calculated based on Y. The predictiveness curve displays the risk distribution through the population quantiles, R(v) vs v for v ∈ (0, 1), where R(v) is the vth quantile of Risk(Y). Equivalently, the inverse function, R−1(p)= P{Risk(Y) ≤ p}, is the proportion of the population with risks less than or equal to p, the cumulative distribution function. If pH corresponds to a high-risk threshold, the capacity of the risk model to identify high-risk subjects is 1 − R−1(pH). If pL is a low-risk threshold, R−1(pL) quantifies the capacity of the model to identify low-risk subjects. Better risk markers put more subjects into high and low-risk categories and fewer people into the intermediate range where treatment decisions are more difficult. In other words, a risk prediction model with larger variability in population quantiles, i.e. steeper predictiveness curve, has a better capacity to stratify risk.

Reference: Ying Huang and Margaret Sullivan Pepe. Assessing risk prediction models in case-control studies using semiparametric and nonparametric methods. Stat Med. 2010 Jun 15; 29(13): 1391–1410.doi: 10.1002/sim.3876