Skip Navigation
small NCES header image
Projections of Education Statistics to 2018

NCES 2009-062
September 2009


Table A-22.  Estimated equations and model statistics for degrees conferred, by degree type and sex

Dependent variable               Equation1     R2 Breusch-Godfrey Serial Correlation LM test statistic2 Time period
                           
Associate's degrees, men DASSOCM =   1,839 + 94DUGFT2M + 68DUGFT2ML2     0.60 0.56* 1970–71 to
          (17.3)   (16.6)         2006–07
                           
Associate's degrees, women DLOGASSOCW =   # + 0.9DLOGUGFT2WS3 + .6MA(1)     0.83 2.66* 1970–71 to
          (15.6)   (8.8)         2006–07
                           
Bachelor's degrees, men DBACHM =   73.0 + 70DUGFT4M + 149DUGFT4ML2     0.68 0.46* 1970–71 to
          (24.0)   (22.2)         2006–07
                           
Bachelor's degrees, women DBACHW =   1940 + 80DUGFT4W + 134DUGFT4WL2     0.59 2.01* 1970–71 to
          (30.4)   (31.0)         2006–07
                           
Master's degrees, men PCHMASTM =   # + 0.5PCHGFTM + 0.6PCHGFTML1     0.66 1.77* 1970–71 to
          (3.4)   (4.1)         2006–07
                           
Master's degrees, women PCHMASTW =   # + 0.4PCHGFTW + 0.6AR(1)     0.60 1.01* 1970–71 to
          (22.2)   (3.8)         2006–07
                           
First-professional degrees,
Firmen
DFPROM =   89 + 161DFPFTML1 + 89DFPFTML2     0.61 3.18* 1971–72 to
          (5.0)   (2.9)         2006–07
                           
First-professional degrees,
Firwomen
DFPROW =   120 + 123DFPFTWL1 + 155DFPFTWL2     0.51 3.17* 1971–72 to
          (2.6)   (3.6)         2006–07
# Rounds to zero.
* p<.05.
1 AR(1) indicates that the model was estimated to account for first-order autocorrelation and MA(1) indicates that the model was estimated to incorporate moving average of the residual into model fit. For a general discussion of the problem of autocorrelation, and the method used to forecast in the presence of autocorrelation, see Judge, G., Hill, W., Griffiths, R., Lutkepohl, H., and Lee, T. (1985). The Theory and Practice of Econometrics. New York: John Wiley and Sons, pp. 315-318.
2 For an explanation of the Breusch-Godfrey Serial Correlation LM test statistic, see Greene, W. (2000). Econometric Analysis. New Jersey: Prentice-Hall.
Where:
LNASSOCM = Log of the ratio of associate's degrees awarded to men relative to the population of 18- to 24-year old men
LNASSOCW = Log of the ratio of associate's degrees awarded to woman relative to the population of 18- to 24-year old women
LNBACHM = Log of the ratio of bachelor's degrees awarded to men relative to the population of 18- to 24-year old men
LNBACHW = Log of the ratio of bachelor's degrees awarded to women relative to the population of 18- to 24-year old women
LNMASTM = Log of the ratio of master's degrees awarded to men relative to the population of 25- to 34-year old men
LNMASTW = Log of the ratio of master's degrees awarded to women relative to the population of 25- to 34-year old women
LNDOCM = Log of the ratio of doctor's degrees awarded to men relative to the population of 35- to 44-year old men
LNDOCW = Log of the ratio of doctor's degrees awarded to women relative to the population of 35- to 44-year old women
LNFPROM = Log of the ratio of first-professional degrees awarded to men relative to the population of 25- to 34-year old men
LNFPROW = Log of the ratio of first-professional degrees awarded to women relative to the population of 25- to 34-year old women
LNUG2ML2 = Log of the ratio of full-time male undergraduate enrollment in 2-year institutions to the male population of 18- to 24-year-olds, weighted over the last 2 years (where weights are .67 and .33 for descending lagged years), plus the similar log ratio for part-time male undergraduate enrollment in 2-year institutions.
LNUG2WL2 = Log of the ratio of full-time female undergraduate enrollment in 2-year institutions to the female population of 18- to 24-year-olds, weighted over the last 2 years (where weights are .67 and .33 for descending lagged years), plus the similar log ratio for part-time female undergraduate enrollment in 2-year institutions.
LNUG4FTML4 = Log of the ratio of full-time male undergraduate enrollment in 4-year institutions to the male population of 18- to 24-year-olds, weighted over the last 4 years (where weights are .4, .3, .2, and .1 for descending lagged years).
LNUG4FTWL4 = Log of the ratio of full-time female undergraduate enrollment in 4-year institutions to the female population of 18- to 24-year-olds, weighted over the last 4 years (where weights are .4, .3, .2, and .1 for descending lagged years).
LNGFTML2 = Log of the ratio of full-time male graduate enrollment to the male population of 25- to 34-year-olds, weighted over the last 2 years (where weights are .67 and .33 for descending lagged years).
LNGWL2 = Log of the ratio of full-time female graduate enrollment to the female population of 25- to 34-year-olds, weighted over the last 2 years (where weights are .67 and .33 for descending lagged years), plus the similar log ratio for part-time female graduate enrollment.
LNGML4 = Log of the ratio of full-time male graduate enrollment to the male population of 35- to 44-year-olds, weighted over the last 4 years (where weights are .4, .3., .2, and .1 for descending lagged years), plus the similar log ratio for part-time male graduate enrollment.
LNGFTWL4 = Log of the ratio of full-time female graduate enrollment to the female population of 35- to 44-year-olds, weighted over the last 4 years (where weights are .4, .3, .2, and .1 for descending lagged years).
LNFPML3 = Log of the ratio of full-time male first-professional enrollment to the male population of 25- to 34-year-olds, weighted over the last 3 years (where weights are .5, .33, and .17 for descending lagged years), plus the similar log ratio for part-time male first-professional enrollment.
LNFPFTWL3 = Log of the ratio of full-time female first-professional enrollment to the female population of 25- to 34-year-olds, weighted over the last 3 years (where weights are .5, .33, and .17 for descending lagged years).
NOTE: R2 is the coefficient of determination. Numbers in parentheses are t-statistics. There are no equations for doctor's degrees for men and women as projections of those items were obtained using double exponential smoothing.
SOURCE: U.S. Department of Education, National Center for Education Statistics, Degrees Conferred Model, 197071 through 200607. (This table was prepared December 2008.)

Would you like to help us improve our products and website by taking a short survey?

YES, I would like to take the survey

or

No Thanks

The survey consists of a few short questions and takes less than one minute to complete.