| * p<.05. |
| 1 For an explanation of the Durbin-Watson statistic, see J. Johnston and J. Dinardo, Econometric Methods, New York: McGraw-Hill, 1996. |
| 2 AR(1) indicates that the model was estimated using least squares with the AR(1) process for correcting for first-order autocorrelation. For a general discussion of the problem of autocorrelation, and the method used to forecast in the presence of autocorrelation, see G. Judge, W. Hill, R. Griffiths, H. Lutkepohl, and T. Lee, The Theory and Practice of Econometrics, New York: John Wiley and Sons, 1985, pp. 315–318. |
| Where: |
| RELENRTCH = Log of the ratio of public elementary school enrollment to classroom teachers (i.e., student/teacher ratio) |
| RSCENRTCH = Log of the ratio of public secondary school enrollment to classroom teachers (i.e., student/teacher ratio) |
| RSALARY = Log of the average annual teacher salary relative to the overall economy wage in 2000 dollars |
| RSGRNTELENR = Log of the ratio of education revenue receipts from state sources per capita to public elementary school enrollment in 2000 dollars |
| RSGRNTSCENR = Log of the ratio of education revenue receipts from state sources per capita to public secondary school enrollment in 2000 dollars |
| RSCENRPU = Log of the ratio of enrollment in public secondary schools to the 11- to 18-year-old population |
| NOTE: R2 indicates the coefficient of determination. Rho measures the correlation between errors in time period t and time period t minus 1. Numbers in parentheses are t-statistics. |
| SOURCE: U.S. Department of Education, National Center for Education Statistics, Elementary and Secondary Teacher Model, 1968–2004. (This table was prepared December 2007.) |
(52 KB)
