8.3 Odds and software output
(This question continues Question 6.6.)
The timing of pubertal maturation can vary, which can have impacts upon behaviour.
A large study (Duncan et al. 1985) studied ‘the relationships between maturational timing and body image, school behavior, and deviance.’
Sample data were collected from
…children and youth of the entire United States drawn by the National Center for Health Statistics… known as the National Health Examination Survey (1966–1970). Data were collected on… adolescents’ physical and psychological status…
— Duncan et al. (1985)
The researchers asked the RQ;
For children, is the odds of a boy maturing late the same as the odds of a girl maturing late?
For the 2,864 males in the sample, 352 were classified as maturing late.
For the girls, 336 of the 2,664 matured late.
Use this information to construct a two-way table of sex against maturation time (Table 8.1).
|Matured late||Did not mature late||Total|
- What graphical summary could be used to display the information? Sketch this display.
- Among the boys, compute the odds of maturing late. Interpret this value.
- Among the girls, compute the odds of maturing late. Interpret this value.
- From the table, compute the odds ratio of a boy maturing late compared to a girl maturing late. Interpret this value, using the software output (Fig. 8.13; Fig. 8.14).
- What is the parameter of interest?
- Write down the OR and the 95% CI for the OR from the jamovi or SPSS output. What does it mean?
- Compile the numerical summary table for these data (Table 8.2).
- Are boys generally more likely to mature later than girls? Vote below. Justify your answer.
|Percentage maturing late||Odds maturing late||Sample size|
Duncan, Paula Duke, Philip L. Ritter, Sanford M. Dornbusch, Ruth T. Gross, and J. Merrill Carlsmith. 1985. “The Effects of Pubertal Timing on Body Image, School Behavior, and Deviance.” Journal of Youth and Adolescence 14 (3): 227–35.