BIOM 121 1nd Edition Exam 3 Study Guide Lectures 14 17 Lecture 6 October 17 Inferential Process In an inferential Process sampling error is problematic because it creates a difference between our population and our sample drawn from it Therefore our null hypothesis is that the difference we see between the population and sample is due to sample error and our alternative hypothesis is that the difference is due to our independent variable Hypothesis Test We use a hypothesis test in order to determine whether the difference we see is due to sampling error or the independent variable We use a generic formula for the test statistic formula test stat observed or obtained difference IV diff due to SE Ztest M M M n Single Sample T Test You only use one sample this eliminates any chance of sampling error You use this test when you don t know and Theory provides us with and we use s to estimate sM s n estimated standard error The reference distribution specifies our critical level and critical region or zone of rejection In a reference distribution for t test there is a separate tdistribution for every df A t disribution has a platykurtic shape flatter more spread out distribution than normal While a leptokurtic t distribution shape is taller and narrower than normal distribution the more participants in sample the more leptokurtic it is Also as df approaches freedom the tdistribution and normal distributions in which df are almost identical therefore you want a sample size of n 30 M 0 but s depends on shape of distribution But the more spread out the distribution is the more variability there is Lecture 15 October 22 Independent Samples T Test We use an independent samples t test when we don t know anything about the population and and have to make a comparison between two separate groups or samples Independent samples are two separate groups or samples with each its own own and s One sample is the treatment condition Mrx and srx and the other is the control condition Mc and sc Independent samples t tests try to answer Is there a difference between our two samples due to IV or SE Lecture 16 October 27 Independent Samples T Test Equations Pooled Variance Used when doing an independent samples t test to average the two samples variance s 2p ss1 ss2 df1 df2 Standard Error s M1 M2 s 2p n1 s 2p n2 T t M1 M1 s M1 M2 Cohen s d d lM1 M2l s 2p Lecture 17 October 29 Repeated Measures T Test Repeated measures are when you measure the same group dependent variable twice once before we administer the IV pretest measure and once after posttest measure This test allows us to see if the difference we see is due to our IV or SE We can see this difference in the scores when comparing the pretest to posttest If the difference we observe far exceeds the difference we see due to SE we can be confident that our IV had an effect This hypothesis test is beneficially because we can use fewer subjects the sample serves as its own control group and measuring the same group twice eliminates the discrepancy between samples due to SE because you use one sample Because we use sample twice we compute a differences score for each participant Differences score is D X2 X1 D posttest pretest Repeated Measures T Test Equations Estimated Standard Error S 2D ssD nD 1 T t MD SMD Cohen s d d lMDl s