Table 1.
Descriptive analysis of sample characteristics.
| Mean | SD | Missing cases | |
|---|---|---|---|
| Self-rated health | 2.921 | 1.24 | 831 (0.52%) |
| Depressive symptoms | 33.088 | 8.105 | 50342 (31.47%) |
| Educational attainment | 7.209 | 5.079 | 744 (0.47%) |
| Sleep time | 7.752 | 1.521 | 48563 (30.36%) |
| Overtime | 24.119 | 20.677 | 100598 (62.89%) |
| Leisure time | 10.971 | 10.399 | 48281 (30.18%) |
| Housework time | 2.196 | 2.009 | 97986 (61.25%) |
| Age | 47.628 | 16.633 | 11 (0.01%) |
| N | % | ||
| CPC member | 2374 (1.48%) | ||
| Yes | 13964 | 8.86 | |
| No | 143632 | 91.14 | |
| Marital status | 6430 (4.02%) | ||
| Yes | 125603 | 81.80 | |
| No | 27937 | 18.20 | |
| Gender | 329 (0.21%) | ||
| Yes | 79525 | 49.81 | |
| No | 80116 | 50.19 | |
| Residence area | 7155 (4.47%) | ||
| Urban | 72686 | 47.56 | |
| Rural | 80129 | 52.44 | |
| Year | 0 | ||
| 2012 | 33306 | 20.82 | |
| 2014 | 34883 | 21.81 | |
| 2016 | 34527 | 21.58 | |
| 2018 | 32633 | 20.40 | |
| 2020 | 24621 | 15.39 | |
| Income level | 7812 (4.88%) | ||
| Low-income group | 47932 | 31.50 | |
| Middle-income group | 48441 | 31.84 | |
| High-income group | 55785 | 36.66 | |
| Occupational type | 0 | ||
| Professional technicians and managers | 13689 | 8.56 | |
| Business service workers and office workers | 24090 | 15.06 | |
| Production workers | 25201 | 15.75 | |
| Farmers and the unemployed | 96990 | 60.63 | |
| Geographic location | 555 (0.35%) | ||
| Western China | 46908 | 29.43 | |
| Central China | 46151 | 28.95 | |
| Eastern China | 66356 | 41.62 | |
| Protein intake | 70828 (44.28%) | ||
| Yes | 75915 | 85.16 | |
| No | 13227 | 14.84 | |
| Exercise time | 6850 (4.28%) | ||
| Less than 0.25 times per week | 85373 | 55.76 | |
| More than 0.25 times but less than 1 time per week | 3505 | 2.29 | |
| 1-2 times per week | 9022 | 5.89 | |
| 3-4 times per week | 9961 | 6.51 | |
| 5 times per week -6 times | 2757 | 1.80 | |
| 7 times a week | 41270 | 26.95 | |
| More than 7 times a week | 1232 | 0.80 |
The values in parentheses represent the percentage of missing values among the 159,970 observations. Besides, the percentage of a specific category within a categorical variable refers to the ratio of that category among all valid responses for the variable, meaning that the calculation of percentages does not include missing values for the variable.