Investigating Psychology 1 – Lecture 5 – Hypothesis Testing and Effect sizes
Hypotheses –
- Alternative hypothesis – there will be a difference or relationship between
the variables in the study
- Null hypothesis – there will be no relationship or difference between the
variables
- One tailed hypothesis – specified direction in the relationship between the
two variables or difference in the conditions – often used if literature on
the research suggests there already is a difference or relationship
- Two tailed hypothesis – predicted a relationship between the two variables
but aren’t sure which direction it will go in – use when you are unsure of
whether a relationship or difference even exists
NHST-
- Tests whether the null hypothesis should be accepted or rejected
- High value indicates a high probability that the results could occur if there is
no difference
- Low value indicates a low probability that the results could occur if there is
no difference
- Test statistics tell us how far away our distance is from no difference
Conducting a NHST –
- Start by assuming the null hypothesis = no difference is true
- Probability of getting a test statistic close to zero is high is there is actually
no difference in population
- If the probability is very low and is less than 0.05, we reject the null
hypothesis
- If the p value is less than .05, we REJECT the NULL, and accept the
alternative hypothesis (we say we think there is a difference/relationship)
Hypotheses –
- Alternative hypothesis – there will be a difference or relationship between
the variables in the study
- Null hypothesis – there will be no relationship or difference between the
variables
- One tailed hypothesis – specified direction in the relationship between the
two variables or difference in the conditions – often used if literature on
the research suggests there already is a difference or relationship
- Two tailed hypothesis – predicted a relationship between the two variables
but aren’t sure which direction it will go in – use when you are unsure of
whether a relationship or difference even exists
NHST-
- Tests whether the null hypothesis should be accepted or rejected
- High value indicates a high probability that the results could occur if there is
no difference
- Low value indicates a low probability that the results could occur if there is
no difference
- Test statistics tell us how far away our distance is from no difference
Conducting a NHST –
- Start by assuming the null hypothesis = no difference is true
- Probability of getting a test statistic close to zero is high is there is actually
no difference in population
- If the probability is very low and is less than 0.05, we reject the null
hypothesis
- If the p value is less than .05, we REJECT the NULL, and accept the
alternative hypothesis (we say we think there is a difference/relationship)
