Abstract
My
study was designed in order to determine if there was a useful
linear relationship between hours of sleep each night and students’
corresponding height. I chose the population of North Olmsted
High School and selected a random sample of 80 students using
mini-tab’s sample from columns tool and Miss Caso’s list of all
students in the high school. I wished to use the direct control
method to control the extraneous variable of gender so I divided the
list into males and females before selecting and took an equal sample
of forty from each list. I created a survey asking students
their height, average hours of sleep each night as well as whether
they were a male or a female. I received about 70 surveys back
and had to discard a few due to response bias and to keep the
population of girls and boys the same.
Receiving the data, I used mini-tab in order to gather statistics and
create graphs of the data. I then used mini-tab to perform a
hypothesis test of the data in the form of a linear regression t-test.
Assumptions were checked using a scatter plot. The assumptions
were met and the p-value was 0.733, which led me to fail to reject my
null hypothesis of there being no useful linear relationship between
hours of sleep and height at the 0.05 level of significance. I
concluded that there was insufficient evidence to suggest that there
was a useful linear relationship between hours of sleep and student
height.
Reflecting on my study, I found the weaknesses of my study to be
response bias, selection bias, and the fact that there are hard to
control extraneous factors that may affect height such as genetics.
I decided that extrapolating the data would be appropriate if it is
limited to high schools because I realized that I missed a large
factor in this study: that high school students are no longer growing
and so their current hours of sleep are more than likely not affecting
their height any longer. Therefore, I think it would be much
more useful if a study was done with younger children and more
extraneous factors were controlled or randomized.
Ultimately, I determined that there was not a useful relationship between hours of sleep each night and height for high school students, but the possibility of a relationship between hours of sleep and height for different age groups may give more useful results.