| Copyright © 2009. National Academy of Sciences. All rights reserved. Terms of Use and Privacy Statement |
Below are the first 10 and last 10 pages of uncorrected machine-read text (when available) of this chapter, followed by the top 30 algorithmically extracted key phrases from the chapter as a whole.
Intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text on the opening pages of each chapter.
Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
Do not use for reproduction, copying, pasting, or reading; exclusively for search engines.
OCR for page 290
APPENDIXES
290
Appendix 3-2
Estimated adjusted mean effects and differences for the probability that there are no female
applicantsa
Estimated mean difference
(lower 95%, upper 95% confidence limits)
Differences across effect levels
Biology – Chemistryb 0.22 (-0.08 , 0.51)
Biology – Mathematics 0.50 ( 0.01 , 0.99)
Biology – Electrical Engineering 0.23 (-0.12 , 0.57)
Biology – Physics 0.22 (-0.11 , 0.54)
Biology – Civil Engineering 0.13 (-0.07 , 0.34)
Tenured – Tenure-track 0.81 (0.71 , 0.92)
Private Institution – Public institution 0.66 (0.49 , 0.84)
Top 10 department – next 10 depts. 0.27 (0.10 , 0.44)
Next 10 depts – Remaining depts. 0.81 (0.59 , 1.03)
M – F Search Committee Chair 0.24 (-0.16 , 0.63)
SOURCE: Departmental Survey conducted by the Committee.
a
The sample size used to fit this model was X. b The effects fit were: (1) indicator variables for
discipline (Biology, Chemistry, Civil Engineering, Electrical Engineering, Mathematics, and
Physics, (2) indicator variables for Tenured, Tenure-track, (3) indicator variables for private
institution, public institution, (4) indicator variables for top ten departments, second ten
departments, and remainder, and (5) an indicator variable as to whether the committee chair was
female.
c
The estimated adjusted mean differences can be interpreted using Biology - Chemistry as an
example. For those individuals in Biology, there is an estimated probability of having no female
applicants given, or conditional on, the values for the remaining predictors in the logistic
regression model. There is an analogous set of estimated conditional probabilities for Chemistry,
again conditional on the predictors in the model. For each set of predictors, one can compute the
difference of the estimated probabilities, and then one can average these differences in estimated
probabilities over the estimated distribution of the predictors. The result is an estimated average
difference of probabilities.
PREPUBLICATION COPY