Statistics of Test For Genius - Revision 2004

Norms

Scores

# Candidates: 60
Median: 39.5
Quartile deviation: 8.3
Range: 67
Maximum possible: 96
Mean: 38.2
Standard deviation: 14.66
Male median: 40.0
Female median: 0.0 (# females: 1)
Hardness: 0.59
Resolution: 0.52

0	**
9	*
12	*
14	*
18	**
19	**
21	*
25	*
26	*
29	**
31	*
32	*
32.5	*
33	*
34	*
35	*
36	****
37	***
38	**
39	*
40	**
41	*
42	*
43	*
45	***
46	**
47	***
48	*****
49	***
51	*
52	*
53	*
56	*
61	**
62	*
63	*
67	*

Correlation with other tests

Test	#	cor
Qoymans Multiple-Choice #3	5	0.97
Sigma Test	5	0.94
Spatial section of Test For Genius - Revision 2004	60	0.93
Long Test For Genius	13	0.90
Titan Test	5	0.89
Cooijmans Intelligence Test - Form 2	16	0.86
The Test To End All Tests	11	0.83
International High IQ Society Miscellaneous tests	7	0.83
Nonverbal Cognitive Performance Examination	13	0.81
Mysterium Entrance Exam	10	0.79
Verbal section of Test For Genius - Revision 2004	60	0.78
Associative LIMIT Test	11	0.76
Space, Time and Hyperspace	17	0.75
Association subtest of Long Test For Genius	14	0.74
Strict Logic Sequences Exam I	12	0.73
Cartoons of Shock	11	0.70
The Final Test	18	0.68
Analogies of Long Test For Genius	14	0.67
Test of the Beheaded Man	5	0.62
Culture Fair Numerical Spatial Examination - Final version	12	0.60
Qoymans Multiple-Choice #4	26	0.57
Reason Behind Multiple-Choice	15	0.51
Numbers	10	0.50
Genius Association Test	20	0.48
Reason	16	0.47
Lieshout International Mesospheric Intelligence Test	22	0.46
The Nemesis Test	8	0.43
Qoymans Automatic Test #3	5	0.43
Bonsai Test	8	0.43
Test of Shock and Awe	9	0.42
Logima Strictica 36	10	0.42
Verbal section of The Marathon Test	5	0.34
The Sargasso Test	6	0.34
TRI	5	0.30
Culture Fair Numerical Spatial Examination - C	7	0.30
KIT Intelligence Test	6	0.30
Spatial Insight Test	8	0.22
Strict Logic Spatial Exam 48	8	0.21
Odds	7	0.10
Cooijmans On-Line Test	5	0.09
The Marathon Test	5	-0.08
Spatial section of The Marathon Test	5	-0.68
Numerical section of The Marathon Test	5	-0.69

Weighted average of correlations: 0.616

Conservatively estimated minimum g loading: 0.79

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 5 score pairs. All known pairs are used to obtain the true, honest statistics; Correlations are not artificially inflated by leaving out ceiling scores, outliers or other anomalies.

National medians

Country	# Scores	Median score
Germany	3	63.0
Canada	2	50.0
Norway	3	47.0
Australia	4	39.5
Italy	2	37.0
Sweden	5	37.0
United_Kingdom	5	37.0
Greece	3	36.0
Finland	3	33.0
United_States	15	32.5

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 personal details

Personalia	#	cor
W-87	3	1.00
Raven's Advanced Progressive Matrices (I.Q.)	3	0.60
Wechsler Adult Intelligence Scales	6	0.44
Educational level	56	0.34
Is male	60	0.34
PSIA Rational	26	0.31
Observed behaviour is good	14	0.28
Father's educational level	56	0.26
Mother's educational level	56	0.16
PSIA Cruel	26	0.10
PSIA Neurotic	26	0.10
Year of birth	59	0.10
Is resident of the European Union	29	0.09
Raven's Advanced Progressive Matrices (raw)	6	0.04
PSIA Cold	26	0.03
PSIA Orderly	26	0.01
PSIA Introverted	26	-0.02
PSIA Ethics factor	32	-0.03
PSIA True	26	-0.03
Disorders (own)	55	-0.05
PSIA Rare	26	-0.08
Number of characters in candidate's name as registered	60	-0.12
PSIA Antisocial	26	-0.13
PSIA Deviance factor	32	-0.14
PSIA Just	26	-0.15
Cattell Culture Fair	3	-0.18
PSIA System factor (phased out)	8	-0.19
Disorders (parents and siblings)	55	-0.26
PSIA Extreme	26	-0.28
PSIA Aspergoid	26	-0.28
Gifted Adult's Inventory of Aspergerisms	7	-0.68

Correlation with national I.Q.s

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

r = 0.16 (n = 60)

Estimated g factor loadings Upward and Downward of specific scores

In parentheses the number of score pairs on which that estimated g factor loading is based (For maximum sensitivity, all other tests are used for which at least two pairs are available). The Upward and Downward values are calculated including the pertinent score itself. It is normal that g factor loadings go down when the range is restricted like this, but careful study of the Upward and Downward columns may reveal possible scores below or above which the test loses validity altogether.

Score	Upward (n)	Downward (n)
0	.75 (618)	NaN (0)
6	.75 (613)	NaN (0)
12	.73 (596)	.53 (14)
18	.69 (554)	.51 (59)
24	.65 (516)	.47 (77)
30	.60 (471)	.45 (117)
36	.60 (403)	.70 (236)
39	.52 (314)	.71 (280)
42	.49 (291)	.72 (317)
45	.58 (273)	.74 (339)
48	.62 (188)	.71 (472)
51	.61 (64)	.74 (538)
54	.42 (35)	.73 (564)
57	.57 (21)	.74 (581)
60	.57 (21)	.74 (581)
63	0.00 (4)	.75 (612)
66	NaN (0)	.75 (612)
67	NaN (0)	.75 (618)

Reliability

Split-half = 0.92
Cronbach's alpha = 0.96

Error

Standard error = 2.8 raw score points
Quartile error = 1.6 raw score points
Range of error = 12.9 raw score points

Scores by age

Age group	# Scores	Median score
60 to 64	1	14.0
55 to 59	2	29.5
50 to 54	3	29.0
45 to 49	3	37.0
40 to 44	6	43.5
35 to 39	7	47.0
30 to 34	10	36.0
25 to 29	12	47.0
22 to 24	10	38.5
20 or 21	1	37.0
18 or 19	2	38.5
17	2	30.0
16	1	34.0

Scores by year taken

Year taken	# Candidates	Median score
2004	14	39.5
2005	18	41.0
2006	10	42.5
2007	13	37.0
2008	5	38.0

Correlation year taken versus median score = -0.50
n = 60

Robustness and overall test quality

Rob = 1.00
Quality = 0.83

Item analysis

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 (validity of the item in this test) 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.