# EBM Exam 1

 The flashcards below were created by user Rx2013 on FreezingBlue Flashcards. Sample must be representative of the entire populationgenerizability Random sampling evenly distributed patient characteristicsequal chance of being in the study Paired sample each subject has a matching mate in the other group independent sample subjects are not matched as pairslarger number of patients needed Data types intervalratioordinalnominal Interval data continuousknown, equal distance between each intervalmay contain negative numbersex. temperature Ratio data continuousknown, equal distance between each intervalnon-arbitrary zerono negative numbersex. age, wt, BG, BP, incidence rates of outcomes Ordinal Data categoricalrankedintervals not equalex. pain scale, military rank Nominal Data categoricalcannot be rankedbinomial or non-binomialbinomial ex. mortality, gendernon-binomial exp. eye color, hair color, ethnicity statistical methods/test are described as being parametric or non-parametric When do you use parametric tests? data from sample results numerically describe a characteristicassumes normal distributionapplies to most interval and ratio data which are more powerful, parametric tests or non-parametric tests? parametric tests when do you use non-parametric tests? no assumption reguarding distributionapplies to ordinal and nominal datacan be applied to interval and ratio data when distribution is skewed specific characteristic determining use of parametric/non-parametric tests type of dataassumed distribution of datahow many groups a study includes parametric test examples student's t-test - 2 groupsanova, ancova - >2 groups non-parametric test examples chi square testfisher's exact test - smaller #mann-whitney U testWilcoxin testKruskal-wallis test Null hypothesis theory about an outcome that a study is designed to testnull = no difference between study groups Alternate hypothesis opposite of null hypothesisthere is a difference between study groups alpha level of significance we usually classify something as statistically significant if it falls below a certain level of significance statistical & clinical significance may be statistically significant but not clinically importantif it is not statistically significant it cannot be clinically important p-value chosen level of significanceusually p<0.05describes the probability that differences between 2 groups occured by chance if p-value < alpha statistically significantreject null hypothesis if p-value > alpha not statistically significantfail to reject null hypothesis setting alpha establishes probability of making a type I error type I error incorrectly reject null hypothesisfalse positivesay there is a difference when there isn't setting Beta establishes probablility of making a type II errorconventionally set at 0.2 Type II error incorrectly fail to reject the null hypothesisfalse negativesay there is no difference when there may be oneassociates with too small sample populationused in calculating power AuthorRx2013 ID132000 Card SetEBM Exam 1 DescriptionBiostats 1 Updated2012-01-31T17:04:58Z Show Answers