hypothesis testing Flashcards
hypothesis testing
We test our hypothesis (about the population) using data from a sample
null hypothesis
the state of affairs where no effect exists
Why do we need a null hypothesis?
The null hypothesis is developed for the purpose of testing
alternate hypothesis
The alternate hypothesis describes what you will conclude if you reject the null hypothesis
the significance level
a level of probability that we consider to be low enough for us to conclude the null hypothesis is probably false
Null Hypothesis Significance Testing
- State the null and alternate hypotheses
- Specify the significance level (α)
- compute sample statistics
- Compute p-value for the test statistic
- Compare p to α; accept or reject the null hypothesis
Different forms of reliability
Internal consistency/ Test-retest reliability/ Inter-rater reliability/ Parallel form reliability
Internal reliability
the consistency of responses to questions that purport to measure the same construct
p value and hypothesis
p > .05 means a fail to reject the null hypothesis
Measurement Error
Systematic error: errors are repeated the same way/ Random error: These errors are random – they occur due to individual differences
Sampling Error
the difference between a sample statistic and the corresponding population parameter
Sampling distribution of the mean
the probability distribution of all possible sample means of a given sample size
central limit theorem
The mean of all the sample means represents the true population mean
standard error
The standard error is an estimate of the average amount by which our measurement is likely to be wrong
Non-directional hypothesis (two-tailed hypothesis)
states that there is a difference between groups, or a relationship between variables, but does not state the direction of the difference/relationship