The classic factor-analysis teaching dataset: 301 seventh- and eighth-grade students from two schools each take nine cognitive-ability tests. The nine continuous scored items split into three subscales — *visual* (`x1`–`x3`), *textual* (`x4`–`x6`), and *speed* (`x7`–`x9`) — which makes it a compact, complete real battery for coefficient alpha: estimate a subscale's alpha with [alpha()], compare reliabilities across the three subscales with a G-way [alpha_test()], or compare a subscale across the two schools with an independent-sample [alpha_test()]. Being complete, it is also a convenient base for illustrating the missing-data estimators under deliberate amputation. The data are factual 1939 measurements and are in the public domain.
Format
A 301 x 15 data frame:
- id
subject identifier.
- sex
1 = male, 2 = female.
- ageyr, agemo
age, years and months.
- school
factor; `"Pasteur"` (n = 156) or `"Grant-White"` (n = 145).
- grade
school grade.
- x1, x2, x3
visual subscale: visual perception, cubes, lozenges.
- x4, x5, x6
textual subscale: paragraph comprehension, sentence completion, word meaning.
- x7, x8, x9
speed subscale: speeded addition, speeded dot counting, speeded discrimination of straight and curved capitals.
Source
The `HolzingerSwineford1939` data frame distributed with the lavaan package; originally Holzinger & Swineford (1939).
References
Holzinger, K. J., & Swineford, F. (1939). A study in factor analysis: The stability of a bi-factor solution. Supplementary Educational Monographs, No. 48. University of Chicago.
Rosseel, Y. (2012). lavaan: An R package for structural equation modeling. Journal of Statistical Software, 48(2), 1-36. doi:10.18637/jss.v048.i02