SEE30N

 SEE30 (former ISRC2018) Statistics

Last Revision : June 2nd, 2018.

1. 4th Norm

Raw Score IQ (sd15) Raw Score IQ (sd15)
7 <=100 19 143
8 104 20 147
9 108 21 150
10 111 22 154
11 114 23 157
12 120 24 162
13 124 25 166
14 127 26 169
15 131 27 173
16 133 28 175
17 137 29 178
18 140 30 185

2. Histogram

A) Grouped scores

see30_4th_group

B) Independent scores

see30_4th_scores

3. Statistical Properties & Correlations with other tests
Calculated mean on reported scores on standard supervised tests is 141.1 sd15 (N=28). Mean raw score of this sample on ISRC2018 is 19.071.

Parameter Value Test Score Pairs (n) r
Mean 18.38 Standard* 28 0.802
Median 18 WAIS 7 0.741
Stand. Deviation 4.088 RAPM 6 0.917
Variance 16.716 CCFIT III 3 0.991
SEM 0.411 Jouve** 37 0.654
Kurtosis -0.127 JCTI 14 0.892
Skewness -0.045 C-09 8 0.835
Cronbach’s a 0.898 TLAP-R 5 0.912
JCCES 3 0.991

* Tests used : WAIS, RAPM, IBF-S, OLSAT, CFIT20R, CCFIT, FRT, Unknown Mensa Entrance Test.
** Tests used : JCTI, CSE, TLAP-R, JCCES, C-09, C-10, Encephalist, NVCPE-R, C-12, EPC-L.

4. Notes
To sum up, SEE30  shows very high positive correlation with standard supervised IQ tests (r=0.802 – It has to be noted at this pointed that scores “greater than”, like >135 that are given in FRT-A case are used when computing validity. Not including those ones could lead to a much higher r.) and excellent reliability (Cronbach’s alpha=0.898), a fact that makes it a reliable tool for estimating one’s intelligence quotient. It’s also quite clear, yet still preliminary as an observation, that there is a stronger correlation with spatial tests, something that was, more or less, expected. Next and final norm will be generated at a total of 120 submissions, although no significant changes are to be expected.

Advertisements