GSE Coordinate Algebra Unit 4 – Describing Data
Name:
How to Compare Distributions
When you compare two or more data sets, focus on four features:
ê Center. Graphically, the center of a distribution is the point where about half of the observations are on either side.
ê Spread. The spread of a distribution refers to the variability of the data. If the observations cover a wide range, the spread is larger. If the observations are clustered around a single value, the spread is smaller.
ê Shape. The shape of a distribution is described by symmetry, skewness, number of peaks, etc.
ê Unusual features. Unusual features refer to gaps (areas of the distribution where there are no observations) and outliers.
SPREAD
The spread of a distribution refers to the variability of the data. If the data cluster around a single central value, the spread is smaller. The further the observations fall from the center, the greater the spread or variability of the set.
Less Spread
More Spread
SHAPE
The shape of a distribution is described by symmetry, number of peaks, direction of skew, or uniformity
Symmetric, Unimodal, Bell-shaped Symmetric, Bimodal
Skewed Left
Skewed Right
Uniform
Non-Symmetric, bimodal
UNUSUAL FEATURES
Sometimes, statisticians refer to unusual features in a set of data. The two most common unusual features are gaps and outliers.
Gap
Outlier
Measure of Dispersion:
How the data is spread over the central value is called dispersion.
Definition: A measure of variation in a set of numerical data, computed by adding the distances between each data value and a Central value, then dividing by the number of data values.
If x1, x2, x3… xn are n data items with mean then mean absolute deviation (MAD).
Mean deviation can also be calculated using median or mode.
How to find MAD?
Step 1. Find the mean of the data
Step 2. Find the absolute deviations from the mean
Step 3. Find mean of absolute deviations.
Find the mean absolute deviations of the following
1. The populations of 10 largest states by land area and the smallest 10 states by land area in 2005 are given. Compare the spread of the data for the two sets using the range and the mean absolute deviation
x / / / Sum of absolutes/ x / / / Sum of absolutes
2) The salaries (in thousand dollars) for all 6 employees at business A and B are given. Compare the spread of data for the two sets using the range and the mean absolute deviation.
A: 24, 22, 18, 28, 26, and 75 B: 64, 26, 54, 20, 25, and 48
x / / / Sum of absolutes/ x / / / Sum of absolutes
3. The table shows the maximum speeds of eight roller coasters at an amusement park. Find the mean absolute deviation of the data and describe what the MAD represents.
Maximum speeds of Roller Coasters(mph)58 / 88 / 40 / 60 / 72 / 66 / 80 / 48
6. The top five salaries and the bottom five salaries for the 2010 New York Yankees are shown in the table below. Salaries are in millions of dollars and rounded to the nearest hundredth.
2010 New York Yankees Salaries( millions of ($s)Top Five Salaries Bottom Five Salaries
33.00 / 24.29 / 22.60 / 20.63 / 16.50 / 0.45 / 0.44 / 0.43 / 0.41 / 0.41
Find the mean absolute deviation of each data and describe MAD
7. The table shows the running time in minutes for two kind of movies. Find the mean absolute deviation for each data set of data. Round to the nearest hundredth. Then write few sentences comparing variations.
Running Time for Movies(minutes)Comedy / Drama
90 / 95 / 88 / 100 / 98 / 115 / 120 / 150 / 135 / 144
8.The table shows the lengths of the longest bridges in the United States and in Europe. Find the mean absolute deviation for each set of data. Round to the nearest hundredth if necessary. Then write a few sentences comparing their variation.
Longest Bridges(in kilometers)United States / Europe
38.4 / 36.7 / 29.3 / 24.1 / 17.7 / 17.2 / 11.7 / 7.8 / 6.8 / 6.6
12.9 / 11.3 / 10.9 / 8.9 / 8.9 / 6.1 / 5.1 / 5.0 / 4.3 / 3.9
Name: ______Date: ______
Scatter Plots and Line of Best Fit
MCC9-12.S.ID.6 Represent data on two quantitative variables on a scatter plot, and describe how the variables are related.
MCC9-12.S.ID.6a Fit a function to the data; use functions fitted to data to solve problems in the context of the data. Use the given functions or choose a function suggested by the context. Emphasize linear and exponential models.
MCC9-12.S.ID.6c Fit a linear function for a scatter plot that suggests a linear association.
The best fitting line or curve is the line that lies as close as possible to all the data points.
Regression is a method used to find the equation of the best fitting line or curve.
Extrapolation – the use of the regression curve to make predictions outside the domain of values of the independent variable.
Interpolation – Interpolation is used to make predictions within the domain of values of the independent variable.
Line of Best Fit by Hand:
1) The environment club is interested in the relationship between the number of canned beverages sold in the cafeteria and the number of cans that are recycled. The data they collected are listed in this chart.
a) Plot the points to make a scatter plot.
b) Use a straightedge to approximate the line of best fit by hand.
c) Find an equation of the line of best fit for the data.
2. Mike is riding his bike home from his grandmother’s house. In the table below, x represents the number of hours Mike has been biking and y represents the number of miles Mike is away from home. Make a scatter plot for this data on the grid below.
Hours (x) / 1 / 2 / 3 / 4 / 5 / 6 / 7 / 8Miles (y) / 35 / 29 / 26 / 20 / 16 / 9 / 6 / 0
a) Describe the association between the data points on the scatter plot.
b) Use a straightedge to approximate the line of best fit.
c) Find an equation of the line of best fit for the data.
d) What does the slope represent in the context of the problem? What does the y-intercept represent in the context of the problem?
e) Could you use your equation to predict how far Mike would be after 10 hours? Use mathematics to justify your answer.
Line of Best Fit using the calculator
3) Use the table below to answer the questions about the population p (in millions) in Florida.
