PSYCH 301 1st Edition Lecture 7Outline of Last Lecture I. Samples and PopulationsII. Null Hypothesis Significance Testing (NHST)III. QuestionsOutline of Current Lecture I. Null Hypothesis Significance Testing (NHST)II. Statistical significanceIII. One- / Two-Tailed HypothesesIV. Relating P to the Comparison DistributionCurrent LectureI. Null Hypothesis Significance Testing (NHST)a. Research Question: Does drinking coffee affect adults’ IQ?b. Step 1: Restate the question as a research hypothesis and a null hypothesis about the populationsi. Null hypothesis: there is no difference in IQ between coffee-drinking adults and non-coffee-drinking adultsii. Research hypothesis: there is some difference in IQ between coffee-drinking adults and non-coffee-drinking adultsc. Step 2: Determine the Characteristics of the comparison distributioni. For population IQ, μ=100 and σ=15d. Step 3: determine the cutoff sample score on the comparison distribution at which the null hypothesis should be rejectedi. 30 point difference (IQ > 130 or IQ < 70)These 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.ii. Do NOT reject if sample score is within the critical valuese. Step 4: determine your samples score on the comparison distributioni. Sample score = 140f. Step 5: determine whether to reject the null hypothesisi. 140 is further away from the mean than the cutoff score, se we reject Hₒg. Step 6: Interpret your resultsi. Adults who drink coffee differ in mean IQ from adults who do notII. Statistical significancea. The p value conveys whether the null hypothesis should be rejected or notb. P = the probability of observing these (or more extreme) data, given that the null hypothesis is truei. This is different from α, which is the level of risk we set before running the experiment1. Α is usually 0.05; alpha has nothing to do with your data2. P can be anywhere from almost 0 to 1; calculated from your datac. If p < α, reject the null hypothesis (p < .05)i. We sat the result is “statistically significant”d. If p ≥ α, do NOT reject the null hypothesisi. We state that groups do not differ, or that any difference is not statistically significante. If p = α, we are too close to reject the null hypothesisIII. One- / Two-Tailed Hypotheses (calculating the probabilities of z scores)a. Non-directional hypothesis: “what is the probability of randomly drawing a z score MORE EXTREME than 2?”i. Two-tailedb. Directional Hypothesis: “what is the probability of randomly drawing a z score LARGER (or smaller) than 2?”i. One-tailedc. Critical values and how they changei. A lower α means more extreme critical valuesIV. Relating P to the Comparison
View Full Document