Volume 8, Number 6—June 2002
Perspective
Clinical Epidemiology of Malaria in the Highlands of Western Kenya
Table 2
Deseasonalized child admissions at the three study hospitals, Kenyaa
Site | Data span | Constant | Slope | Change | t value | Significance | Adjusted r2 |
---|---|---|---|---|---|---|---|
Kilgoris | 1980–1999 (n=20) | 56.2 | 7.2 | 144 | 6.956 | p<0.001 | 0.165 |
Kisii | 1987–2000 (n=14) | 433.8 | 10.0 | 140 | 2.362 | p=0.019 | 0.027 |
Tabaka | 1981–2000 (n=20) | 166.4 | 7.6 | 152 | 6.980 | p<0.001 | 0.174 |
a The data span shows the range of complete years for which data are available (parenthesis indicate the number of observation years). The adjusted r2 (sometimes called the coefficient of determination) is goodness-of-fit measure of a linear regression model and varies between 0 and 1. The measure is the proportion of variation in the dependent variable (in this case, malaria admissions) explained by the regression model (in this case, the trend line). The t value is the value of a t-test used to determine if the adjusted r2 value is significantly different from 0. The result is shown in the significance column where p values <0.05 are significant.