Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with
or
.
Download ZIP
Branch: master
Fetching contributors…

Cannot retrieve contributors at this time

36 lines (34 sloc) 1.977 kB
Interential Statistics
* Statistics used to draw conclusions about your data and how they can be applied to other groups
Definitions
* Population: All members of some predefined groups
* Sample: Some subset of the population
* Statistic: a numerical index (e.g., mean) based on sample data
* Parameter: a numerical index based on population data
Inferential Statistics
* Sometimes we can study all members of a population, especially when they are a small group
* Other times, we can't and so we need to sample from the population to whom we wish to generalize
* Basically, alllows you to say how well your data apply to the larger population of which you want to generalize to
* It relies on sampling distrbutions for making probabilitic statements about the populations based on sample data
Remember Hypothesis testing?
* What is the Null Hypothesis?
* No relationship
* What is the Alternative Hypothesis?
* There is a relationship
* What are the two possible outcomes we can have?
* We can reject null hypothesis
* Fail to reject
Hypothesis Testing as Distributions
* The Null Hypothesis suggests that our two sets of data come from the same population distribution
* The Alternative Distribution suggests that they come from different populations
* If they come from different populations we should be able to see the difference
Alpha Level
* The Alpha level: The probability of obtaining your particular result if the null hypothesis is really true
* If you reject the null at Alpha = .05, then it means you believe the probability is very low (5 out of 100) that your research outcome is due to chance.
Why .05?
* In reality, it is an arbitrary number that developed over the years
* But it still makes sense
* Remember the Normal Distrbution
One-Tailed vs Two-Tailed tests
* Sometimes we are just interested in one groul being different from another
* Other times we are interested in one group being not only different, but better or worse than another group
Jump to Line
Something went wrong with that request. Please try again.