The topic being surveyed revolved around the subject of curricular activities.
I conducted
the survey by asking my friends from school and texting others for data for my questions. The
sample was selected with bias. I have concluded that I truly did not select random people as I
only surveyed people that I knew, defeating the element of the survey being random to make it
a more accurate survey to represent a wide range of people.
Part A:
Frequency Table
Subject Frequency
Math 13
Science 8
History 4
English 5
Pie Chart
Pareto Chart
Conclusion:
From the data we can conclude that the most liked to least liked subjects in
the sample follow in the order: math, science, English, and science. Using the
mode, we can conclude that math is the most liked subject as the option of
math has a frequency of 13 in the sample; 13 is the mode. We can also
make the connection that the stem subjects of math and science are more
liked relative to the subjects of English and history, as well as the fact that
science and math correlate one another from a conceptual perspective.
Part B:
Box Plot
Information:
Mean:6.46666666667
Mode:6
Standard Deviation:2.609443504
Median:6
Five Number Summary: 2,5,6,8,14
Outlier:14
Conclusion:
The mean and median are 6.4666667 and 6, respectively. My graph is
skewed towards the right with a big drop in the last two classes, with one
outlier at 14. I am not surprised by the outlier as 14 hours of studying a week
for me is extreme as with school and other activities that is dedicating 2
hours of studying every day. I noticed on average a lot of people dedicate 1
hour of studying their favorite subject; studying 6-7 hours a week. This I feel
is a balanced time, which I am close to personally as I sit at 8-9 hours a
week.
Part C:
Scatter Plot
Information:
Regression equation for the best fit line: y=-0.686x+10.47
Correlation Coefficient: -0.6262
Conclusion:
The explanatory variable is the number of hours spent studying, and the
response variable was the number hours spent on extracurriculars. The
graph has a linear relationship with a correlation coefficient of –0.6262,
which is slightly different from what I expected as I thought it would have a
strong correlation closer to –1. The regression line has a negative slope with
a y-intercept of 10.47. This implies that the more hours spent on studying
reduces the time spent on extracurriculars. The y-intercept is possible but
very unlikely from the sample which I took as I took people that are currently
in school. In the future, I predict more extracurricular hours relative to my
sample.
Part D:
1. The explanatory variable is weight, and the response variable is
highway MPG.
2. Y=0.006x+47.942
3. Correlation Coefficient: -0.85369; It has represented a strong
correlation as it close to -1
4. The slope of the line implies that as the weight increases, the MPG will
gradually decrease. The y-intercept shows that when the weight is
1500, the MPG will be around 47.942.
Reflection:
One thing I would do differently is take a better sample by asking people in
my neighborhood, including people I may not know, to do a better job of
respecting the randomness of my sampling.
