A STATISTICIAN’S LIFE
resulting in a larger range of response values for the
index. For example, one of the research groups was
interested in how students’ perceived social distance
might be associated with perceived loneliness. To
produce results that could be analyzed, we created a
summation of seven Likert sub-questions relating to
“
To be effective, we had to think of basic ways
students’ perceived social distances. Thus, we com- to explain particular concepts and terms that
bined seven Likert questions ranging from 0–4 into
a single response ranging from 0–28 that produced
made sense to the research groups. … We
more precise and powerful analyses.
had to remember how our first statistics pro-
Early Challenges: Back to the Basics fessors explained the difference between
One of our more definitive challenges involved
categorical and quantitative data
learning the utilities of a statistical software program
used within the sociology discipline, SPSS. Each of
”
.
us was familiar with STATA, Minitab, and R, hav-
ing used them in our statistics courses; however,
we were all new to SPSS. While the program is
relatively user-friendly, we struggled to find ways
learned the different connotations that terms such
to organize and code the data to create graphi-
as “gender,” “a college hook-up,” and “transgender
cal representations during our preliminary and
and transsexual roles” could have within our campus
exploratory analysis. While two of us stayed with-
society and how important it was to accurately define
in the SPSS program and learned the intricacies
them in our study if we wanted to produce relevant
of using it is a statistical software tool, one of us
data. Overall, our ability to define and learn differ-
brought the data into R to create representations
ent terms across the two disciplines was a beneficial
in a more familiar environment.
and necessary first step in the consulting process.
Another challenge was learning how to commu-
nicate across two disciplines. For instance, it was dif-
Defining Our Role: Forming Questions
ficult for us to use terms such as “nonparametric,”
Upon meeting with the groups, our first task was
“quantitative response,” or “logistic regression” when
to help them brainstorm about how they might
our peers had few experiences with statistical analysis
improve their research questions and hypotheses.
prior to this study. To be effective, we had to think of
With limited space on the survey reserved for each
basic ways to explain particular concepts and terms
group, it was important that they have specific ques-
that made sense to the research groups. This chal-
tions in mind. We also encouraged them to think
lenge took us back to the basics of our statistical
ahead to the data analysis stage—do the questions
education. We had to remember how our first statis-
they ask provide the outcomes necessary to assess
tics professors explained the difference between cat-
their hypotheses? We worked together to formulate
egorical and quantitative data. Additionally, we had
questions that would yield responses addressing their
to define nonparametric as a “less restrictive” tech-
primary and secondary research questions.
nique to understand associations between response
As statisticians, we tried to quantify as many vari-
and predictor variables. We also remembered our
ables as possible, which can be challenging when it
basic understanding of the odds as “the probability
comes to asking questions about attitudes or emo-
of a success divided by the probability of a failure.”
tions. Eventually, we were able to find solutions that
We did have some humorous misunderstandings,
would satisfy both parties, such as building Likert
such as when Sheppard stared at us in shock as we
scale indexes or including quantitative responses for
discussed the “gender discrimination” that occurred
outcomes such as the total number of relationships
during our statistical test. Consequently, the com-
a subject had during a given period. It was helpful
munication challenges forced us to have a complete
for us to have a look at the electronic questionnaire
understanding of some of the statistical tools and
before it was sent out because we were able to think
terms we thought we already knew.
ahead to make suggestions for how to collect and
Challenges also arose when we met with the
code the data. We also were able to start thinking
research groups to discuss their primary research
as a consulting group about how we might analyze
questions. When we listened to their hypotheses,
the data.
we became familiar with the etiologies of some of
What was more important to explain early on
the terms used within sociology. For instance, we
was our intended role as undergraduate statistical
SEPTEMbER 2009 AMSTAT NEwS 49
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80