Associatie - Statistics

© Mar 2007 Paul Cooijmans

This is the association subtest of the Netherlandic version of the Long Test For Genius, no longer in use. Currently only the English version of the Test For Genius (Revision 2004) is in use, to prevent candidates from comparing the different language versions to thus gain an advantage. Also, there was very little interest in the non-English versions.

The lack of interest is regrettable, since the problems of the Netherlandic verbal subtests, just as those of the nonverbal subtests, are of an exceptional quality. Some of them live on in the English TFG, and those that have no English versions are now revived in De Golfstroomtest.

Norms

This test is normed to protonorms. To translate protonorms to the proportion of candidates outscored and IQ, see the relevant table.

RawProtonorm
051 or lower
1106
2150
3183
4205
5216
6227
7238
8249
9260
10275
11277
12300
13312
14337
15339
16341
17353
18368
19387
20392
21393
22402
23404
24405
25426
26432
27433
28453
29459
30460
31461
32462
33463
34483
35547
36558
37569
38580
39591
40602
41613
42624
43635
44646
45657
46668
47679
48690
49701
50712
51734
52777
53821
54876
55942
56919
571007
581106
591216
601337

Used for norming are all of the known scores from tests correlating .34 or higher with the Association subtest of Long Test For Genius (NL). The used scores are if needed converted to protonorms using the relevant conversion formula or table. The raw scores on the Association subtest of Long Test For Genius (NL) that form pairs with the used scores are rank-equated to the used scores, and where needed there is interpolation or extrapolation.

Scores

9 *
12 *
14 **
17 **
18 **
19 *
20 *
21 *
25 **
27 *
28 **
29 *
35 ***

Correlation with other tests

Test#cor
De Laatste Test31
A-22 - Early experimental association test in Netherlandic, 27 items (maximum score 31)30.96
Drenth number series50.89
The Test To End All Tests30.86
Long Test For Genius (NL)160.79
Cooijmans Intelligence Test - Form 130.77
Analogies of Long Test For Genius (NL)170.59
Space, Time and Hyperspace170.52
Mega Test30.34
Numbers120.22
Short Test For Genius7-0.01
Cattell Culture Fair9-0.18
Hoeflin Power Test3-0.35
Unknown tests4-0.8

Weighted average of correlations: 0.425

Conservatively estimated minimum g loading: 0.65

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 3 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 averages

Country# scoresAverage score
Netherlands1722.5
Belgium219

For reasons of privacy, only countries with 2 or more candidates are included in this table. Ranking is based on the unrounded averages.

Correlation with personal details

Personalia#cor
PSIA Orderly31
PSIA Introverted30.83
PSIA Just30.76
PSIA Deviance factor40.6
PSIA Extreme30.5
PSIA Aspergoid30.42
PSIA True30.36
PSIA Cold30.24
Is male200.2
PSIA Cruel30.1
PSIA Ethics factor40.09
Educational level6-0.08
PSIA Neurotic3-0.1
PSIA Rare3-0.2
PSIA Rational3-0.28
Disorders (own)6-0.36
Disorders (parents and siblings)6-0.36
Mother's educational level6-0.56
Father's educational level5-0.72
Is resident of the European Union3-0.83
PSIA Antisocial3-0.86
Year of birth8-0.87

Correlation with national IQs

Correlation of this test with national average IQs published by Lynn and Vanhanen:

Scores by age

Age group# testeesAverage score
60 to 64128
50 to 54120
40 to 44224.5
35 to 39431
30 to 34324.3
25 to 29619.5
22 to 2419
18 or 19112
15114

Scores by year taken

Year taken# testeesAverage score
1996723.1
1997315.3
1999324.3
2000127
2001119
2002112
2004326.3
2005128

Correlation year taken vs average score = 0.29
n = 20

Reliability and standard error

Using the "split-half" method:

Robustness and overall test quality

Item analysis

Item statistics are not published as that would help future candidates. To detect bad items, answers and comments from testees 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.

Most of this report was generated by software created 2002-present by Paul Cooijmans.