Refinement of an instrument measuring science teachers’ knowledge of language through mixed method

Disciplinary and Interdisciplinary Science Education Research

Table 3 Item difficulty, item fit statistics, and correlations (n = 126)

Item	Difficulty δ	Outfit MNSQ	Outfit.t	Infit MNSQ	Infit.t	Item-Total Alpha	Alpha if Item Deleted
LQ01R	-0.58	1.21	1.63	1.09	0.72	0.33	0.61
LQ03R	-0.96	1.08	0.58	1.05	0.37	0.52	0.57
LQ05	-1.00	1.08	0.56	0.99	-0.05	0.30	0.61
LQ06	-0.40	1.12	1.02	1.03	0.31	0.11	0.64
LQ07R	-2.26	0.76	-1.61	0.74	-1.69	0.51	0.60
LQ11	-1.19	0.85	-0.97	0.83	-1.14	0.63	0.57
LQ12R	-1.32	0.92	-0.49	0.87	-0.81	0.48	0.60
LQ16R	-0.43	1.26	2.13	1.18	1.51	0.18	0.64
LQ17R	-2.37	0.70	-2.06	0.73	-1.85	0.68	0.59
LQ18	-1.38	0.94	-0.32	0.94	-0.31	0.55	0.58
LQ20R^a	-2.51	0.87	-0.80	0.89	-0.64	0.43	0.61
LQ22R^a	-0.77	1.51	3.42	1.38	2.67	-0.09	0.67
LQ24R^b	-1.85	0.77	-1.47	0.73	-1.71	0.68	0.58
LQ26^a	-0.43	1.35	2.83	1.26	2.14	0.14	0.64
LQ100^a	-1.27	1.30	1.75	1.16	1.02	0.30	0.62

(1) ^a means those items should be coded reversed in data analysis
(2) ^b Because LQ24R doesn’t have category 1 response, recode 0 category as 1, so there is continuous with category 2, 3, and 4
(3) Item-total correlation was calculated by alpha () function in psych package in r language (r.cor = item-total correlation)