Chapter 2 and 3 Flashcards
What is important to note when using the Theoretical approximations of the sampling distribution?
We can only make educated guesses/assumptions about the population requirements considering our sample
Differences between Independent and Dependent samples
Independent samples are not affected by each other and are drawn separately from the population.
Dependent samples are used for comparing two means from the same sample
Definition of Point estimate
Using a sample statistic value as the best guess to name a parameter (if estimator is unbiased)
Definition of Interval estimate
Range of scores for sample statistics in a sampling distribution which are closest to the mean
Why is the width of an interval important?
The width is important because it is the precision of our estimate.
The wider the estimate, the less precise our estimate
What is a standard error?
It’s the standard devition of the sampling distribution (expressed in z-scores)
Why are critical values useful?
For standardizing the sampling distribution. They separate the sample statistics outcomes that are the closest to the paramter (depends on the confidence level)
Calculate the Confidence interval lower and upper limit
Confidence interval lower limit = sample value – critical value * standard error
Confidence interval upper limit = sample value + critical value * standard error
Important things to consider about the confidence interval
- It is linked to probablity
- It’s NOT a probability that a parameter has a particular value or that it falls within the interval, because a parameter is NOT a random variable and is not affected by the random sample that we draw
What does approximating sampling distribution with theoretical probability distribution mean?
using critical values & standard error to calculate CI
