Research conducted by: Darin
Baskin, UH-D undergraduate, as part of a class project in the summer
of 2003

Case study prepared by: Emily
Zitek

Overview

Many people believe that weather patterns influence their driving
ability. This is evidenced by the fact that there are so many
web sites and other publications dedicated to giving people tips
about how to drive in various weather conditions (see references
and links below). Additionally, car accidents are often attributed
to bad weather (e.g., see Taylor & Quinn, 1991). This study
examines the beliefs and behaviors of people with respect to this
important topic, driving in inclement weather.

The participants in this study filled out a questionnaire consisting
of some demographic questions and then questions asking about
their transportation habits and other beliefs concerning inclement
weather. This questionnaire was administered to a convenience
sample of 61 University of Houston - Downtown students at various
locations (i.e., classrooms, hallways, and the food court).

Questions to Answer Is gender
or age related to the likelihood of driving in inclement weather?
Does the number of accidents that someone thinks occur during inclement
weather relate to how often he or she takes public transportation
or chooses to drive during inclement weather?

Design Issues This is a correlational
study, so we cannot infer causation.

Descriptions of Variables

Variable

Description

Age

The age of the participant in years

Gender

1 = female, 2 = male

Cho2drive

How often he or she chooses to drive in inclement weather
1 = always, 3 = sometimes, 5 = never

Pubtran

% of travel time spent on public transportation in inclement
weather

Accident

% of accidents thought to occur from driving in inclement
weather

References

Galski, T., Ehle, H. T, & Bradley,
W. J. (1998). Estimates of driving abilities and skills
in different conditions. American Journal of Occupational
Therapy, 52, 268-275.

Griffin, J., & Murdock, G. (1993,
August). Wet weather driving. Consumers' Research Magazine,
76, 2.

Taylor, G. W., & Quinn, H. (1991,
January 14). An arctic winter rage. Maclean's, 104,
12-13.

Plot a histogram of the distribution of the ages. Using
this plot and the information from #1, determine if the
age variable is normally distributed, positively skewed,
or negatively skewed.

What is the mean percentage of time that the participants
in this study spend traveling on public transportation
during inclement weather?

What is the standard deviation of Pubtran?

What is the correlation between age and how often the
person chooses to drive in inclement weather? Is this
correlation statistically significant at the .01 level?
Are older people more or less likely to report that they
drive in inclement weather?

Is there a gender difference in the likelihood to drive
in inclement weather? Do the following exercises to find
out.

Plot side-by-side box plots of Cho2drive by gender.

What is the mean difference in how much men and
women choose to drive in inclement weather?

Perform an independent samples t test.

Is there any evidence that the assumption of homogeneity
of variance is violated?

What is the 95% confidence interval for the mean
difference?

Can you reject the null hypothesis if alpha = .05?

What is the correlation between how often a person chooses
to drive in inclement weather and what percentage of accidents
the person believes occur in inclement weather? Is this
correlation significantly different from 0?

What is the correlation between how often someone rides
public transportation in inclement weather (Pubtran) and
what percentage of accidents the person thinks occur in
inclement weather (Accident)?

Use a linear regression line to predict how often someone
rides public transportation in inclement weather from
what percentage of accidents that person thinks occur
in inclement weather. (Pubtran by Accident)

Plot the scatter plot of this data and add a regression
line.

What is the slope?

What is the intercept?

Is the relationship at least approximately linear?

Test if the slope is significantly different from
0.

What is the standard error of the estimate of the
slope?