Statistics of Cooijmans On-Line Test — Two-barrelled version

Scores on Cooijmans On-Line Test - Two-barrelled version as of 19 February 2022

Contents type: Verbal, numerical, logical.   Period: 2008-present

• n: 36
• Median: 10.0
• Quartile deviation: 5.3
• Range: 17
• Maximum possible: ∞
• Male median: 10.0 (n = 34)
• Female median: 5.5 (n = 2)
• Resolution: 0.47 (0.66 if half points are frequently given)

Correlation of Cooijmans On-Line Test - Two-barrelled version with other tests by I.Q. Tests for the High Range

Weighted average of correlations: 0.520 (N = 595, weighted sum = 309.47)

Conservatively estimated minimum g loading: 0.72

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.

Correlation of Cooijmans On-Line Test - Two-barrelled version with tests by others

Weighted average of correlations: -0.011 (N = 41, weighted sum = -0.47)

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.

Please be aware that correlations with these external tests are in most cases affected (depressed, typically) by one or more of the following: (1) Little overlap with the object test because of the much lower ceilings and inherent ceiling effects of the tests used in regular psychology; (2) Candidates reporting scores selectively, for instance only the higher ones while withholding lower ones; (3) Candidates reporting, or having been reported by psychometricians, incorrect scores.

Estimated loadings of Cooijmans On-Line Test - Two-barrelled version on particular item types

These are estimated g factor loadings, but against homogeneous tests (containing only particular item types) as opposed to non-compound heterogeneous tests. Although tending to surprise the lay person, it is not uncommon for tests to have high loadings on item types they do not actually contain themselves. Such loadings reflect the empirical fact that most tests for mental abilities measure primarily g, regardless of their contents; that the major part of test score variance is caused by g, and only a minor part by factors germane to particular item types. It is of key importance to understand that this is a fact of nature, a natural phenomenon, and not something that was built into the tests by the test constructors.

N = 434

Compound tests have been left out of this table to avoid overlap.

Balanced g loading = 0.69

National medians for Cooijmans On-Line Test - Two-barrelled version

For reasons of privacy, only countries with 2 or more candidates are included in this table. Ranking is based on the medians, and then alphabetic.

Correlation with national I.Q.'s of Cooijmans On-Line Test - Two-barrelled version

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

• r = 0.19 (n = 36)

Correlation of Cooijmans On-Line Test - Two-barrelled version with personal details

The only significant correlation here is with Disorders (own).

Estimated g factor loadings upward and downward of particular scores

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 both values to be lower than the test's full-range g loading.

Reliability

• Split-half (odd-even) = 0.97

Cronbach's alpha should not be computed for this test because its items (the two barrels) are not necessarily scored uniformly.

Error

• Standard error = 1.0 raw score points

Remark: In terms of internal statistics, this test functions as a two-item test (the two barrels) so the reliability coefficient rests solely on the correlation between the two barrels. This is so because each individual item of a barrel has to be solved in order to be admitted to the next item of that barrel, so that computing correlations between individual items is meaningless; any candidate reaching a particular item must have solved all of the previous ones. In addition, the second barrel appears only after exceeding a certain threshold in the first barrel, so that the correlation between the barrels is inflated by the construction of the test. In other words, this high reliability is enforced by the test construction and not a result of item quality. The second barrel serves to provide finer resolution in the higher range of the test.

Scores by age

N = 36

Scores by year taken

r_{year taken × median score} = -0.16 (N = 36)

Robustness and overall test quality

• Robustness by month = 0.78 (r_{raw scores × months} = -0.22)
• Quality = 0.718

Item analysis

Item statistics can not be meaningfully computed due to the construction of the test (see remark above). To detect bad items, answers and comments from candidates are studied. Possible bad items are removed or revised, resulting in a revised version of the test.

[More statistical reports]