CAUSAL
ANALYSIS
TECHNIQUES
,INDEX
• Basics
• ANOVA
• Correlations • Dummy Variables
• Bivariate Regressions • More Multiple Regression
• Adding a Variable • Moderation/ Interaction
• Multiple Regressions • Path Analysis
• Logistic Regression
,NHST - NULL HYPOTHESIS
SIGNIFICANCE TESTING
NULL HYPOTHESIS (H0)
• there is no effect (of X)/ difference in the population (all groups have the same mean
• states that a parameter has a specific value
• Can never be true: only not enough evidence to conclude that H0 is rejected or Type
• If rejected: there is at least one significant difference between the means
ALTERNATIVE HYPOTHESIS (H1)
• there is a (significant) effect/ difference in the population
• there is at least one difference in the population
• states that a parameter can have a range of values that are different from H0
• Can never be true/ false:
, ALPHA
• Alpha is proportion of possible samples from the population that are
extreme, when we assume H0 is true
• Indicates the border to critical values in T- test statistics
• Alpha level is the chance of committing a Type I error
• P-Value is chance of finding a more extreme value than found in the sam
(if H0 is true)
– Can NOT be interpreted; we always assume H0 is true
Accept H0 if p-value > alpha
Reject H0 if p-value < alpha extreme value significant effect/
difference
• Significant results: found evidence, that is inconsistent with H0
ANALYSIS
TECHNIQUES
,INDEX
• Basics
• ANOVA
• Correlations • Dummy Variables
• Bivariate Regressions • More Multiple Regression
• Adding a Variable • Moderation/ Interaction
• Multiple Regressions • Path Analysis
• Logistic Regression
,NHST - NULL HYPOTHESIS
SIGNIFICANCE TESTING
NULL HYPOTHESIS (H0)
• there is no effect (of X)/ difference in the population (all groups have the same mean
• states that a parameter has a specific value
• Can never be true: only not enough evidence to conclude that H0 is rejected or Type
• If rejected: there is at least one significant difference between the means
ALTERNATIVE HYPOTHESIS (H1)
• there is a (significant) effect/ difference in the population
• there is at least one difference in the population
• states that a parameter can have a range of values that are different from H0
• Can never be true/ false:
, ALPHA
• Alpha is proportion of possible samples from the population that are
extreme, when we assume H0 is true
• Indicates the border to critical values in T- test statistics
• Alpha level is the chance of committing a Type I error
• P-Value is chance of finding a more extreme value than found in the sam
(if H0 is true)
– Can NOT be interpreted; we always assume H0 is true
Accept H0 if p-value > alpha
Reject H0 if p-value < alpha extreme value significant effect/
difference
• Significant results: found evidence, that is inconsistent with H0
