Psych 311 1nd Edition Lecture 15 Outline of Last Lecture I Review of Inferential Process and Hypothesis Testing II Hypothesis Test T test III Single Sample T Test Outline of Current Lecture I Single Sample T Test Example II Independent Sample T Test III Independent Sample T Test Example Current Lecture I Single Sample T Test Example Ginkgo Biloba is advertised to produce an increase in strength and stamina A sample of n 36 adults takes a regular daily dose for 30 days After 30 days each person is tested in a treadmill test in which on average age adjusted score is 15 Our sample scores M 169 with ss 1260 Can we conclude the herb significantly affectst strength and stamina Ho Difference due to SE not Ginkgo Biloba H1 Different due to Ginkgo Biloba 1 Ho 15 H1 15 0 05 two tailed test 2 Df 36 1 df 15 critical level 2 042 Consult T Distribution table to find critical level using df 3 T M sM t 16 8 15 sM must calculate sM S 2 ss n 1 S 2 1260 36 1 S 2 36 s s 2 s 36 s 6 sM 6 36 sM 1 t 16 9 15 1 t 1 9 1 t 1 9 4 We fail to reject our Ho because our t 1 9 is not within our critical region 5 Cohen s d lM l s d l16 9 15l 6 d 1 9 6 d 0 32 Our Cohen s d is a small to moderate effect size II Independent Samples T Test 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 Recall we use single sample t test when we compare single sample M to theoretically determined population when we don t know and have to estimate it using s Independent Samples t Test when we don t know anything about the population and make a comparison between two separate groups or samples Independent Samples two spate groups and samples each sample has its own and s one sample is treatment condition and then other is control condition Treatment Condition Sample Receives treatment Mrx and srx Control Condition Sample Mc and sc Question Is there a difference between our two samples due to IV or SE III Independent Sample T Test Example We re interested in knowing whether caffeine consumption increases happiness IV caffeine consumption DV happiness We assign 25 people to drink regular coffee and 25 to drink decafe and measure happiness on a scale of 1 not happy to 5 very happy Mcaf 3 2 sscaf 19 44 Mdecaf 3 sdecaf 24 Notice that there is a 0 2 difference between the groups Is this due to caffeine consumption H1 or SE Ho 1 Ho caff decaf 0 One tailed test H1 caff decaf 0 Use because we predict increase 0 05 2 df dfcaff 1 dfdecaf 1 df 25 1 25 1 df 48 Use the df find our critical region using the Unit Normal Table Critical region 1 684 3 Steps to calculate t a Calculate pooled varience sample with larger n is weighter more heavily when averaging s2 S 2p ss1 ss2 df1 df2 S 2p 19 44 24 24 24 S 2p 43 44 28 S 2p 0 91 b Calculate estimated standard error s M1 M2 S 2p n1 S 2p n2 s M1 M2 0 91 25 0 91 25 s M1 M2 0 04 0 04 s M1M2 0 08 s M1 M2 0 27 c Calculate t stat t Mcaf Mdecaf s M1 M2 t 3 2 3 0 27 t 0 74 4 We fail to reject our Ho because our t 0 74 is not within our critical region 5 Cohen s d lM1 M2l S 2p d l2 3 3l 0 91 d 0 2 0 95 d 0 21