Quantitative Methods - Hypothesis Testing - Hypothesis Tests and Types of Errors Flashcards
define a hypothesis
a statement about a population’s parameter
what are the 7 steps in hypothesis testing?
1) state the hypothesis
2) select a test statistic
3) specify the level of significance (probability in the tails)
4) state the decision rule for the hypothesis
5) collect the sample and calculate statistics
6) make a decision about the hypothesis
7) make a decision based on the test results
what is the null hypothesis?
- the hypothesis to be tested
- what the researcher wants to reject
- always includes the equal sign
- contains equals sign, greater or equal to sign or less than or equal to sign
that is the alternative hypothesis?
- what the researcher would like to conclude
- what is concluded if the researcher rejects the null hypothesis
what are the two outcomes an alternative hypothesis can be?
one or two sided
what is the difference betwene a one and two sided test?
one-tailed: if your alternative hypothesis is either greater than or less than your null hypothesis
two-tailed: allow for deviation on sides of the hypothesised value (0). whenever the alternative hypothesis doesn’t equal the null hypothesis
what are the two components that make up a test statistic
- calculated from sample data
- compared to critic value(s) to test the null hypothesis
what are critic values similar to?
confidence intervals
what is a type I error? What is the probability of the error?
the rejection of a null hypothesis when it is actually true e.g. value falling into tail
- the significance level
what is a type II error? what is the probability of the error?
the failure to reject a null hypothesis when it is false
- the power of a test is 1 - the probability of a type II error
what is the decision for a hypothesis test?
reject the null hypothesis or fail to reject the null hypothesis (aka the decision rule)
explain a decision rule and relationship between confidence intervals and hypothesis tests
we set up confidence intervals around our sample/point estimate and see whether the value falls in these to reject/accept the null
e.g. if a hypothesized mean falls outside the confidence interval for the population mean, we reject the hypothesis that the population mean = hypothesised mean
what are possible reasons for statistical significance not necessarily implying economic significance
- transaction costs
- taxes
- risk