Question

Only a few days ago, a paper was published testing the association between blood type and COVID-19 infection. The paper used a dataset a part of which is summarized as below.

Blood Type	COVID-19 + Counts	COVID-19 - Counts
A	233	245
AB	21	47
B	116	136
O	312	449

Based on the provided sample, would you conclude that there is a correlation between blood type and COVID-19 infection (using a significance level of 0.05)? What is the p-value?

1.)   Yes, COVID-19 infection is correlated with blood type. p-value = 0.0064.

2.)   No, COVID-19 infection is not correlated with blood type. p-value = 0.12.

3.)   Yes, COVID-19 infection is correlated with blood type. p-value = 0.12.

4.)    No, COVID-19 infection is not correlated with blood type. p-value = 0.0064.

Answer 1

		COVID 19+	COVID 19-	Total
A	Observed	233	245	478
	Expected	209.11	268.89	478.00
	O - E	23.89	-23.89	0.00
	(O - E)² / E	2.73	2.12	4.85
AB	Observed	21	47	68
	Expected	29.75	38.25	68.00
	O - E	-8.75	8.75	0.00
	(O - E)² / E	2.57	2.00	4.57
B	Observed	116	136	252
	Expected	110.24	141.76	252.00
	O - E	5.76	-5.76	0.00
	(O - E)² / E	0.30	0.23	0.54
O	Observed	312	449	761
	Expected	332.91	428.09	761.00
	O - E	-20.91	20.91	0.00
	(O - E)² / E	1.31	1.02	2.33
Total	Observed	682	877	1559
	Expected	682.00	877.00	1559.00
	O - E	0.00	0.00	0.00
	(O - E)² / E	6.92	5.38	12.30
		12.30	chi-square
		3	df
		.0064	p-value

Answer: Since P value<alpha.

Yes, COVID-19 infection is correlated with blood type. p-value = 0.0064.