1Scientific PapersScientific PapersNew model for lab reportsNew model for lab reportsAnnouncementsAnnouncementsClass Book Debate Class Book Debate ––Tuesday night, Tuesday night, 7:30 PM, C7:30 PM, C--106 Holmes106 HolmesMicrosoft OfficeMicrosoft OfficeMSU Computer StoreMSU Computer StoreOffice 2003 PRO WIN, MEDIA Office 2003 PRO WIN, MEDIA &LICENSE, ACADEMIC STUDENT &LICENSE, ACADEMIC STUDENT SELECTSELECT$60.00$60.00Lab ReportsLab ReportsLab Reports are similar to what scientists Lab Reports are similar to what scientists publish in research journalspublish in research journalsFollow format of scientific papersFollow format of scientific papersKey PartsKey PartsIntroductionIntroductionMethodsMethodsResultsResultsDiscussionDiscussionTables and FiguresTables and FiguresLiterature CitedLiterature CitedAbstractAbstractIntroductionIntroductionDescription of the general question and Description of the general question and backgroundbackgroundDescription of current project’s scope and Description of current project’s scope and general methodsgeneral methodsHypothesis / hypotheses and predictionsHypothesis / hypotheses and predictions2HypothesisHypothesisPlural is hypothesesPlural is hypothesesTested and supported, not proved!Tested and supported, not proved!I tested the hypothesis that smaller computer I tested the hypothesis that smaller computer monitors are harder to use. monitors are harder to use. I tested the hypothesis that smaller computer I tested the hypothesis that smaller computer monitors are harder to use by comparing monitors are harder to use by comparing readability tests on a 15 inch and 17 inch readability tests on a 15 inch and 17 inch monitor.monitor.Null HypothesisNull HypothesisStates that there is no difference (between observed States that there is no difference (between observed and expected, if there had been no effect)and expected, if there had been no effect)HH00: "There will be no difference in readability between : "There will be no difference in readability between 15" and 17" monitors."15" and 17" monitors."HH00: "There will be no relationship between processor : "There will be no relationship between processor speed and startup time, indicated by a line with a slope speed and startup time, indicated by a line with a slope of 0."of 0."DO NOT INCLUDE NULL HYPOTHESIS IN PAPERDO NOT INCLUDE NULL HYPOTHESIS IN PAPERHypothesis TestingHypothesis TestingStatistical Tests are how scientists Statistical Tests are how scientists decide if data support their hypothesis decide if data support their hypothesis (NOT PROVE their hypothesis)(NOT PROVE their hypothesis)Four major statistical tests: TFour major statistical tests: T--test, X2 test, X2 Test, Regression, ANOVATest, Regression, ANOVAHypothesisHypothesisProcessor speed has an effect on the Processor speed has an effect on the performance of the computer.performance of the computer.Null HypothesisNull HypothesisHH00: Processor speed has NO EFFECT on : Processor speed has NO EFFECT on the performance of a computer.the performance of a computer.Hypothesis TestingHypothesis TestingHypothesis testing is using statistical Hypothesis testing is using statistical values to determine whether the Null values to determine whether the Null Hypothesis is correctHypothesis is correctCommon Statistical Tests for Common Statistical Tests for Hypotheses: Hypotheses: tt--Test, ANOVA, Regression, Test, ANOVA, Regression, XX22(Chi (Chi ––Square)Square)Statistical Tests and Statistical Tests and ProbabilityProbabilityStatistical tests give a valueStatistical tests give a valueThat value can be related to a probabilityThat value can be related to a probabilityProbability is likelihood that NULL Probability is likelihood that NULL hypothesis is correct given the data you hypothesis is correct given the data you havehaveIf P < 0.05 (1/20), then you conclude If P < 0.05 (1/20), then you conclude NULL hypothesis is FALSENULL hypothesis is FALSE3TT--TestTestCompares differences between two Compares differences between two meansmeansFormula: T = (xFormula: T = (x11--xx22)/SEM)/SEMSEM is Standard Error of Mean [SD/(NSEM is Standard Error of Mean [SD/(N--1)]1)]T Values: Difference between mean in T Values: Difference between mean in comparison to the amount of spread in comparison to the amount of spread in your datayour dataTT--ValuesValuesIf T > 2.5 or 3.0, difference is usually If T > 2.5 or 3.0, difference is usually significant (this depends on your sample significant (this depends on your sample sizes)sizes)Hypotheses for current Hypotheses for current studystudyWhat were we testing?What were we testing?How did certain characteristics affect How did certain characteristics affect computer performance.computer performance.Use of TestsUse of Teststt--Test: Comparing two meansTest: Comparing two meansANOVA: Comparing multiple meansANOVA: Comparing multiple meansRegression: Looking for a slope in lineRegression: Looking for a slope in lineChiChi--Square: Looking at distribution Square: Looking at distribution patternspatternsHypothesesHypothesesThe startup speed of a computer is The startup speed of a computer is determined by processor speed. determined by processor speed. The startup speed of a computer is The startup speed of a computer is determined by the amount of RAM. determined by the amount of RAM. The stability of a computer is affected by The stability of a computer is affected by its operating system. its operating system. MethodsMethodsExplain what steps were taken in Explain what steps were taken in collecting data and whycollecting data and whyUse past tenseUse past tenseUse active voiceUse active voice“I entered data into a form,” not “The data “I entered data into a form,” not “The data were entered into a form.”were entered into a form.”4ResultsResultsPresent general trends without comment, bias Present general trends without comment, bias or interpretationor interpretationPresent all relevant results, even those that do Present all relevant results, even those that do not support the hypothesesnot support the hypothesesIf statistics are used, report
View Full Document