Between 1994 and 2000 a large scale radon survey was implemented in Greece with calibrated radon dosimeters based on CR-39 polymers. The dosimeters were exposed for a period of twelve-months. From the measured dwelling sample, 963 apartments were accompanied with fully filled questionnaires. The questionnaires were designed according to the international standards so as to account for factors that would potentially affect mean annual indoor radon concentrations. The available questionnaires were rechecked recently during 2012-14 with multivariate statistics in order to quantify possible inter-connections. Important factors were the following: i) area, ii) building level-floor, iii) ground type, iv) basement, v) building type, vi) construction year, vii) building walls contact, viii) wall materials, ix) floor materials. Several multivariate methods were employed in the analysis, namely (i) Linear Regression Analysis, (ii) One way or multiway ANOVA, (iii) General MANOVA, (iv) Stepwise Regression Analysis and (v) Principal Components Analysis. As most significant, it was found that approximately 0.1% of the examined dwellings were associated with outlier radon concentrations. Significant were the statistical correlations between indoor measured mean annual indoor radon concentrations and ”building level-floor” factor, as well as ”wall materials” factor. The findings of this work provided weak evidence regarding potential association of the factors ”building type”, ”construction year” and “floor materials” with mean annual radon concentration. Minor was the link with ”building walls contact” factor. It is important to note, that the employed statistical methods provided significant different results for the relative efficiency of the investigated factors.