Statistics help - Scatter plot, regression

Click For Summary
SUMMARY

This discussion focuses on analyzing a dataset of ten first-grade students to determine the relationship between the number of minutes spent studying spelling words and the number of incorrect answers on a spelling test. Key findings include a correlation coefficient of -0.7698, indicating a strong negative correlation, and a coefficient of determination of 68%. The slope of the best-fitting regression line is -0.4096, with an intercept of 19.1903, leading to the regression equation y = -0.4096x + 19.1903. Predictions for additional study times and the identification of outliers and influential points are also discussed.

PREREQUISITES
  • Understanding of scatter plots and regression analysis
  • Familiarity with correlation coefficients and their interpretation
  • Knowledge of the least squares method for linear regression
  • Basic statistical concepts such as residuals and outliers
NEXT STEPS
  • Learn how to calculate and interpret the residuals in regression analysis
  • Study the implications of the coefficient of determination in predictive modeling
  • Explore the concept of influential points in regression and their impact on results
  • Practice plotting regression lines on scatter plots using statistical software like R or Python
USEFUL FOR

Students, educators, and data analysts interested in understanding the fundamentals of regression analysis and its application in educational settings.

Calculator14
Messages
23
Reaction score
0
Statistics help -- Scatter plot, regression

Homework Statement



Consider the following data set for ten first grade students; the variables are the number of minutes spent learning a list of spelling words and the number wrong on the spelling test. [15 points total]

(supposed to be a chart)
STUDENT A B C D E F G H I J
MINUTES 25 28 30 31 31 35 36 38 40 50
WRONG 12 10 8 1 6 4 4 3 2 1


a. Describe the scatter plot: form, direction, and strength. [3 points]
b. Determine the value of the correlation coefficient.
c. Determine the value of the coefficient of determination (state as a percent).
d. Find the slope of the best fitting regression line for predicting number wrong.
e. Find the intercept of this regression line.
f. Present the equation of this best fitting regression line.
g. If another student now studies the list for 32 minutes, use the equation to predict his number wrong.
h. If that student’s actual number wrong is 8, determine the residual associated with this prediction.
i. Plot the regression line on your scatterplot. (submit this plot)
j. Are there any outliers? If so, give the coordinates.
k. Are there any influential points? If so, give the coordinates.
l. Suppose another student studies the list for 60 minutes. Predict his number wrong.
m. Comment on this prediction.


Homework Equations


y = mx+b
y-b=mx
??

The Attempt at a Solution



a.strong; positive
b. 4.65
c. 68%
d. ?
e. 30
f. 28
g. ?
h. ?
I don't understand how to do this, please help:(
 
Physics news on Phys.org


Calculator14 said:

Homework Statement



Consider the following data set for ten first grade students; the variables are the number of minutes spent learning a list of spelling words and the number wrong on the spelling test. [15 points total]

(supposed to be a chart)
STUDENT A B C D E F G H I J
MINUTES 25 28 30 31 31 35 36 38 40 50
WRONG 12 10 8 1 6 4 4 3 2 1


a. Describe the scatter plot: form, direction, and strength. [3 points]
b. Determine the value of the correlation coefficient.
c. Determine the value of the coefficient of determination (state as a percent).
d. Find the slope of the best fitting regression line for predicting number wrong.
e. Find the intercept of this regression line.
f. Present the equation of this best fitting regression line.
g. If another student now studies the list for 32 minutes, use the equation to predict his number wrong.
h. If that student’s actual number wrong is 8, determine the residual associated with this prediction.
i. Plot the regression line on your scatterplot. (submit this plot)
j. Are there any outliers? If so, give the coordinates.
k. Are there any influential points? If so, give the coordinates.
l. Suppose another student studies the list for 60 minutes. Predict his number wrong.
m. Comment on this prediction.


Homework Equations


y = mx+b
y-b=mx
??

The Attempt at a Solution



a.strong; positive
b. 4.65
c. 68%
d. ?
e. 30
f. 28
g. ?
h. ?
I don't understand how to do this, please help:(

Welcome to the PF.

Can you please show us your work on the answers that you were able to calculate? That will help us a lot. Thanks.
 


my work for this problem is..

b) -.4096 = (3.8137/7.1678) r
r = -.7698

c) (-.7698)^2

d) y= -.4096x +19.1903

e) m=-.4096

f) y = -.4096x = 19.1903

g) y = -.4096 (32) + 19.1903
y=6.0831

h) 8 - 6.0831 = 1.9169

i) ?

j) (31,1)

k) graphed

l) y= -.4096(60) + 19.1903 = -5.3857

m)?
 

Similar threads

Replies
7
Views
3K
Replies
6
Views
5K
  • · Replies 3 ·
Replies
3
Views
5K
  • · Replies 1 ·
Replies
1
Views
1K
  • · Replies 4 ·
Replies
4
Views
2K
  • · Replies 1 ·
Replies
1
Views
2K
Replies
26
Views
3K
  • · Replies 7 ·
Replies
7
Views
2K
Replies
12
Views
6K
  • Poll Poll
  • · Replies 1 ·
Replies
1
Views
3K