Statistics of Graduate Record Examination

Introduction

These statistics are based on scores on this test as reported by candidates taking I.Q. tests from I.Q. Tests for the High Range.

Scores on Graduate Record Examination as of 5 September 2024

• n: 64
• Median: 1495.0
• Quartile deviation: 52.5
• Range: 491
• Maximum possible: 1640
• Minimum possible: 400
• Male median: 1490.0 (n = 58)
• Female median: 1540.0 (n = 5)
• Proportion of males among candidates: 0.906
• Hardness: 0.14
• Resolution: 0.47 (assuming 10 G.R.E. points as the unit)

Scores by males

n = 58

Scores by females

n = 5

Correlation of Graduate Record Examination with other mental ability tests

Weighted average of correlations: 0.410 (N = 128)

Estimated g factor loading: 0.64

Ranking in above table is based on the unrounded correlations. All available data is present in this table, no tests are left out except for those with less than 4 score pairs. All known pairs are used, including possible floor/ceiling scores or outliers.

Remark: The low number of scores on other tests is caused by the fact that this test is accepted for admission to the Glia Society, and that thus qualified members tend not to engage in much further high-range testing.

Estimated loadings of Graduate Record Examination on particular item types

There is not enough data to make this significant.

National medians for Graduate Record Examination

For reasons of privacy, only countries with 3 or more candidates are included in this table. Ranking is based on the medians, and then alphabetic.

Correlation with national I.Q.'s of Graduate Record Examination

Correlation of this test with national average I.Q.'s published by Lynn and Vanhanen, later Lynn and Becker:

• r = -0.15 (n = 53)

Correlation of Graduate Record Examination with personal details

Estimated g factor loadings for restricted ranges

In parentheses the number of score pairs on which that estimated g factor loading is based. The goal of this is to verify the hypothesis that g becomes less important, accounts for a smaller proportion of the variance, at higher I.Q. levels. The mere fact of restricting the range like this also depresses the g loading compared to computing it over the test's full range, so it would be normal for these values to be lower than the test's full-range g loading.

[Main page]