PSYCH 301 1st Edition Lecture 10Outline of Last Lecture I. Z TestII. NHSTIII. Variability IV. QuestionsOutline of Current Lecture I. Statistical SignificanceII. ErrorsIII. Four Error ScenariosIV. QuestionsCurrent LectureI. Statistical Significance a. If p < α, reject the null hypothesisi. Results are “statistically significant”ii. “p< .05” (or“p < .01”ect.)b. If p ≥ α, do not reject the null hypothesis. This means that the groups did not differ, or thatany difference is not statistically significantc. P is ALWAYS > 0II. Errors : a. Because p > 0, there is always a chance that we reject the null hypothesis when it is actually truei. We can avoid this by selecting a lower value for α 1. The lower the α value, the more conservative you are, the harder it becomes to reject the null hypothesis2. The higher the α value, the higher the level of error, the harder it becomesto reject the null hypothesisIII. Four Error ScenariosIV.Truth(What’s going on in the real world)Null hypothesis isTRUENull hypothesis isFALSEThese notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.Decision(The decision you are making based on your data)REJECT null hypothesis(exceeds cutoff score)Type I errorαPower( 1 – β )DO NOT REJECT null hypothesis(Does not exceed cutoff score)Correct decision( 1 – α )Type II errorβa. Type I Error : Rejecting the null hypothesis when it is actually truea. α = the probability of making a type I errorb. Type I error is when there is only 1 distribution (Hₒ) c. When your sample actually came from the population (score is under the bell-shape curve and within the values of cutoff scores), but you decided to reject itd. Type I errors are more common if you use a higher α level (the largest and most common alpha level used is .05 (α=.05)e. When does a type one error happen? When the score falls outside cutoff b. Correct decision: when you CORECTLY fail to reject the null hypothesisa. Probabilities add up to 1 ( 1 – α )c. Type II error: Not rejecting the null hypothesis when it is in fact falsea. β (beta) = is the probability of making a type II errorb. This means that your sample is outside of the cutoff scores and it came from a different populationd. Power: probability the study will give a significant result if research hypothesis is truea. Power = ( 1 – β ) probabilities add up to oneb. Power depends on knowing what size difference you are looking forDifferent Cutoff ScoresV. Questions:a. Can p = 0? Why or why not?i. No, because there is always some possibility that you reject the null hypothesis when it is actually trueb. Explain how changing your alpha level affects your ability to reject Hₒ.i. Having a smaller α you are less likely to make an error and less likely to rejectii. Having a larger α you are more likely to make an error and more likely to rejectc. Explain the difference between type I errors and type II errorsi. A type I error uses α, you reject when it is true, and you only have 1 distributionii. A type II error uses β, you don’t reject when its false, and you have 2