Table 3.
Mediation Analysis With The Analytic Sample Size, The Baseline Hazards Of Television Hours On
| Putative Mediator (Olkin & Finn P Value) |
N |
|---|---|
| Less trusting | 3136 |
| People are not fair | 2826 |
| Feel afraid in neighborhood*** | 8002 |
| People are not helpful | 2843 |
| Less general happiness** | 9309 |
| Less satisfied with hobbies** | 2151 |
| Less satisfied with friends* | 2156 |
| Unfair to bring a child into world*** | 4954 |
| Cannot control bad things in life** | 683 |
| Should not plan much in life*** | 683 |
| Less confidence in military*** | 3705 |
| Less confidence in organized religion*** | 3688 |
| Less confidence in the federal government | 3699 |
| Less confidence in the scientific community*** | 3561 |
| Government should not pay for medical care | 1940 |
| Government should do less | 1907 |
| Government should not help the poor | 1938 |
P <.001,
P <.01,
P <.05
This is the analytic sample of respondents who report good or excellent self- rated health only
Television viewing hazard ratio from the baseline regression model (television hours as the independent variable and mortality hazards as the dependent variable) but no mediator added
Television viewing coefficient in the baseline regression model (b above) with the mediator variable added
Coefficient of the mediator within model c above