Model

What is the most correlated variable to listen to to increase happiness levels?

Author

Thomas Seoh

To answer the question of which factor correlates most with happiness, we have to see which of the variables are most associated with levels of happiness, by using a Bayesian Linear Regression Model. For this model, we are using this formula:

\[ \text{happiness} = \beta_{0} + \beta_{1} \cdot \text{social_support} + \beta_{2} \cdot \text{income} + \beta_{3} \cdot \text{health} + \beta_{4} \cdot \text{freedom} + \beta_{5} \cdot \text{generosity} + \beta_{6} \cdot \text{perceptions\_of\_corruption} \]

Characteristic

Beta

95% CI

1
social_support 2.6 2.3, 2.9
income 0.36 0.31, 0.40
health 0.03 0.02, 0.03
freedom 1.2 1.0, 1.4
generosity 0.52 0.37, 0.68
perceptions_of_corruption -0.74 -0.90, -0.58
1

CI = Credible Interval

We see that on average, higher levels of social support generally have higher levels of happiness. Note that the Perceptions of Corruptions should be reversed, as it is a scale from lowest to highest (best to worst).

 Family: gaussian 
  Links: mu = identity; sigma = identity 
Formula: happiness ~ social_support + income + health + freedom + generosity + perceptions_of_corruption 
   Data: df1 (Number of observations: 2103) 
  Draws: 4 chains, each with iter = 2000; warmup = 1000; thin = 1;
         total post-warmup draws = 4000

Regression Coefficients:
                          Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS
Intercept                    -1.99      0.16    -2.32    -1.66 1.00     4276
social_support                2.63      0.15     2.33     2.92 1.00     4299
income                        0.36      0.02     0.31     0.40 1.00     3418
health                        0.03      0.00     0.02     0.03 1.00     4972
freedom                       1.23      0.11     1.02     1.45 1.00     4088
generosity                    0.52      0.08     0.37     0.68 1.00     4760
perceptions_of_corruption    -0.74      0.08    -0.90    -0.58 1.00     4220
                          Tail_ESS
Intercept                     3569
social_support                2675
income                        2766
health                        3379
freedom                       3087
generosity                    3017
perceptions_of_corruption     2916

Further Distributional Parameters:
      Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
sigma     0.57      0.01     0.55     0.58 1.00     4445     2696

Draws were sampled using sampling(NUTS). For each parameter, Bulk_ESS
and Tail_ESS are effective sample size measures, and Rhat is the potential
scale reduction factor on split chains (at convergence, Rhat = 1).