. Author manuscript; available in PMC: 2010 Feb 22.

Published in final edited form as: Struct Equ Modeling. 2008;15(1):23–51. doi: 10.1080/10705510701758166

TABLE 2.

Average Confidence Limits

		Sample Size
		50		100		200
Effect Type	Test	True to Left	True to Right	True to Left	True to Right	True to Left	True to Right
Null two-path, two zero paths	Standard z	.00000^a	.00018^a	.00027^a	.00000^a	.00000^a	.00000^a
	M	.00255^a	.00145^a	.00209^a	.00145^a	.00155^a	.00091^a
	Percentile bootstrap	.00155^a	.00282^a	.00136^a	.00109^a	.00091^a	.00127^a
	Bias-corrected bootstrap	.00682^a	.00682^a	.00491^a	.00636^a	.00545^a	.00618^a
Null two-path, one zero path	Standard z	.01042^a	.01013^a	.01308	.01233^a	.01492	.01650
	M	.02571	.02450	.02488	.02425	.02363	.02579
	Percentile bootstrap	.02029	.02171	.02263	.02358	.02363	.02704
	Bias-corrected bootstrap	.03592	.03308	.03338	.03425	.03450	.03683
Null two-path overall	Standard z	.00714^a	.00700^a	.00906^a	.00846^a	.01023^a	.01131^a
	M	.01843	.01726	.01771	.01709	.01669	.01797
	Percentile bootstrap	.01440	.01577	.01594	.01651	.01649	.01894
	Bias-corrected bootstrap	.02677	.02483	.02443	.02549	.02537	.02720
Null three-path, three zero paths	Standard z	.00000^a	.00000^a	.00000^a	.00000^a	.00000^a	.00000^a
	Emp-M	.00000^a	.00000^a	.00000a	.00000^a	.00000^a	.00000^a
	Percentile bootstrap	.00000^a	.00150^a	.00000^a	.00000^a	.00000^a	.00000^a
	Bias-corrected bootstrap	.00350^a	.00250^a	.00100^a	.00050^a	.00200^a	.00200^a
Null three-path, two zero paths	Standard z	.00000^a	.00000^a	.00000^a	.00000^a	.00000^a	.00007^a
	Emp-M	.00236^a	.00129^a	.00157^a	.00193^a	.00179^a	.00207^a
	Percentile bootstrap	.00064^a	.00243^a	.00071^a	.00071^a	.00086^a	.00129^a
	Bias-corrected bootstrap	.00993^a	.00743^a	.00729^a	.00921^a	.00800^a	.00543^a
Null three-path, one zero path	Standard z	.00387^a	.00473^a	.01000^a	.01013^a	.01533	.01313
	Emp-M	.02647	.02767	.02707	.02687	.02527	.03100
	Percentile bootstrap	.01493	.01973	.02353	.02080	.02407	.02180
	Bias-corrected bootstrap	.04060^a	.04033^a	.04047^a	.03773^a	.04060^a	.03800^a
Null three-path, overall	Standard z	.00187^a	.00229^a	.00484^a	.00490^a	.00742^a	.00639^a
	Emp-M	.01387	.01396	.01381	.01387	.01303	.01594
	Percentile bootstrap	.00752^a	.01074^a	.01171^a	.01039^a	.01203^a	.01113^a
	Bias-corrected bootstrap	.02435	.02303	.02294	.02245	.02339	.02097
Nonzero two-path	Standard z	.00814^a	.06346^a	.01011^a	.06592^a	.01230^a	.05719^a
	M	.01678	.05046^a	.01738	.05519^a	.01892	.04338^a
	Percentile bootstrap	.01449	.04162^a	.01754	.04173^a	.01986	.04438^a
	Bias-corrected bootstrap	.02219	.04054^a	.02376	.04322^a	.02505	.03532
Nonzero three-path	Standard z	.00160^a	.07620^a	.00700^a	.08920^a	.00680^a	.08300^a
	Emp-M	.01000^a	.06780^a	.01600	.08100^a	.01440	.07320^a
	Percentile bootstrap	.00920^a	.03580	.01420	.04320^a	.01620	.05920^a
	Bias-corrected bootstrap	.01960	.05300^a	.02660	.05720^a	.02420	.04640^a

Value outside Bradley (1978) robustness interval.