Table 8

Chi-Squared Goodness-of-Fit Test Statistics

Outcome	Quintiles
Outcome	First	Second	Third	Fourth	Fifth	Overall
Do not enroll in college	0.40	0.06	0.18	0.28	1.46	2.37
Enroll in HBCU, no degree	4.34	4.32	10.32	10.90	17.91	47.79
Enroll in HBCU, degree, no advanced health degree	5.53	0.73	1.11	0.08	0.89	8.35
Enroll in non-HBCU
Two-year, no degree	0.79	0.95	0.35	5.09	3.75	10.94
Two-year, degree, no advanced health degree	0.04	3.38	4.64	2.39	5.32	15.77
Four-year level 2 (lowest), no degree	14.17	45.37	42.46	69.47	33.88	205.35
Four-year level 2 (lowest), degree, no advanced health degree	0.86	0.25	1.48	0.17	0.89	3.65
Four-year level 3, no degree	17.11	32.88	24.63	33.57	50.77	158.96
Four-year level 3, degree, no advanced health degree	6.20	2.39	0.43	0.40	2.08	11.50
Four-year level 3, degree, advanced health degree	1.24	0.22	0.77	2.15	1.41	5.78
Four-year level 4, no degree	0.34	0.15	2.94	3.73	6.11	13.28
Four-year level 4, degree, no advanced health degree	3.34	0.61	1.67	1.28	4.66	11.56
Four-year level 4, degree, advanced health degree	0.95	2.11	6.44	0.35	0.19	10.04
Four-year level 5 (highest), no degree	1.69	11.07	3.20	10.71	8.34	35.00
Four-year level 5 (highest), degree, no advanced health degree	0.10	0.76	0.04	0.57	0.01	1.47
Four-year level 5 (highest), degree, advanced health degree	1.07	0.18	1.79	0.14	0.17	3.34
Overall						545.14
Normalized^*						42.53

Notes: Quintiles are based on predicted probabilities of each educational/career path listed in the first column. Critical values for quintile statistics, which have one degree of freedom, are 3.84 (5 percent significance) and 6.64 (1 percent significance). Critical values for overall statistics, which have four degrees of freedom, are 9.49 (5 percent significance) and 13.28 (1 percent significance). Test statistics above the critical value imply a rejection of the null hypothesis that predicted proportions choosing each educational/career path equal action proportions making those choices in the data. Those statistics above the 1 percent critical value are bolded.
↵* Converted to a standard normal test statistic.