Question

Can people tell the difference between a female nose and a male nose? Eight Caucasian males and eight Caucasian females posed for nose photos. The article states that none of the volunteers wore nose studs or had prominent nasal hair. Each person placed a black Lycra tube over his or her head in such a way that only the nose protruded through a hole in the material. Photos were then taken from three different angles: front view, three-quarter view, and profile. These photos were shown to a sample of undergraduate students. Each student in the sample was shown one of the nose photos and asked whether it was a photo of a male or a female; and the response was classified as either correct or incorrect. The accompanying table was constructed using summary values reported in the article. Is there evidence that the proportion of correct sex identifications differs for the three different nose views? Test the appropriate hypotheses using a .05 significance level. (Use 2 decimal places.)

Sex IDViewFrontProfileThree-QuarterCorrect272625Incorrect131415

χ² =
P-value interval

p < 0.0010.001 ≤ p < 0.01    0.01 ≤ p < 0.050.05 ≤ p < 0.10p ≥ 0.10

The data  ---Select--- support do not support the hypothesis that the proportions of correct sex identifications differ for the three different nose views.

Answer 1

using excel>addin>phstat>multiple sample test

we have

Chi-Square Test
Observed Frequencies
	Column variable			Calculations
Row variable	Front	threee	correct	Total		fo-fe
correct	27	26	25	78		1	0	-1
Incorrect	13	14	15	42		-1	0	1
Total	40	40	40	120
Expected Frequencies
	Column variable
Row variable	Front	threee	correct	Total		(fo-fe)^2/fe
correct	26	26	26	78		0.038462	0	0.038462
Incorrect	14	14	14	42		0.071429	0	0.071429
Total	40	40	40	120
Data
Level of Significance	0.05
Number of Rows	2
Number of Columns	3
Degrees of Freedom	2
Results
Critical Value	5.991465
Chi-Square Test Statistic	0.21978
p-Value	0.895933
Do not reject the null hypothesis

χ2 =0.220
P-value interval

p ≥ 0.10

The data do not support the hypothesis that the proportions of correct sex identifications differ for the three different nose views.