A Cluster-wise Linear Regression Model to Investigate the Effect of Demographical and Clinical Variables on the Average Depression Score

Depression is a prevalent illness in the world. Given the importance of mental disorders, many researchers have investigated the effects of different variables on average depression scores. In this study, we decided to investigate the effect of some explanatory variables on the average depression score.

The data were obtained from the second phase of the cohort of the Kerman Coronary Artery Diseases Risk Factors study (KERCADRS), which was performed in 2014-2018. We used the cluster-wise linear regression model to find more accurate relationships between depression scores and predictor variables.

The total number of the subjects in this study was 9811, out of whom 2144 were allocated to cluster 1, 4540 to cluster 2, and 3127 to cluster 3. The average depression score was 13.76 7.6 in cluster 1, 4.39 4.7 in cluster 2, and 10.83 6.7 in cluster 3. However, the average depression score for all the data was 8.5 7.2. In all the clusters, the average depression score of females was significantly greater than that of men (p-value<0.0001). In cluster 1, the age category of 35-54, in cluster 2, the age category of 55-80, and in cluster 3, the age category of 15-34 had a maximum average depression score.

we can name the three clusters to low ( cluster 2), medium ( cluster 3 ), and high (cluster 1) depression score with respect to age group with the maximum ADS in each cluster. that they are 55-80 years old, 15-34 years old and 35-54 years old in cluster 2 ( low), cluster 3 ( medium) and cluster 1( high) respectively.