Data Driven Decisions
Data Driven Decisions
Name: Date:
Marine biologists studying the health of the ecosystem in the Lower Deschutes River in Oregon, U.S.A. sample the
rainbow trout fish population in the river every few years. The back-to-back stem and leaf plot below compares the
lengths of one hundred sampled fish in the river in 2009 and in 2015.
1. Given that the sum of fish lengths for 2009 is 3610.5 and the sum of fish lengths for 2015 is 3386.6,
find the mean length of fish in 2009 and in 2015.
2. Find the position of the median value in both data sets. Then, find the median fish length for each year.
3. For which year is there a greater difference between the mean and median? Looking at the data sets, explain why this
greater difference between the mean and median exists for that year. As a result, justify which measure of central
tendency is a better representation for the middle of that data set?
4. Find the position of Q1 and Q3 for the 2009 data set. Then, find the first and third quartile fish lengths.
2015
7. a) Between what lengths are the middle 50% of fish in 2009 and in 2015?
b) The statement of inquiry for this unit is: How populations are represented can help to establish underlying
relationships and trends in a population.
From the perspective of a marine biologist, observe the box plot representations of data above. Describe a trend that is
occurring in the rainbow trout fish population. Refer to your values in a) when answering.
9. Considering your answers to questions 7. and 8., discuss how the collection and analysis of this data connects to our
unit’s global context.
10. Is the rainbow trout length data discrete or continuous? Justify your answer.
11. Complete the frequency table for the 2015 data set.
13. Find the estimated mean for the 2015 data set using the frequency table.
14. Compare your estimated mean to the actual mean calculated in question 1. Comment on the degree of accuracy of
the estimated mean by referring to the class intervals. What would have to change about the class intervals in order to
produce a less accurate estimated mean? Explain.
15. Create a cumulative frequency curve for the 2015 data set.
Label both axes. Mark the plotted points clearly before sketching the curve.
16. The cumulative frequency curve below shows data collected in the river in 2017 for a larger sample of fish.
c) What percent of fish are 38 cm in length or less? d) What percent of fish have a length between 33 and 36 cm.?
17. Compare the shapes of the 2015 and 2017 cumulative frequency curves. What trend in fish lengths is evident over
these past two years?
18.
19. Use your frequency table from question 11. to create a histogram for the 2015 data set.
The histogram nearly has what is called a “normal distribution”. When data is normally (or nearly
normally) distributed, a “bell curve” can be used to represent it as shown in the diagram on the right.
NOTE:
Using an approximate mean of 33 and standard deviation of 6, sketch a normal curve to represent the 2015 data. Mark
the horizontal axis with the mean and the values that are 1, 2, and 3 standard deviations from the mean in both
directions.
50% + 34%
= 84%
15 21 27 33 39 45 51