1. Review Find the mean square (MS) based on these two samples. A.26.1 B.32.7 C.43.6 D.65.3 E.792.7 +14 M A = 14 M B = -36.3 -27 -41 Flood

2. Review The mean square is MS = 43.6. Now find the standard error, A.6.0 B.8.5 C.19.5 D.36.3 E.56.0 +14 M A = 14 M B = -36.3 -27 -41 Flood

3. Review The standard error is. Now calculate t. A.3.7 B.8.4 C.133.8 D.301.8 +14 M A = 14 M B = -36.3 -27 -41 Flood

4. Effect Size 10/17

5. Effect Size If there's an effect, how big is it? – How different is  from  0, or  A from  B, etc.? Separate from reliability – Inferential statistics measure effect relative to standard error – Tiny effects can be reliable, with enough power – Danger of forgetting about practical importance Estimation vs. inference – Inferential statistics convey confidence – Estimation conveys actual, physical values Ways of estimating effect size – Raw difference in means – Relative to standard deviation of raw scores

6. Direct Estimates of Effect Size Goal: estimate difference in population means – One sample:  -  0 – Independent samples:  A –  B – Paired samples:  diff Solution: use M as estimate of  – One sample: M –  0 – Independent samples: M A – M B – Paired samples: M diff Point vs. interval estimates – We don't know exact effect size; samples just provide an estimate – Better to report a range that reflects our uncertainty Confidence Interval – Range of effect sizes that are consistent with the data – Values that would not be rejected as H 0

7. Computing Confidence Intervals CI is range of values for  or  A –  B consistent with data – Values that, if chosen as null hypothesis, would lead to |t| < t crit One-sample t-test (or paired samples): – Retain  0 if – Therefore any value of  0 within t crit  SE of M would not be rejected i.e. 00 t crit  SE M M – t crit  SE M + t crit  SE 00 00 00 M

8. Example Reject null hypothesis if: Confidence Interval:

9. Formulas for Confidence Intervals Mean of a single population (or of difference scores) M ± t crit  SE Difference between two means (M A – M B ) ± t crit  SE Always use two-tailed critical value – p(t df > t crit ) =  /2 – Confidence interval has upper and lower bounds – Need  /2 probability of falling outside either end Effect of sample size – Increasing n decreases standard error – Confidence interval becomes narrower – More data means more precise estimate

10. Interpretation of Confidence Interval Pick any possible value for  (or  A –  B ) IF this were true population value – 5% chance of getting data that would lead us to falsely reject that value – 95% chance we don’t reject that value For 95% of experiments, CI will contain true population value – "95% confidence" Other levels of confidence – Can calculate 90% CI, 99% CI, etc. – Correspond to different alpha levels: confidence = 1 –  – Leads to different t crit : t.crit = qt(alpha/2,df,low=FALSE) – Higher confidence requires wider intervals (t crit increases) Relationship to hypothesis testing – If  0 (or 0) is not in the confidence interval, then we reject H 0  t crit  SE M M – t crit  SE M + t crit  SE M

11. Standardized Effect Size Interpreting effect size depends on variable being measured – Improving digit span by 2 more important than for IQ Solution: measure effect size relative to variability in raw scores Cohen's d – Effect size divided by standard deviation of raw scores – Like a z-score for means Samples dOneIndependentPaired True Estimated d

12. Meaning of Cohen's d How many standard deviations does the mean change by? Gives z-score of one mean within the other population – (negative) z-score of  0 within population – z-score of  A within Population B pnorm(d) tells how many scores are above other mean (if population is Normal) – Fraction of scores in population that are greater than  0 – Fraction of scores in Population A that are greater than  B  00 dd BB AA dd

13. Cohen's d vs. t t depends on n; d does not Bigger n makes you more confident in the effect, but it doesn't change the size of the effect Samples StatisticOneIndependentPaired d t

14. Review The average guppy can swim at 21 mph. On a scuba trip, you discover a new species and wonder if they go the same speed as normal guppies. You time 15 fish and calculate a confidence interval for the mean of [21.4, 25.0]. What do you conclude? A.Null hypothesis: These guppies are the same as average B.Alternative hypothesis: These guppies are faster than average C.It depends on your choice of 

15. Review The average guppy can swim at 21 mph. On a scuba trip, you discover a new species and wonder if they go the same speed as normal guppies. You time 15 fish and calculate a confidence interval for the mean of [21.4, 25.0]. What was the mean of your sample? A.21.0 B.21.4 C.22.8 D.23.2 E.25.0

16. Review Ten subjects are assessed for anxiety before and after a session of mindful meditation training. Calculate the standardized effect size. A.1.33 B.4.00 C.4.22 D.9.72 Subject 12345678910 Before27442932475324593817 After23402533415121503416 Difference444623941 M diff = 3.6 s diff = 2.7