# testees: 60
Mean: 90.6
SD: 12.44
Male mean: 90.5
Female mean: 98 (1 persons)
60*
69*
71*
72*
74*
75**
77***
78*
79***
81**
82*
84*
86***
87*****
89*
90****
91**
92*
93**
94***
95**
96*
97*
98**
99**
101*
102**
103*
104*
106*
107*
108*
110*
113*
114*
118**
Test | # | cor |
---|---|---|
Analogies #1 | 9 | 0.82 |
Test To End All Tests | 4 | 0.8 |
Association Subtest of LTFG | 12 | 0.74 |
Analogies of LTFG | 11 | 0.71 |
Final Test | 13 | 0.69 |
Sigma Test | 7 | 0.63 |
Space, Time & Hyperspace | 21 | 0.6 |
Long Test For Genius | 10 | 0.54 |
Encephalist-R | 5 | 0.51 |
Numbers | 17 | 0.5 |
Qoymans Multiple-Choice #3 | 8 | 0.47 |
SAT (old) | 6 | 0.42 |
Raven APM | 7 | 0.37 |
OCIP | 4 | 0.32 |
Mega Test | 12 | 0.31 |
Logima Strictica 36 | 5 | 0.27 |
Mysterium Entrance Exam | 4 | 0.26 |
Short Test For Genius | 8 | 0.24 |
Unknown tests | 10 | 0.21 |
Cattell Culture Fair | 11 | 0.17 |
Bonsai Test | 6 | 0.14 |
Power Test | 6 | 0.13 |
W87 | 7 | 0.11 |
European IQ Test | 5 | -0.05 |
Qoymans Multiple-Choice | 13 | -0.09 |
Titan Test | 5 | -0.09 |
GRE | 6 | -0.28 |
NVCP | 4 | -0.82 |
Used for norming are the prior tests correlating .6 and higher. Prior scores are converted to an IQ scale with a standard deviation of 15. Prior and raw scores are rank-equated, missing scores are interpolated and there is a bit of extrapolation above and below.
The test appears to be harder than it seemed before, judging by the overall higher norms. Also remarkable is that only one female has taken it so far. Considering my observation about male and female ratios and score differences in the report "Correlations between Cooijmans tests", this too indicates the test is very hard.
To improve internal consistency, 25 items are removed from the test. Most of those are too easy, some have too low correlations with total score. The remaining 39 items, CIT Form 2, have correlations with total score (in the CIT Form 1) from .26 to .61, and difficulties (percentage of testees missing the item) from 7 to 95.
52 | ** |
60 | * |
69 | * |
71 | * |
72 | ** |
74 | * |
75 | ** |
77 | *** |
78 | * |
79 | *** |
81 | ** |
82 | * |
84 | * |
86 | **** |
87 | ***** |
89 | * |
90 | **** |
91 | ** |
92 | * |
93 | ** |
94 | *** |
95 | ** |
96 | * |
97 | ** |
98 | ** |
99 | ** |
101 | * |
102 | ** |
103 | * |
104 | * |
106 | * |
107 | * |
108 | * |
110 | * |
113 | * |
114 | * |
118 | ** |
(Test index) Test name | n | r |
---|---|---|
(18) The Nemesis Test | 4 | 0.93 |
(53) Qoymans Multiple-Choice #3 | 8 | 0.91 |
(35) Intelligence Quantifier by assessment | 14 | 0.90 |
(54) Test of Shock and Awe | 4 | 0.90 |
(10) Genius Association Test | 9 | 0.85 |
(79) Association subtest of Long Test For Genius | 15 | 0.76 |
(77) Analogies #1 | 9 | 0.76 |
(75) Analogies of Long Test For Genius | 15 | 0.73 |
(63) Long Test For Genius | 14 | 0.72 |
(1) Cartoons of Shock | 4 | 0.69 |
(7) The Final Test | 16 | 0.69 |
(27) Spatial section of Test For Genius - Revision 2004 | 4 | 0.66 |
(57) Space, Time, and Hyperspace | 24 | 0.64 |
(28) The Test To End All Tests | 8 | 0.61 |
(2) Cooijmans Intelligence Test - Form 3 | 4 | 0.56 |
(68) Numbers | 19 | 0.41 |
(56) Short Test For Genius | 10 | 0.38 |
(84) Bonsai Test | 10 | 0.36 |
(74) Cooijmans On-Line Test | 5 | 0.12 |
(51) Qoymans Multiple-Choice #1 | 13 | -0.09 |
(16) Lieshout International Mesospheric Intelligence Test | 4 | -0.27 |
(80) Qoymans Multiple-Choice #4 | 5 | -0.51 |
Weighted average of correlations: 0.569
Conservatively estimated minimum g loading: 0.75
(Test index) Test name | n | r |
---|---|---|
(237) Sigma Test | 8 | 0.52 |
(243) Scholastic Aptitude Test (old) | 7 | 0.48 |
(225) Logima Strictica 36 | 6 | 0.45 |
(242) Unknown tests | 11 | 0.39 |
(229) Mega Test | 13 | 0.37 |
(230) Omega Contemplative Items Pool | 5 | 0.37 |
(213) Encephalist - R | 6 | 0.36 |
(231) Mysterium Entrance Exam | 4 | 0.26 |
(220) Cattell Culture Fair | 11 | 0.17 |
(233) Hoeflin Power Test | 6 | 0.13 |
(206) W-87 | 7 | 0.11 |
(201) Wechsler Adult Intelligence Scales | 4 | 0.06 |
(239) Titan Test | 5 | -0.09 |
(219) Graduate Record Examination | 7 | -0.23 |
(218) Raven's Advanced Progressive Matrices (I.Q.) | 8 | -0.42 |
(235) Nonverbal Cognitive Performance Examination | 4 | -0.70 |
Weighted average of correlations: 0.177
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.
