Statistical Analysis of Bio-archaeological Data

         The bio-archeological dataset from Radovic et al. comprises cranial pathology measurements and cranial age assessment for 113 individuals from four Mesolithic-Neolithic sites in the Danube Gorges, Serbia. One of the characteristics the data quantify is the surface wear of left mandibular molars. The occlusal surface of each molar is divided into four quadrants. Each quadrant received a surface wear score, in which low values indicate no or little wear and high values indicate substantial tooth wear. We are interested in whether there is a difference in the mean tooth wear of the first quadrant of molar one and the first quadrant of molar three. The null hypothesis is that there is no difference in the mean tooth wear between the first quadrant of molar one and the first quadrant of molar three, and the alternative hypothesis is there is a difference in the mean tooth wear between the first quadrant of molar one and the first quadrant of molar three because first molars erupt much earlier than third molars and thus experience many more years of wear. The method of analysis chosen was a two-sample t-test. The t-value was 8.7324, meaning the difference between the group mean values is large relative to the amount of variation in the groups. The p-value is 1.042e-15, meaning there is a less than 5% chance of getting the observed result, or a more extreme result, if the null hypothesis is true, which means the data does not support the null hypothesis. In conclusion, there is a significant difference in the mean surface wear of the first quadrants of molars one and three.