Long Test For Genius statistics

Introduction

This report concerns the English version of the Long Test For Genius, consisting of the subtests "Association", "Analogies", and "Space, Time, and Hyperspace". The spatial subtest is weighted by 3 in the total score.

Scores on Long Test For Genius as of 14 February 2023

Contents type: Verbal, spatial. Period: 1995-2004

n: 84
Median: 68.0
Quartile deviation: 12.8
Range: 97
Maximum possible: 162
Male median: 68.0 (n = 77)
Female median: 72.0 (n = 7)
Proportion of males among candidates: 0.917
Hardness: 0.59
Resolution: 0.73

13	*
27	**
29	*
30	*
34	***
35	*
36	*
37	*
38	**
43	*
45	*
46	*
47	*
48	*
49	*
52	*
53	*
54	***
55	*
57	**
58	**
59	*
61	**
62	*
63	****
64	*
66	***
68	**
69	*
70	**
71	*
72	***
73	***
75	***
76	*
77	*
78	***
79	****
80	*
82	**
84	*
85	*
87	***
88	*
90	**
94	*
95	*
98	**
102	**
108	*
109	*

Scores by males

n = 77

27	*
29	*
30	*
34	**
35	*
36	*
37	*
38	**
43	*
45	*
46	*
47	*
48	*
49	*
52	*
53	*
54	***
55	*
57	**
58	**
59	*
61	**
62	*
63	****
64	*
66	***
68	**
69	*
70	**
71	*
72	**
73	***
75	***
76	*
78	***
79	****
80	*
82	*
84	*
85	*
87	***
88	*
90	**
94	*
95	*
98	*
102	**
108	*
109	*

Scores by females

n = 7

13	*
27	*
34	*
72	*
77	*
82	*
98	*

Correlation of Long Test For Genius with other mental ability tests

Test name	n	r
Spatial Insight Test	5	1.00
Space, Time, and Hyperspace	84	0.93
Epiq Tests (aggregate)	4	0.92
Test of Inductive Reasoning / J.C.T.I. (Xavier Jouve)	7	0.91
Test For Genius - Revision 2004	14	0.89
Cooijmans Intelligence Test - Form 2	5	0.87
Spatial section of Test For Genius - Revision 2004	14	0.86
The Nemesis Test	6	0.86
Cooijmans Intelligence Test - Form 3	4	0.86
Associative LIMIT	6	0.79
Bonsai Test	8	0.79
916 Test (Laurent Dubois)	5	0.78
The Final Test	28	0.77
Analogies of Long Test For Genius	84	0.77
Association subtest of Long Test For Genius	84	0.74
Miller Analogies Test (raw; old version)	5	0.73
Short Test For Genius	12	0.72
Cooijmans Intelligence Test - Form 1	14	0.72
Genius Association Test	20	0.71
Non-Verbal Cognitive Performance Examination (Xavier Jouve)	15	0.69
Qoymans Multiple-Choice #4	13	0.65
Verbal section of Test For Genius - Revision 2004	14	0.65
Test of Shock and Awe	7	0.63
Cartoons of Shock	6	0.62
The Test To End All Tests	12	0.61
Titan Test (Ronald K. Hoeflin)	8	0.59
Scholastic Aptitude Test (old)	6	0.58
Numbers	26	0.57
Qoymans Multiple-Choice #3	17	0.55
Strict Logic Sequences Exam I (Jonathan Wai)	8	0.54
Lieshout International Mesospheric Intelligence Test	9	0.48
Culture Fair Numerical Spatial Examination - Final version (Etienne Forsström)	5	0.47
Graduate Record Examination	6	0.42
Reason Behind Multiple-Choice	4	0.41
Unknown and miscellaneous tests	30	0.38
Mega Test (Ronald K. Hoeflin)	12	0.33
Wechsler Adult Intelligence Scales	5	0.32
Odds	4	0.29
Analogies #1	8	0.29
Logima Strictica 36 (Robert Lato)	10	0.28
American College Testing program	4	0.27
Sigma Test (Melão Hindemburg)	10	0.22
Isis Test	9	0.21
W-87 (International Society for Philosophical Enquiry)	8	0.19
Hoeflin Power Test (Ronald K. Hoeflin)	4	0.16
Reason - Revision 2008	4	0.11
Encephalist - R (Xavier Jouve)	6	0.11
Reason Behind Multiple-Choice - Revision 2008	4	0.09
New York High I.Q. Society tests	4	0.04
Cattell Culture Fair	10	-0.06
Reason	4	-0.07
Qoymans Multiple-Choice #5	4	-0.07
Qoymans Multiple-Choice #2	8	-0.10
Tests by Greg Grove (aggregate)	12	-0.13
Qoymans Multiple-Choice #1	9	-0.14
International High IQ Society tests (aggregate)	10	-0.28
Cooijmans On-Line Test	4	-0.47
Raven's Advanced Progressive Matrices (I.Q.)	10	-0.55
Strict Logic Sequences Exam II (Jonathan Wai)	4	-0.61

Weighted average of correlations: 0.572 (N = 762)

Estimated g factor loading: 0.76

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.

Estimated loadings of Long Test For Genius 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.

Type	n	g loading of Long Test For Genius on that type
Verbal	306	0.81
Numerical	38	0.73
Spatial	112	0.94
Logical	19	0.50
Heterogeneous	131	0.77

N = 606

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

Balanced g loading = 0.75

National medians for Long Test For Genius

Country	n	median score
Canada	3	82.0
Australia	3	77.0
Finland	5	75.0
United_Kingdom	8	74.0
Greece	3	63.0
Sweden	7	63.0
United_States	25	62.0

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 Long Test For Genius

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

r = 0.04 (n = 70)

Correlation of Long Test For Genius with personal details

Personalia	n	r
Observed behaviour	14	0.65
Observed associative horizon	12	0.52
Educational level	36	0.30
Sex	84	0.12
Year of birth	81	0.03
Disorders (own)	35	-0.12
Disorders (parents and siblings)	35	-0.15
Father's educational level	28	-0.20
Mother's educational level	28	-0.35
Gifted Adult's Inventory of Aspergerisms	17	-0.44

Correlation with personal details of Long Test For Genius - within females

Personalia	n	r
Year of birth	7	0.46

Correlation with personal details of Long Test For Genius - within males

Personalia	n	r
Observed associative horizon	11	0.64
Observed behaviour	11	0.63
Educational level	34	0.33
Year of birth	74	-0.07
Disorders (own)	33	-0.12
Disorders (parents and siblings)	33	-0.14
Father's educational level	27	-0.17
Mother's educational level	27	-0.35
Gifted Adult's Inventory of Aspergerisms	16	-0.46

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.

Below 1st quartile	0.66 (163)
Below median	0.67 (366)
Above median	0.64 (377)
Above 3rd quartile	0.64 (200)

Reliability

Reliability = 0.88

Computed from the subtest reliabilities using a form of the Spearman-Brown formula.

Error

Standard error = 7.18 raw score points

Robustness and overall test quality

Robustness by month = 0.66 (r_{raw scores × months} = 0.13)
Quality = 0.718

Subtest statistics

The three subtests (named in the introduction above) have statistical reports of their own.

[More statistical reports]