In a two-way table of counts, we can compute the expected counts under the assum

Question

In a two-way table of counts, we can compute the expected counts under the assumption that there is no relationship between the row (R) and column C rs. For the table below: 012 = n12 n1+-n11 + n12 02 = n21 022 = n22 n2+ = n21 n22 n+1 = n11 + n21 n+2 = n12 + n22 n = n11 + n12 + n21 + n22 the expected values under the assumption of statistical independence are 2 21 An approximate test of they hypothesis of no relationship is given by O-E)2 which is distributed as a random variable with k _ (nr-1)(m-1) degrees of freedom where n, is the number of rows and nc is the number of columns Here are data from the Scotticsh Heart Health Study on smoking and gender: Male Female Nonsmoker Cigarettes 1400 1551 2241 2599 (011-811) Computeto three decimal places. Note: You can use table.margins and the expected function from the epitools package or do the computations manually

Explanation / Answer

from above (o11 -e11)2/e11   = 0.193

please revert for any clarificaiton required.

Observed O Non smokers Cigarettes Total male 2241 1400 3641 female 2599 1551 4150 Total 4840 2951 7791 Expected E=rowtotal*column total/grand total Non smokers Cigarettes Total male 2261.90 1379.10 3641 female 2578.10 1571.90 4150 Total 4840 2951 7791 chi square =(O-E)^2/E Non smokers Cigarettes Total male 0.1931 0.3166 0.510 female 0.1694 0.2778 0.447 Total 0.362 0.594 0.957

Related Questions

Navigate

• Browse (All)
• Browse I
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.