Outliers and Misleading Data

How can you identify outliers in a scatter plot?

• Outliers are always the highest values in the dataset.

• Outliers can be identified as points that are far removed from the main cluster of data in a scatter plot.

• Outliers are points that are close to the main cluster of data.

• Outliers can only be identified using a line graph.

When there are outliers present, we refer to this as

• multimodal

• skew

• symmetric

• normal

When a data set has outliers, the following measure of center can be misleading:

• mean

• median

• mode

• range

Explain why this graph may be misleading?

• the x-axis does not have equal intervals

• San Fransisco is not a real city

• you cannot have percents in a line graph

• the y-axis does not have equal intervals

Which data point did the statistician exclude?

• (2.3, 11.0)

• (4.2, 16.5)

• (6.4, 23.1)

• (8.2, 24.3)

What is misleading about this graph?
**choose the best answer

• Nothing is misleading about this graph.

• The democrats are too high.

• The y-axis does not start at zero, so it makes the democrats look much higher than the other two parties.

The dotplot below shows the number of televisions owned by each family on a city block. Which of the following statements is true?

• The distribution is skewed to the right without any outliers.

• The distribution is skewed to the left with one outlier.

• The distribution is skewed to the left without any outliers.

• The distribution is skewed to the right with one outlier.

The list below shows the number of baseball cards seven people own.

130, 142, 145, 145, 150, 163, 121

An eighth person owns 842 baseball cards. What effect does the eighth person have on the distribution of the data?

• The data distribution will become skewed to the left.

• The data distribution will become skewed to the right.

• The data distribution will become more symmetrical.

• The data distribution will become less spread.

If outliers are removed, what changes more significantly the standard deviation or interquartile range (IQR)?

• Standard Deviation

• Interquartile Range (IQR)

The students in Mr. Tyson’s high school statistics class were recently asked if they would prefer a pasta party, a pizza party, or a donut party. The following bar graph displays the data. This graph is misleading because

• the bars should be arranged in decreasing order by height.

• the vertical axis scale should start at 0.

• there should not be gaps between the bars.

• it should be a histogram, not a bar graph.

• preferred party should be on the vertical axis and number of students should be on the horizontal axis.