Transcript Fri. Jan. 11

Stat 100
Jan. 11
To Do
• Chapter 7, Try problems 1-5,10-15
What we’ve done so far
• Mon. – defined statistics as being about
gathering and analysis of sample data in
order to generalize about larger populations
• Wed. Discussed ways to collect data for the
purpose of comparing groups or conditions
Today – Intro to descriptive
statistics
• Methods for summarizing a batch of
numbers
Example 1
• 189 students asked what’s fastest they’ve
ever driven, data shown below -
Question
What facts would you like to
know about the observed fastest
ever driven data?
Measures of “average”
• Median = middle, half are smaller, half are
larger
• Mean = usual average, add up all values
divide by number of values
Example 2
• Suppose five students say the number of
CDs they have are: 20, 30, 60 , 100, 500
• What’s the median?
• Median = 60
• What’s the mean?
• Mean = (20+30+60+100+500)/5 = 142
Example 2 continued
• In our example 2, why was the mean larger
than the median?
• Largest value (500) was much larger than
others and pulled up the mean.
• Mean is affected by extreme values, median
is not
Five Number Summary of
Variation
• Median
• Lower quartile (25th percentile)= ¼ are
smaller and ¾ are larger
• Upper Quartile (75th percentile) = ¾ are
smaller and ¼ are larger
• Lowest
• Highest
5 Number Summary for fastest
ever driven
•
•
•
•
•
Median=95
Lower Quartile = 85
Upper Quartile = 110
Lowest = 30
Highest = 150
Graph of 5-number summary
• Called a boxplot
Histogram
• Create data categories
• Determine number and/or percent in each
category
• Draw a bar chart showing the results
Data “Shape”
• Symmetric - about the same pattern of
values on both sides of the median
• Skewed - data stretches further from the
median on one side than on the other
Example 3 Symmetric shape
Example 4 Skewed Shape