1: Descriptive Statistics Flashcards
Time series data
observations on the values a variable takes over time. for example, quarterly GDP
cross-sectional data
data of individuals, households, firms, cities, states, countries, or other units of interest at a specific point in time.
obtained from random sampling of underlying population
for example, class results on a certain test
panel data
the same cross-sectional units are followed over time
used to model lagged responses
pooled cross sections
data configuration where independent cross sections, usually collected at different points in time, are combined to form a single data set
positive skewness
there are positive outliers, positive extreme values
negative skewness
there are negative outliers, negative extreme values
positive kurtosis
more peaked than normal
there are more observations around the mean
negative kurtosis
less peaked than normal
observations are more evenly spread
zero kurtosis
equivalent to the normal distribution
skewness formula
=((1/(N−1)) ∑▒(y_i−y ̅ )^3 )/((σ^2 )^(3/2) )
kurtosis formula
=((1/(N−1)) ∑▒(y_i−y ̅ )^4 )/((σ^2 )^2 )
correlation and covariance
measure the extent to which two variables move together
covariance has units
correlation has no units and ranges from -1 to 1