Unit 3 Project: 1,000,000 Skittles!

Your Mission: Your boss is interested in knowing the weight of 100, 1,000, 100,000 or 1,000,000 candy pieces. Unfortunately, he is cheap and won’t buy you 100 pieces of candy to weigh. Luckily for you, you paid attention in Math 1 class and you know that you can use linear models to make predictions.

CCSS.Math.Content.HSA.CED.A.1 – Create equations and inequalities in one variable and use them to solve problems.

Your Process:

  1. You will first accurately weigh your container (paper cup, petri dish, beaker, etc) to know your starting weight.
  1. You will then add various numbers of candies to the container and accurately record the weight in a table. You need to record measurements for 10 different quantities of candy and fill that data into the table.
  1. Plot your data on a graph with appropriate scales. Don’t forget labels and titles!
  1. On your graph, draw a line of best fit and find the rule by hand, looking for slope and the y-intercept.
  1. Plug the data into your calculator, and using linear regression, find the rule that the calculator determines is the best fit for the data you have collected.
  1. Explain, in context of the problem, what does the slope and the y-intercept mean?
  1. Using your calculator generated y=mx+b rule, make a prediction as to how much 100 pieces of candy will weight? 1,000 pieces of candy will weigh? 100,000 pieces of candy will weigh? 1,000,000 pieces?
  1. Write a memo to your boss explaining your results and the process you used to get your results. You must include the following:
  • Summary of findings about weights of various numbers of candies.
  • Description of data collection: what data was collected? How was it collected?
  • Did you use your hand drawn or calculator model for the predictions? Were the 2 models close?
  • What was the meaning of slope and intercept in your model?
  • How did you use your y-intercept in your prediction calculations?
  • How confident are you in your predictions?

Unit 3 Project Grading Sheet

Name:______Date Submitted: ______

Data Collected

x values
y-values

Estimate best fit line (No Calculator Used) ______

Linear regression line (Using Calculator) ______

Predicted weight:

100 Pieces: ______1000 Pieces: ______

100,000 Pieces: ______1,000,000 Pieces: ______

Linear Equation Report Specifications

Points Possible / Poster must include. . . / Points Earned
15 / Labeled TABLE with at least 10 x and y paired values for each equation.
15 / A labeled coordinate grid with data points and line of best fit drawn by hand. (axis must be labeled)
15 / Correct equation in form for hand drawn line of best fit.
15 / Correct Linear Regression Equation from Calculators.
15 / Correct prediction using the linear regression equation.
Memo to boss – Typed paragraph addressing each of the items below.
3 /
  • Summary of findings about weights of various numbers of candies.

2 /
  • Description of data collection: what data was collected? How was it collected?

2 /
  • Describe the relationship between the two variables that is shown on the scatterplot. Why is a linear model a good fit for the data?

2 /
  • Did you use your hand drawn or calculator model for the predictions? Were the 2 models close?

2 /
  • What was the meaning of slope and intercept in your model?

2 /
  • How did you use your y-intercept in your prediction calculations?

2 /
  • How confident are you in that prediction?

10 / Quality Presentation: sensible layout, appropriate title, originality, colorful, pictures, etc.

Grading Rubric

4 points / 3 points / 2 points / 1 point
Table / Data is correct
Titles, labels, and units are included
Looks professional / Data is correct
Titles, labels are units are included.
Sloppy presentation / Incorrect or missing data
Missing titles, labels or units
Doesn’t look professional / Very few data pieces
Data looks incorrect
Table is unclear
Graph / Scales are appropriate
Data is plotted correctly
Line of best fit makes sense
Titles are included
Graph looks good / Scales are off or not correct
Data is plotted correct
Line of best fit makes sense
Titles are included
Graph could be neater / Scales are off or not correct
Data isn’t plotted correct
Line of best fit doesn’t work
Missing titles
Sloppy graph / Missing scales
Missing titles
Data not plotted correct
Low quality work
Equation of Line from Graph / The equation is correct
Work is shown
Correct rule is used / The equation is correct
No work is show / Either the slope or the y-intercept are found incorrectly / Neither slope nor y-intercept are found correctly
Regression Equation from Calculator / The equation is found correctly / The equation is not found correctly
Slope and y-intercept explained / The slope and y-intercept both are identified and explained in context of the problem / The slope and y-intercept are identified, but the context doesn’t make sense / The slope are the y-intercept are incorrectly identified and incorrectly explained
Predictions / Correctly uses the rules to predict the weight of various numbers of pieces
Correctly accounts for the starting value / Correctly uses the rules to predict the weight of various numbers of pieces
Doesn’t account for the starting value in prediction / Doesn’t use the rule correctly to make predictions
Does account for the starting weight / Doesn’t use the rule correctly, nor accounts for the starting weight in making predictions
Memo