STAT 100 UIUC Midterm 2
1. what is a two way table?: Displays categorical data for two variables.
2. how is a two-way table different from a frequency table?: A frequency table analyzes one categorical variable,
and a two way table analyzes two categorical variables.
3. what are conditional relative frequencies?: relative frequencies based on only the total from a single row or
column.
4. why are conditional relative frequencies important?: they are important in understanding in relationships
between variables.
5. What is the Cramer's V Statistic?: quantified the association between two attributes.
6. When will Cramer's V be 0?: When attributes are not at all related.
7. When will Cramer's V be 1?: When attributes are perfectly related.
8. What is the side-by-side bar graph?: this is a graphical represe conditional distribution table.ntation of
There will be a group of bars representi of the response variable over each value of the explanatory the ng the
variable
values
9. How is a side by side bar graph different from a standard bar graph?: a standard bar graph has a bar that
represents a single category. There are no subdivisions within the bars themselves. A side by side bar graph
compares two or more values.
10.What does "middle 95%" mean?: the portion of data that falls within 2 standard deviations of the mean in a
normal distribution.
11.What are the three aggregate characteristics of a distribution?: Spread, shape, and location
12.What are side-by-side density plots used for?: to compare the shape and spread of two distributions.
13.What statistic is used by statisticians when comparing the spread of two distributions?: ratio of standard
deviations
14.How is ratio of standard deviations computed?: largest standard deviation between two groups divided by the
smallest standard deviation.
15.At what point would we consider one distribution to be much more spread out than the other?: If the ratio is
approx 3 or higher, then one distribution is more spread out than the other.
16.What does effect size represent?: the difference in the means divided by the standard deviation.
17.What effect size is indicative of a large difference between groups?: Over and including 0.75
18.What effect size is indicative of a small difference between groups?: under and including 0.25
1/
7
, STAT 100 UIUC Midterm 2
19.What is a scatterplot?: a plot in which each observational unit is placed as a point on a graph according to their
value for each quantitative attribute.
20.Which factor do data scientists place on the horizontal axis?: causal actor
21.How do data scientists and statisticians think about whether or not two quantitative attributes are
related?: by considering what the average value of the attribute on the vertical axis is across different values of the
attribute on the horizontal axis
22.What is a smoothed trend line?: a line through the average value of the vertical axis attribute across all values of
the horizontal axis attribute.
23.what is another name for the smoothed line trend?: line of averages
24.what does a positive trend look like?:
25.what does a negative trend look like?:
26.what does no trend look like?:
27.what is a commonly used measurement of correlation?: Kendall's Tau
28. What does it mean if Kendall's Tau is equal to 0?: the attributes are not related at all.
29.What does it mean if Kendall's Tau is equal to 1?: the attributes are perfectly related with a positive trend.
30.What does it mean if Kendall's Tau is equal to -1?: The attributes are perfectly related with a negative trend.
31.What is one way to think about the strength of a relationship when looking at a scatterplot and trend line?: If
the points are all very close to the trend line, then the relationship is strong. If the points are more spread out, then the
relationship is not as strong.
32.What is aesthetic mapping?: linking the color of each of the point to the value of a categorical attribute
33.What are the most common mappings?: color and shape of the points
2/
7
1. what is a two way table?: Displays categorical data for two variables.
2. how is a two-way table different from a frequency table?: A frequency table analyzes one categorical variable,
and a two way table analyzes two categorical variables.
3. what are conditional relative frequencies?: relative frequencies based on only the total from a single row or
column.
4. why are conditional relative frequencies important?: they are important in understanding in relationships
between variables.
5. What is the Cramer's V Statistic?: quantified the association between two attributes.
6. When will Cramer's V be 0?: When attributes are not at all related.
7. When will Cramer's V be 1?: When attributes are perfectly related.
8. What is the side-by-side bar graph?: this is a graphical represe conditional distribution table.ntation of
There will be a group of bars representi of the response variable over each value of the explanatory the ng the
variable
values
9. How is a side by side bar graph different from a standard bar graph?: a standard bar graph has a bar that
represents a single category. There are no subdivisions within the bars themselves. A side by side bar graph
compares two or more values.
10.What does "middle 95%" mean?: the portion of data that falls within 2 standard deviations of the mean in a
normal distribution.
11.What are the three aggregate characteristics of a distribution?: Spread, shape, and location
12.What are side-by-side density plots used for?: to compare the shape and spread of two distributions.
13.What statistic is used by statisticians when comparing the spread of two distributions?: ratio of standard
deviations
14.How is ratio of standard deviations computed?: largest standard deviation between two groups divided by the
smallest standard deviation.
15.At what point would we consider one distribution to be much more spread out than the other?: If the ratio is
approx 3 or higher, then one distribution is more spread out than the other.
16.What does effect size represent?: the difference in the means divided by the standard deviation.
17.What effect size is indicative of a large difference between groups?: Over and including 0.75
18.What effect size is indicative of a small difference between groups?: under and including 0.25
1/
7
, STAT 100 UIUC Midterm 2
19.What is a scatterplot?: a plot in which each observational unit is placed as a point on a graph according to their
value for each quantitative attribute.
20.Which factor do data scientists place on the horizontal axis?: causal actor
21.How do data scientists and statisticians think about whether or not two quantitative attributes are
related?: by considering what the average value of the attribute on the vertical axis is across different values of the
attribute on the horizontal axis
22.What is a smoothed trend line?: a line through the average value of the vertical axis attribute across all values of
the horizontal axis attribute.
23.what is another name for the smoothed line trend?: line of averages
24.what does a positive trend look like?:
25.what does a negative trend look like?:
26.what does no trend look like?:
27.what is a commonly used measurement of correlation?: Kendall's Tau
28. What does it mean if Kendall's Tau is equal to 0?: the attributes are not related at all.
29.What does it mean if Kendall's Tau is equal to 1?: the attributes are perfectly related with a positive trend.
30.What does it mean if Kendall's Tau is equal to -1?: The attributes are perfectly related with a negative trend.
31.What is one way to think about the strength of a relationship when looking at a scatterplot and trend line?: If
the points are all very close to the trend line, then the relationship is strong. If the points are more spread out, then the
relationship is not as strong.
32.What is aesthetic mapping?: linking the color of each of the point to the value of a categorical attribute
33.What are the most common mappings?: color and shape of the points
2/
7