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.
Type | g loading of Cooijmans Intelligence Test - Form 1 on that type |
---|---|
Verbal | 0.76 |
Numerical | 0.64 |
Spatial | 0.73 |
Logical | 0.34 |
Heterogeneous | 0.74 |
Balanced g loading = 0.64
Country | n | median score |
---|---|---|
Belgium | 3 | 113.0 |
Canada | 3 | 98.0 |
Finland | 10 | 94.0 |
Netherlands | 4 | 92.0 |
United_Kingdom | 4 | 90.5 |
France | 2 | 88.0 |
United_States | 21 | 87.0 |
Italy | 2 | 86.0 |
Personalia | n | r |
---|---|---|
Observed associative horizon | 8 | 0.60 |
P.S.I.A. Cruel | 7 | 0.53 |
P.S.I.A. True | 7 | 0.48 |
Observed behaviour | 16 | 0.46 |
Gifted Adult's Inventory of Aspergerisms | 6 | 0.40 |
P.S.I.A. Ethics factor | 13 | 0.36 |
P.S.I.A. Orderly | 7 | 0.26 |
Mother's educational level | 16 | 0.23 |
P.S.I.A. Aspergoid | 7 | 0.22 |
P.S.I.A. Rare | 7 | 0.22 |
Father's educational level | 16 | 0.19 |
P.S.I.A. Antisocial | 7 | 0.12 |
P.S.I.A. Deviance factor | 13 | 0.04 |
Educational level | 19 | 0.01 |
Sex | 65 | 0.01 |
Disorders (own) | 18 | -0.07 |
P.S.I.A. Cold | 7 | -0.07 |
Year of birth | 59 | -0.14 |
P.S.I.A. Introverted | 7 | -0.16 |
P.S.I.A. Neurotic | 7 | -0.20 |
Disorders (parents and siblings) | 18 | -0.21 |
P.S.I.A. Rational | 7 | -0.35 |
P.S.I.A. System factor | 9 | -0.44 |
P.S.I.A. Just | 7 | -0.45 |
P.S.I.A. Extreme | 7 | -0.58 |
Correlation of this test with national average I.Q.'s published by Lynn and Vanhanen:
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.
Raw score | Upward g (n) | Downward g (n) |
---|---|---|
0 | 0.75 (218) | NaN (0) |
80.5 | 0.65 (142) | 0.34 (32) |
90 | 0.67 (96) | 0.70 (91) |
99.5 | 0.51 (45) | 0.70 (144) |
128 | NaN (0) | 0.75 (218) |
Age class | n | median score |
---|---|---|
60 to 64 | 1 | 94.0 |
55 to 59 | 1 | 90.0 |
50 to 54 | 7 | 84.0 |
45 to 49 | 4 | 96.5 |
40 to 44 | 7 | 98.0 |
35 to 39 | 8 | 89.0 |
30 to 34 | 10 | 92.5 |
25 to 29 | 6 | 86.0 |
22 to 24 | 7 | 91.0 |
20 or 21 | 3 | 87.0 |
17 | 2 | 85.5 |
16 | 1 | 75.0 |
Year taken | n | median score |
---|---|---|
1998 | 2 | 99.0 |
1999 | 13 | 94.0 |
2000 | 15 | 88.0 |
2001 | 11 | 91.0 |
2002 | 8 | 89.5 |
2003 | 8 | 83.0 |
2004 | 6 | 74.5 |
ryear taken × median score = -0.92 (n = 63)
Item statistics are not published as that would help future candidates. To detect bad items, answers and comments from candidates are studied, as well as, for each problem, the correlation with total score and the proportion of candidates getting it wrong (hardness of the item). Possible bad items are removed or revised, resulting in a revised version of the test.