Table 3.
Simulation Results: Unidimensional Model, Null Condition
K | N | reps |
M2
|
RMSEA
|
rejection rates
|
||||||
---|---|---|---|---|---|---|---|---|---|---|---|
df | Mean | Var | Mean | (90% CI) | .150 | .100 | .050 | .010 | |||
test statistic based on full one- and two-way marginal tables (M2) | |||||||||||
2 | 750 | 1000 | 90 | 90.9 | 183.4 | .006 | (.000,.019) | .164 | .104 | .053 | .016 |
1500 | 1000 | 90 | 89.9 | 162.0 | .004 | (.000,.013) | .133 | .075 | .044 | .008 | |
3 | 750 | 1000 | 405 | 399.8 | 781.8 | .003 | (.000,.011) | .099 | .062 | .032 | .009 |
1500 | 1000 | 405 | 396.2 | 794.8 | .002 | (.000,.008) | .082 | .063 | .031 | .005 | |
4 | 750 | 1000 | 930 | 904.8 | 1857.9 | .002 | (.000,.008) | .055 | .033 | .010 | .002 |
1500 | 1000 | 930 | 903.5 | 1716.1 | .001 | (.000,.006) | .054 | .034 | .015 | .001 | |
5 | 750 | 1000 | 1665 | 1622.1 | 3380.4 | .001 | (.000,.007) | .042 | .020 | .010 | .001 |
1500 | 1000 | 1665 | 1619.6 | 3320.3 | .001 | (.000,.004) | .033 | .022 | .008 | .000 | |
| |||||||||||
test statistic based on reduced one- and two-way marginal tables( ) | |||||||||||
3 | 750 | 1000 | 75 | 75.7 | 158.5 | .006 | (.000,.020) | .160 | .106 | .061 | .020 |
1500 | 1000 | 75 | 75.5 | 149.8 | .004 | (.000,.014) | .155 | .103 | .053 | .012 | |
4 | 750 | 1000 | 60 | 60.2 | 120.2 | .006 | (.000,.021) | .159 | .106 | .056 | .010 |
1500 | 1000 | 60 | 60.4 | 129.4 | .005 | (.000,.015) | .165 | .117 | .056 | .012 | |
5 | 750 | 1000 | 45 | 45.0 | 95.5 | .007 | (.000,.023) | .150 | .105 | .057 | .019 |
1500 | 1000 | 45 | 45.1 | 91.7 | .005 | (.000,.016) | .158 | .106 | .052 | .012 |
Notes. K is the number of categories. N is the sample size. The number of valid (converged and stable) solutions are reported under the column heading “reps.” The reference distribution of M2 and statistics is central chi-square with df degrees of freedom. Note that M2 is equivalent to when K is 2.