What is a statistically significant variable?
Q: What is a statistically significant variable?
A: A variable is statistically significant if under a certain status quo assumption, the probability of obtaining its outcome (or a more extreme outcome) is less than a given value.
Q: What is statistical significance used for?
A: Statistical significance is used to determine the unlikeliness of an experimental result when a certain status quo assumption is assumed to be true.
Q: What are statistical hypothesis tests used for?
A: Statistical hypothesis tests are used to check significance.
Q: Who originated the concept of statistical significance?
A: Ronald Fisher originated the concept of statistical significance in his 1925 publication, Statistical Methods for Research Workers, when he developed statistical hypothesis testing.
Q: What cutoff level did Fisher suggest to reject the null hypothesis?
A: Fisher suggested a probability of one in twenty (0.05 or 5%) - as a convenient cutoff level to reject the null hypothesis.
Q: Who recommended that the significance level be set before any data collection?
A: Jerzy Neyman and Egon Pearson recommended that the significance level (for example 0.05), which they called α, be set before any data collection.
Q: Did Fisher intend the cutoff value of 0.05 to be fixed?
A: No, Fisher did not intend this cutoff value to be fixed. In his 1956 publication Statistical methods and scientific inference, he recommended that significant levels be set according to specific circumstances.