chapter 3 bivariate data. do tall people have big heads? collect data –enter your height (in...
TRANSCRIPT
![Page 1: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/1.jpg)
Chapter 3
Bivariate Data
![Page 2: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/2.jpg)
Do Tall People Have Big Heads?
• Collect Data– Enter your height (in inches) and your
head circumference (in cm) into my calculator. Be as exact as possible!
• Graph a scatterplot – label x-axis and y-axis
• Describe the bivariate data
![Page 3: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/3.jpg)
Scatter Plots VocabularyExplanatory Variable (x) and
Response Variable (y)Changes in x explain (or even cause) changes in y.
Describe a scatterplot• Direction: positive or negative• Form: linear or not (power and
exponential in Ch 4)• Strength: correlation• Outliers: are there outliers present
![Page 4: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/4.jpg)
Correlation (r)( measures strength of a
scatterplot)• r is between -1 and 1• r = 1 and r = -1 are perfect linear
associations• r does not change if you change units
(feet to inches, etc)• r ONLY measures LINEAR association• r is not resistant (it is strongly affected
by outliers)
![Page 5: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/5.jpg)
Least Square Regression Lines
orRegression Equations
(a.k.a. Line of Best Fit)
![Page 6: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/6.jpg)
Is your 1st term grade in AP stats a good predictor of your 1st
semester grade?1st Term 1st Sem
61 73
74 73
77 85
64 64
82 78
87 85
95 97
![Page 7: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/7.jpg)
observed y
predicted y
error = observed - predictedyy ˆ
Mrs. Pfeiffer’s AP Stats Class Averages
![Page 8: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/8.jpg)
Where did it get it’s name?
The sum of all the errors squared is called the total sum of squared errors (SSE).
Calculate the error (residual) and square it.
![Page 9: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/9.jpg)
Four Key Properties of LSR
The LSR passes through the point The LSR sum of residuals (errors) is zero.The LSR sum of residuals squared is an
absolute minimum.The histogram of the residuals for any value
of x has a normal distribution (as does the histogram of all the residuals in the LSR)—constant variance.
yx,
![Page 10: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/10.jpg)
You MUST know how to Calculate a Least Squares Linear Regression
Equation using the formulas
LSRL:
Slope:
Intercept:
xbbybxay o 1ˆor ˆ
x
y
s
srb 1
xbybo 1
![Page 11: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/11.jpg)
Using the output for the graph of the class averages, answer the following questions:
1. Write the LSR equation.2. Interpret the slope and y-intercept.3. What is the value of the correlation coefficient?4. If your term grade is 65%, at what percent
would you predict your semester grade?
3.77x 95.11xs 52.10ys4.79y 766.2 r
![Page 12: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/12.jpg)
Interpret SLOPE and Y-INTERCEPT
SLOPE As x increase by 1, y increases (or decreases) by slope .
Y-INTERCEPT When x = 0, y is predicted to equal y-intercept .
![Page 13: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/13.jpg)
Extrapolation (pg 203)Residuals (pg 214)Coefficient of Determination r2 (pg 223)Outliers and Influential Points (pg 237)Lurking Variables (pg 239)
![Page 14: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/14.jpg)
Predicting outside the range of values of the explanatory variable, x. These predictions are typically inaccurate.
Example:
Men’s 800 Meter Run World Records
What reservations you might have
about predicting the record in 2005?
YEAR RECORD
1905 113.4
1915 111.9
1925 111.9
1935 109.7
1945 106.6
1955 105.7
1965 104.3
1975 104.1
1985 101.73
1995 101.73
![Page 15: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/15.jpg)
Residual = observed y – predicted y=
To Graph: Plot all points of the form (x, residual)Good Residual Plot: Scattered (conclude that the
regression line fits the data well)Bad Residual Plot: Curved or Megaphone (conclude that
the regression line may not be the best model, possibly a quadratic or exponential function may be more appropriate)
Look at graphs on pages 216 – 218
𝑦− ��
![Page 16: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/16.jpg)
This is exactly what you think it is…the correlation (r) squared.
ALWAYS EXPRESSED AS A PERCENT!
Example 1: Height explains weight. Not totally, but roughly. Suppose r2 is 75% for a dataset between height and weight. We know that other things affect weight, in addition to height, including genetics, diet and exercise. So we say that 75% of a person's variation in weight can be explained by the variation in height, but that 25% of that variation is due to other factors.
Example 2: Suppose you are buying a pizza that is $7 plus $1.50 for each topping. Clearly, Price = 7 + 1.50(of toppings). Clearly, r and r2 are 1 and 100%. Does this mean that the number of toppings 100% determines my cost? No, clearly the $7 base price has a lot to do with the price! However, my variation in price is explained 100% by the variation in the number of toppings I choose.
![Page 17: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/17.jpg)
How do you INTERPRET it? Use this sentence:
The percent of the variation in y is explained by the linear relationship between y and x .
Example: 97% of the variation in word record times is explained by the linear relationship between world record times and the year.
![Page 18: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/18.jpg)
An OUTLIER is an observation that lies outside the overall pattern of the other observations. Points can be outliers in the x direction or in the y direction.
An INFLUENTIAL POINT is an outlier that, if removed, would significant change the LSRL. Typically, outliers in the x direction are influential points.
![Page 19: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/19.jpg)
Child 18 is an outlier in the x direction.
Child 19 is an outlier in the y direction.
Child 18 is an influential point.
Child 19 is not an influential point.
![Page 20: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/20.jpg)
A LURKING VARIABLE is a variable that is not among the explanatory or response variables in the study and yet may influence the interpretation of relationships among those variables.
Example: Do big feet make you a better speller? Children with larger shoe sizes in elementary school were found to be better spellers than their small footed schoolmates. Why?
![Page 21: Chapter 3 Bivariate Data. Do Tall People Have Big Heads? Collect Data –Enter your height (in inches) and your head circumference (in cm) into my calculator](https://reader036.vdocument.in/reader036/viewer/2022062421/56649cf35503460f949c12df/html5/thumbnails/21.jpg)
Association does not imply Causation!
x and y can be associateda change in x cannot CAUSE a
change in y(unless you have performed a well-designed,
well-conducted experiment)