Question

A researcher wants to assess association between high blood pressure prevalence and the amounts of processed foods. If the level of education is associated with both amounts of processed food and high blood pressure, is education a confounder or effect modifier?

Answer 1

Diet Low in Processed Foods
Normal BP	High BP	Total
College Education	124	55	179
High School Education	69	152	221
Total	193	207	400
	Diet High in Processed Foods
	Normal BP	High BP	Total
College Education	64	85	149
High School Education	98	153	251
Total	162	238	400

A researcher wants to assess the association between the prevalence of high blood pressure and amounts of processed foods. Data are presented below to evaluate whether the education level is a confounder of effect modifier for the association of interest. Which of the statement is correct (assuming a 5% significance level)?

Chi-square Contingency Table Test for Independence
	Diet Low
			Normal BP	High BP	Total
	College Education		124	55	179
	High School Education		69	152	221
	Total		193	207	400
			57.35	chi-square
			1	df
			0.0000	p-value
Chi-square Contingency Table Test for Independence
	Diet high
			Normal BP	High BP	Total
	College Education		64	85	149
	High School Education		98	153	251
	Total		162	238	400
			0.59	chi-square
			1	df
			.4413	p-value

The association between education and BP is significant in low diet group ( chi square =57.35, P=0.0000) and not significant in high diet group( chi square =0.59, P=0.4413).

		Normal BP	High BP	Total
College Education		188	140	328
High School Education		167	305	472
Total		355	445	800
		37.72	chi-square
		1	df
		0.0000	p-value

Overall the association between education and BP is significant ( chi square =37.72, P=0.0000)

Education level is neither a confounder nor an effect modifier

Note: diet is the effect modifier