MGT 496 Lecture Notes - Lecture 3: Type I And Type Ii Errors, Null Hypothesis, Test Statistic
Document Summary
Set a p-value (researcher"s prerogative, but often 0. 05), a threshold for your test statistic (for error) P-value - probability that you are wrong when you reject the null hypothesis, and conclude that relationship exists. Type 1 error - false rejection of the null hypothesis. Run the proper statistical test; get a test statistic. Reject the null hypothesis if the test statistic"s p-value is less than your threshold (ie. p < 0. 05) P-value represents your threshold for (type i) error. If you do not reject the null (ie. p > 0. 05), you conclude the correlation is not a real" relationship, regardless of its size. Only interpret correlations as having a relationship that are not rejected by your test of statistical significance. For statistically significant correlations, ask how related are the two variables?". Objects are rank-ordered according to how much of attribute they possess. Differences between points on measurement scale are equal. Equal differences between scale points (same as interval)