Compare models, identify dependent variables, interpret effects...

The table below gives the frequencies (freq) of reported happiness (happ) crossclassified by years of schooling (years) and number of siblings (sibs). Would the years and sibs be dependent? Justify your answer by providing a formal statistical test. Comparing m1, m2, and m1.1, would happ be a variable we should include in the model? Justify your answer by developing a suitable statistical test Based on the output of model m1.1, write down the expression of this model, and interpret the happ effect. Comparing models m3, m4, m5 and m6, which one is the best in your opinion? Support your choice by using a formal statistical test. Write down the expression of your best model among m3, m4, m5 and m6. Based on your best model, interpret how the years of schooling and number of siblings affect the happiness. Would your best model be sufficient for modeling the data? Justify your answer by a formal statistical test. Comment on the possible approaches for improving the modeling.