The Essentials of Biostatistics for Physicians, Nurses, and Clinicians

Solutions to Selected Exercises 189

Sum of Expected Std Dev Mean

group N Scores Under H0 Under H0 Score

ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒƒ ƒƒ ƒƒ ƒ ƒ ƒ ƒƒ ƒƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒƒ ƒ ƒ ƒ ƒƒ ƒƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ ƒ

g2 12 90.50 150.0 17.312976 7.541667

g1 12 209.50 150.0 17.312976 17.458333

Average scores were used for ties.

Wilcoxon Two - Sample Test

Statistic 90.5000

Normal Approximation

Z - 3.4078

One - Sided Pr < Z 0.0003

Two - Sided Pr > |Z| 0.0007

t Approximation

One - Sided Pr < Z 0.0012

Two - Sided Pr > |Z| 0.0024

Z includes a continuity correction of 0.5.

Kruskal - Wallis Test

Chi - Square 11.8111

DF 1

Pr > Chi - Square 0.0006

Yes, we do need births to be at least uniform over the seasons. This is because

we are ranking based on number of births over a season. If there tended to be more

births in the fall and winter compared with summer and spring, the higher number

of schizophrenic patients could be due to the higher number of total births rather

than a tendency for schizophrenics to be born during winter and fall. If there were

a higher number of births in the winter, then we could not reach our intended con-

clusion. We would need to know the number of births in each season and adjust

accordingly by looking at proportion of schizophrenic births rather than the total

number.

6. Using Table 9.9 , compute the Spearman rank correlation coeffi cient for the
   aggressiveness scores. Does this suggest that both twins tend to be similar in
   degree of aggressiveness?
   Recall that the formula for Spearman ’ s rank correlation is given as follows:

bboth.indd 189oth.indd 189 6 6/15/2011 4:08:22 PM/ 15 / 2011 4 : 08 : 22 PM