Short Test For Genius statistics

Scores on Short Test For Genius as of 14 October 2019

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

• n: 73
• Median: 5.0
• Quartile deviation: 3.0
• Range: 27
• Maximum possible: 40
• Male median: 6.5 (n = 66)
• Female median: 2.0 (n = 7)
• Resolution: 0.35

Scores by males

n = 66

Scores by females

n = 7

Correlation of Short Test For Genius with other tests by Paul Cooijmans

Weighted average of correlations: 0.628 (N = 214, weighted sum = 134.36)

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 4 score pairs. All known pairs are used, including possible floor/ceiling scores or outliers.

Correlation of Short Test For Genius with tests by others

Weighted average of correlations: 0.422 (N = 117, weighted sum = 49.34)

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 Short 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.

N = 179

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

Balanced g loading = 0.80

National medians for Short Test For Genius

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 Short Test For Genius

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

• r = 0.05 (n = 55)

Correlation of Short Test For Genius with personal details

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) = 0.92
• Split-half (other division) = 0.89

The computation of Cronbach's alpha is problematic for this test because a small number of its numbered items were actually examples with the answers given, so that there is no variance for those items. The split-half reliabilities are probably underestimations of the true reliability for the same reason, and as a result, the error of measurement given below may be an overestimation of the actual error.

Error

• Standard error = 1.7 raw score points

Scores by age

N = 64

Scores by age - within females

N = 5

Scores by age - within males

N = 59

Scores by year taken

r_{year taken × median score} = 0.46 (N = 73)

Robustness and overall test quality

• Robustness by month = 0.69 (r_{raw scores × months} = 0.06)
• Quality = 0.711

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 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.

Correlations between sections (internal consistency versus profile information)

Ideal values for correlations between sections are around .5, thus being a compromise between the test's ability to yield a "profile" and its ability to provide an indication of general intelligence. With a too high correlation (like .8 or higher) the sections measure basically the same so there is almost no profile information in them, with a too low correlation (like .2 or lower) the sections are so different that there is little point in combining them into a measure of general intelligence.

Loadings of sections on the first factor in the total score variance of this test

Proportion of total score variance accounted for by this factor: 0.64

These first factor loadings represent the subtests' correlations with that which the test is primarily measuring, and are a somewhat better indicator than the subtests' correlations with total score, which is why the latter are not reported any more. The remainder of the total score variance may lie in other factors (group factors), specificity, and error.

Section frequency tables

Prop. = proportion of candidates outscored in this section. In parentheses the proportion outscored for any possible scores higher than the present score but lower than the next-higher score in the table.

Verbal

Numerical

Spatial

[More statistical report]