Table 7. Multilevel models with various social interactions, wave, and social interactions by wave predicting NA.
| No One | Partner | Family | Friends+ | |||||
|---|---|---|---|---|---|---|---|---|
| N observations | 15,188 | 10,283 | 15,188 | 15,188 | ||||
| N participants | 188 | 124 | 188 | 188 | ||||
| Estimate | SE | Estimate | SE | Estimate | SE | Estimate | SE | |
| Fixed effects | ||||||||
| Intercept | 21.10*** | 3.73 | 11.96* | 5.21 | 19.69*** | 3.70 | 18.87*** | 3.62 |
| Momentary social interaction | 0.35 | 0.51 | -1.64** | 0.62 | -1.50* | 0.68 | -3.79*** | 0.73 |
| Wave 2 | 3.02** | 1.07 | 2.05 | 1.32 | 1.92 | 1.09 | 2.18* | 1.09 |
| Wave 3 | 0.13 | 0.82 | -0.74 | 1.00 | -0.27 | 0.82 | -0.53 | 0.83 |
| Wave 4 | 0.31 | 0.87 | -0.98 | 1.05 | -0.39 | 0.86 | -0.65 | 0.86 |
| Social Interaction:wave 2 | -0.72 | 0.73 | 0.55 | 0.90 | 1.63 | 0.98 | 3.05* | 1.20 |
| Social Interaction:wave 3 | 0.18 | 0.62 | 0.22 | 0.74 | -0.67 | 0.85 | 2.18* | 0.98 |
| Social Interaction:wave 4 | -0.44 | 0.65 | 0.70 | 0.78 | -0.30 | 0.91 | 2.54* | 1.05 |
| Social interaction proportion | -7.55*** | 2.16 | -0.34 | 2.52 | 6.01* | 2.61 | -1.35 | 3.76 |
| Control Variables | ||||||||
| Age | -2.21 | 1.33 | -2.67 | 1.63 | -1.65 | 1.32 | -1.26 | 1.29 |
| Gender (male) | 0.18 | 2.05 | 0.86 | 2.24 | 0.40 | 2.05 | 0.95 | 2.00 |
| Race (white) | 1.80 | 2.63 | 4.73 | 3.58 | 1.64 | 2.62 | 2.13 | 2.57 |
| Living with spouse or partner | -6.34** | 2.42 | -- | -- | -4.29 | 2.36 | -5.47* | 2.32 |
| College | -0.59 | 2.20 | -1.28 | 2.60 | -0.92 | 2.19 | -0.68 | 2.15 |
| Working | -0.10 | 2.29 | -0.77 | 2.59 | -0.29 | 2.28 | 0.13 | 2.23 |
| Income 1 ($30,000–$59,999) | -2.09 | 2.87 | 0.13 | 3.87 | -1.36 | 2.85 | -1.39 | 2.79 |
| Income 2 ($60,000–$99,999) | -4.29 | 3.43 | 0.13 | 4.04 | -3.51 | 3.41 | -3.47 | 3.35 |
| Income 3 (> = $100,000) | -2.18 | 3.36 | 1.50 | 3.84 | -1.83 | 3.35 | -1.28 | 3.28 |
| Random effects | ||||||||
| Intercept Var: wave:person | 28.70 | 29.51 | 30.96 | 30.06 | ||||
| Slope Var: wave:person | 10.30 | 8.28 | 18.06 | 18.02 | ||||
| Intercept Var: person | 155.19 | 122.52 | 156.51 | 157.64 | ||||
| Slope Var: person | 2.39 | 3.40 | 1.25 | 0.85 | ||||
| Residual Var | 67.66 | 67.68 | 67.63 | 68.61 | ||||
| AIC | 109173.28 | 73840.76 | 109121.55 | 109189.28 | ||||
| BIC | 109363.99 | 74014.48 | 109312.26 | 109379.99 | ||||
| R2 conditional | 0.75 | 0.70 | 0.74 | 0.74 | ||||
| R2 marginal | 0.04 | 0.04 | 0.03 | 0.04 |
Note.
* p < .05
** p < .01
*** p < .001. Wald tests were conducted only on fixed effects. Var = variance.
+The solution of this model resulted in a singular covariance matrix, but the solution provided by the nlme package in R [47] was admissible and results were practically the same. Therefore, original results were presented.