Exam 1 Cumulative Review Flashcards
cross-sectional
data across different entities from a single period of time
time series
data on one thing across different time periods
panel data
combination of cross-sectional and time-series
probability
the proportion of an outcome is the proportion of time that outcome occurs…
getting heads on a slot machine
discrete random variable
can only take on a discrete limited number of values
continuous random variable
can take on a continuum of possible values
probability distribution
list of all possible values a random variable can take on and the probability that each occurs
cumulative probability distribution
probability that your variable is less than or equal to a certain value
expected value
the weighted average of all possible outcomes for this variable where the weights are the probabilities of each outcome
why do we care about the spread of the data?
when the variance is small, tight, the expected value is more representative of the values in the distribution
joint probability distribution
the probability that the random variables simultaneously take on certain values
example of 2 random variables
rolling a dice, flipping a coin
marginal probability distribution
This term is used to distinguish the distribution of Y alone from the joint distribution of Y and another random variable with regards to two random variables
conditional distribution
the distribution of a random variable Y conditional on another random variable X taking on a specific value
ex: given that you are batting .320, what’s the probability your salary is xxxxx
if the conditional distribution is NO different than the marginal distribution, then the two variables are ___________
independent
if the conditional distribution IS different than the marginal distribution, then the two variables are ___________
not independent
conditional expectation
the mean of the conditional distribution of Y given X
covariance of two random variables
the measure of how much two random variables “move together” or change together
if X is much bigger than it’s expected value, and Y is much bigger than it’s expected value…then the covariance will be a ______________
large and positive number
If X is much smaller than it’s expected value,
and Y is much smaller than it’s expected value,
then the covariance will be a ________
large and positive number
if two random variables are independent, their covariances will be…..
zero
correlation
measures a relationship between two variables
- always falls between -1 and 1
- if correlation =0, variables are independent
what if you add two random variables together?
the expected value of their sums is equal to the sum of their expected values
what if you add two random variables variances together?
the variance of the sum is equal to the sum of the variances PLUS two times the covariance
if you have a linear function, say y=12,000 + .8x, then the expected value is…
12,000 + .8x
z value
a z-value is how many SD’s above or below the mean a score is
what do the probabilities in the z-tables show?
what percentage of values fall below (to the left) of a certain point
is the sample mean a random variable?
yes, because it can take on lots of values
because a sample mean is a random variable, it ….
- has a probability distribution
- has an expected value
- has a variance and a standard deviation
variability in a sample average is measured in terms…
of standard error
what is meant by error in the term “standard error”?
error doesn’t mean mistake, it means the gap between the sample and the population
as the number in your sample gets bigger, the variability of your sample average gets…
smaller, dummy
sampling distribution
the distribution of the sample average
what are the two ways to look at a sampling distribution?
- when the population (from which the sample and sample average came) is normally distributed
- when the population isn’t normally distributed, or when it’s unknown
if the population has a normal distribution, then…
then Ῡ does too
if the population isn’t normally distributed, the sampling distrubtion ….
will be approximately normally distributed if n is over 30 (which means we can use the z table)