QUANTITATIVE SKILLS EXAM
QUESTIONS AND COMPLETE
SOLUTIONS GRADED A+
Your Exam Plug
, What is meant by "the counterfactual"? How is it helpful for understanding whether a causal
relationship exists between two variables (or events)? - Answer: The "counterfactual" is what would
have happened had something else (that didn't actually happen) happen - What would have happened
to Europe had the U.S. not entered WWII? This is the counterfactual, which, by its nature, means we
can't know it for sure.
One of the three tasks involved in understanding causes is to compare the observed results to those you
would expect if the intervention had not been implemented - this is known as the 'counterfactual'.
What is the difference between a "normal" and a "skewed" distribution. Also understand what the
consequences are for the mean and median when a distribution is positively vs. negatively skewed? -
Answer: But also, the shape of the distribution is important: • When working with symmetrical (aka,
"normal") distribution, we can use various measures of central tendency: - Mean, median, and mode will
be the same. » Mean is generally what is used. • But when working with skewed distribution, the
"shape" of the data dictates which measure is best (more on this below) - Note: Here, "best" means
most informative. The whole point of looking at these statistics is to quickly learn something valuable
about whatever variable we're studying
Note: "skewness" is a matter of degree; amount of skewness can be calculated • For skewed
distributions or when there are outliers, mean does not equal (=/=) median
In positively skewed dist., the mean gets pulled to the right of the median; in negatively skewed dist.,
mean gets pulled to the left of the median
Levels of measurement (aka, "measurement metric): Understand the difference between
categorical/nominal, ordinal, and continuous-level variables. Be able to identify examples of each -
Answer: There are three (technically four) types of variables, categorized according to the metric in
which the values of the variable occur: categorical/nominal , ordinal, and continuous (interval and ratio).
Categorical variables are variables whose values simply indicate a particular category—the values do not
have any natural ordering. - That is, we cannot logically number the values in terms of lowest to highest
because higher values will not signify more of something
Dichotomous ("dummy") variables—i.e., variables that have two values. For example, answering "Yes"
or "No" to a question; indicating whether you are or are not Female; indicating whether you are or are
not receiving government assistance
The distinction between ordinal and categorical variables is that we can order the values such that
higher numbers mean more of something, and lower numbers mean less. - BUT the conceptual
difference between each value of an ordinal variable is not equal
An important characteristic that ordinal variables do not have is equal unit differences. • The metric in
which we measure a variable has equal unit differences if a one-unit increase in the value of that
variable indicates the same amount of change across all values of that variable. Continuous variables are
variables that do have equal unit differences. - Example: Age (in years)
QUESTIONS AND COMPLETE
SOLUTIONS GRADED A+
Your Exam Plug
, What is meant by "the counterfactual"? How is it helpful for understanding whether a causal
relationship exists between two variables (or events)? - Answer: The "counterfactual" is what would
have happened had something else (that didn't actually happen) happen - What would have happened
to Europe had the U.S. not entered WWII? This is the counterfactual, which, by its nature, means we
can't know it for sure.
One of the three tasks involved in understanding causes is to compare the observed results to those you
would expect if the intervention had not been implemented - this is known as the 'counterfactual'.
What is the difference between a "normal" and a "skewed" distribution. Also understand what the
consequences are for the mean and median when a distribution is positively vs. negatively skewed? -
Answer: But also, the shape of the distribution is important: • When working with symmetrical (aka,
"normal") distribution, we can use various measures of central tendency: - Mean, median, and mode will
be the same. » Mean is generally what is used. • But when working with skewed distribution, the
"shape" of the data dictates which measure is best (more on this below) - Note: Here, "best" means
most informative. The whole point of looking at these statistics is to quickly learn something valuable
about whatever variable we're studying
Note: "skewness" is a matter of degree; amount of skewness can be calculated • For skewed
distributions or when there are outliers, mean does not equal (=/=) median
In positively skewed dist., the mean gets pulled to the right of the median; in negatively skewed dist.,
mean gets pulled to the left of the median
Levels of measurement (aka, "measurement metric): Understand the difference between
categorical/nominal, ordinal, and continuous-level variables. Be able to identify examples of each -
Answer: There are three (technically four) types of variables, categorized according to the metric in
which the values of the variable occur: categorical/nominal , ordinal, and continuous (interval and ratio).
Categorical variables are variables whose values simply indicate a particular category—the values do not
have any natural ordering. - That is, we cannot logically number the values in terms of lowest to highest
because higher values will not signify more of something
Dichotomous ("dummy") variables—i.e., variables that have two values. For example, answering "Yes"
or "No" to a question; indicating whether you are or are not Female; indicating whether you are or are
not receiving government assistance
The distinction between ordinal and categorical variables is that we can order the values such that
higher numbers mean more of something, and lower numbers mean less. - BUT the conceptual
difference between each value of an ordinal variable is not equal
An important characteristic that ordinal variables do not have is equal unit differences. • The metric in
which we measure a variable has equal unit differences if a one-unit increase in the value of that
variable indicates the same amount of change across all values of that variable. Continuous variables are
variables that do have equal unit differences. - Example: Age (in years)
