Chapter 3&4; testing a man, z/t-tests Flashcards
Standard Error of a statistic can be described as
the expected error of that statistic as an estimator for its parameter
When testing a mean or proportion, the standard error is equivalent to the standard deviation of our
sample statistic
A population distribution represents the
Entire distribution of a particular variable
A sample data distribution is the
distribution of measurements collected from our sample
As sample size increases, your sample distribution will converge in _____ to the _________________________
shape ; population distribution
A sampling distribution is the general name for the ________________________________
distribution of a sample statistic
As sample size increases, the sampling distribution of the sample mean will converge in ________ to the ____________________
value ; population mean
Parametric tests assume the
Null Model will be normally distributed and use calculus to find the p-value precisely based on the position of our sample statistic relative to the distribution
Every normally distributed variable can be defined by two values
- the mean
- the standard deviation
z scores represent the
standardized position of values in a normal distribution
Negative z scores mean the data point is
below the mean
Positive z scores mean the data point is
above the mean
The z score value represents
how many standard deviations the point is away from the mean
z-test for a proportion
the distribution of p-hat is reasonably approximated by a normal distribution
z-test for a mean
- sigma is known or well approximated with our sample (ex. when n>100)
- the distribution of x-bar is normally distributed
t-test for a mean
- sigma is unknown and estimated by s
- the distribution of x-bar is normally distributed