Year, t / 2002 / 2003 / 2004 / 2005Population (millions) / 16.4 / 17.0 / 17.4 / 17.8
a) Find the best-fitting line for the data and the correlation coefficient.
b) Using this model, what will be the population in 2020?
c) Find the rank correlation and describe the kind of correlation.
4) Use the table below to answer the questions about the U.S. residential carbon dioxide emissions from 1993 to 2002. Emissions are measured in million metric tons.
Year, t / 1993 / 1994 / 1995 / 1996 / 1997 / 1998 / 1999 / 2000 / 2001 / 2002Emissions / 1027.6 / 1020.9 / 1026.5 / 1086.1 / 1077.5 / 1083.3 / 1107.1 / 1170.4 / 1163.3 / 1193.9
a) Find the best-fitting line for the data and the correlation coefficient.
b) Using this model, how many residential tons were emitted in 1990? In 2010?
c) Find the rank correlation and describe the kind of correlation.
5) Use the table below to answer the questions about the operating costs in thousands of a small business from 2000 to 2007.
Year, t / 2000 / 2001 / 2002 / 2003 / 2004 / 2005 / 2006 / 2007Operating Costs / 2.3 / 2.6 / 3.1 / 3.3 / 4.0 / 5.2 / 5.9 / 7.0
a) Find the best-fitting line for the data and the correlation coefficient.
b) Using this model, what will be the operating costs in 2015?
c) Find the rank correlation and describe the kind of correlation.
Name: ______Date: ______
Correlation
MCC9-12.S.ID.6 Represent data on two quantitative variables on a scatter plot, and describe how the variables are related.
MCC9-12.S.ID.9 Distinguish between correlation and causation.
A scatter plot is often used to present bivariate quantitative data. Each variable is represented on an axis and the axes are labeled accordingly.
A scatter plot displays data as points on a grid using the associated numbers as coordinates or ordered pairs (x, y). The way the points are arranged by themselves in a scatter plot may or may not suggest a relationship between the two variables. For instance, by reading the graph below, do you think there is a relationship between the hours spent studying and exam grades?
If y tends to increase as x increases, then the data have positive correlation.
If y tends to decrease as x increases, then the data have negative correlation.
A correlation coefficient, denoted by r, is a number from -1 to 1 that measures how well a line fits a set of data pairs (x, y). If r is near 1, the points lie close to a line with a positive slope. If r is near -1, the points lie close to a line with a negative slope. If r is near 0, the points to not lie close to any line.
Give an example of negative correlation: ______
Practice Problems:
For each scatter plot, tell whether the data have a positive correlation, a negative correlation, or no correlation. Then, tell whether the correlation is closest to -1, -0.5, 0, 0.5, or 1.
3. Positive, negative, or no correlation?
a. Amount of exercise and percent of body fat ______
b. A person’s age and the number of medical conditions they have ______
c. Temperature and number of ice cream cones sold ______
d. The number of students at Hillgrove and the number of dogs in Atlanta ______
e. Age of a tadpole, an amphibian, and the length of its tail ______
Correlation vs. Causation
When a scatter plot shows a correlation between two variables, even if it's a strong one, there is not necessarily a cause-and-effect relationship. Both variables could be related to some third variable that actually causes the apparent correlation. Also, an apparent correlation simply could be the result of chance.
Example 1: During the month of June the number of new babies born at the Utah Valley Hospital was recorded for a week. Over the same time period, the number of cakes sold at Carlo’s Bakery in Hoboken, New Jersey was also recorded. What can be said about the correlation? Is there causation? Why or why not?
Example 2: Mr. Jones gave a math test to all the students in his school. He made the startling discovery that the taller students did better than the short ones. His Causation Statement: As your height increases, so does your math ability.
What can be said about the correlation? Is there causation? Why or why not?
Example 3: In this present economy families are trying to find ways to save money Families might be thinking about not eating out to spend less money. Causation Statement: The more you eat out, the more money you spend at restaurants.
What can be said about the correlation? Is there causation? Why or why not?
Example 4:The table below shows number of students going to the field trip and number of teachers accompanying them
Field TripsStudents / 28 / 38 / 45 / 48 / 57 / 65
Teachers / 2 / 3 / 3 / 4 / 4 / 5
Find (a) the line of best-fit
b) Rank correlation/coefficient of rank. c) Is there any Causation?
d) How many teachers will have to accompany if 100 students are decided to go on a field trip?
Name: ______Date: ______
Correlation and Causation Homework
1. From the information given,
a. Determine if the correlation is positive, negative or none.
b. Estimate the correlation coefficient.
c. Is there causation? Why or why not?
2. A history teacher asked her students how many hours of sleep they had the night before a test. The data above shows the number of hours the student slept and their score on the exam. The graph is a scatter plot from the given data.
a. Determine if the correlation is positive, negative, or none.
b. Estimate the correlation coefficient.
c. Is there causation? Would this information affect your behavior the night before a test?
3. The following chart shows violent crime rates compared to high school graduation for all fifty states.
a. Determine if the correlation is positive, negative, or none.
b. Estimate the correlation coefficient.
c. Is this an illustration of cause and effect, or are these two variables simply correlated?
For the given situations below,
a. Is the association positive, negative or none?
b. Is the causation statement is true or false?
4. When you are on a diet, the less calories you eat daily vs. the more weight you lose. Causation statement: Therefore, eating less calories makes you lose weight.
5. The more ice cream consumed on a beach vs. the increased number of people who go in the water. Causation statement: Therefore, eating more ice cream on the beach makes people go in the water.
6. The more people in a family vs. the increased number of cars the family owns. Causation Statement: Therefore, the more people there are in a family determines how many cars a family owns.