PSYCH 312 1st Edition Lecture 6Outline of Last Lecture I. Internal validity II. External validity III. Initial steps for protecting validity a. Random selection b. Random assignment IV. Threats to validity V. Extraneous variables VI. Strong inferencea. Music exampleOutline of Current Lecture I. MeasurementII. Scales of measurementIII. OrdinalIV. Nominal V. IntervalVI. ratioCurrent Lecture Defining variables-Conceptual definitionoHow you think about a variable as a concept or construct -EX: functional fixedness-The inability to imagine an unusual use for an object-Operational definitionoHow you will define the variable for the purpose of measuring it (i.e., transforming it intoa number that can be analyzed)-EX: functional fixedness-The time it takes a participant to attach the tape to connect the two dowels 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.-Validity & reliabilityoValidity of the constructs definition -Measurement oAllows us to test our hypotheses oRelates to our operational definitions -How we translate our variable into something that we can measure and recordoShould be reliable & valid-Reliable-Consistent -Shows same effect repeatedly -Valid-Reflects the variable you say it measures (construct validity)-NOTE:-A measurement can be reliable but NOT valid-CANNOT be valid without also being reliable -Internal validity -A study depends upon both reliability and validity of measures within the study-Scales of measurement oScaling defines rules we use to transform observations-->numbersoHow we…-Analyze data-Display the data-Interpret the dataoExample:-Emotional response to particular visual stimuli-How are we going to operationally define "emotional response"-Changes in..-Facial expression-EEG activity-HR-Self report-Decide what to record about response -Type-Frequency-Duration-Latency-Strength/intensity -These all reflect scaling (numerical code)oTypes-Nominal -Ordinal -Interval-Ratio-Nominal scale oNumbers represent CATEGORIES or LABELSoDifferences btw categories are qualitative NOT quantitative oExample-Code for sex-Female-1 male-2-Code for emotional response to images-Grimace-1-Gag-2-Look away-3-Close eyes-4oCannot add, subtract, multiply, or divide dataoCan only calculate frequency or percentage in each category -Ordinal Scale oCategories AND rankoNumbers reflect some degree of quantitative difference (ranking)oBUT, differences between values are NOT necessarily equaloExamples-Rank images in term of disgust -1=most disgusting -2=moderately disgusting-3=least disgusting -NOTE: difference between a score of 1 and 2 may large but difference between a score of 2 and 3 may be small-Scales on a questionnaire-1-strongly agree-2-agree-3-neutral-4-disagree-5-strongly disagree-Interval scale oValues related by a single underlying quantitative dimension with equal intervals btw thescale values-Can be +, 0, - values-NO ABSOLUTE OR TRUE ZERO POINT representing total lack or absence of value-Examples-Fahrenheit temp-Different values represented different levels of heat (nominal)-Higher values represent greater heat (ordinal)-Differences between values represent equal intervals -BUT, zero doesn’t represent "absence of heat"-IQ tests-Different values represent different levels of intelligence(nominal)-Higher values represent greater intelligence (ordinal)-Differences between values represent equal intervals -BUT, "zero" does not represent "absence of intelligence"oCan do mathematical operations-Add, multiply, subtract, divide, ectoBut cannot make claims based on relative magnitudes-E.g., 4 deg F not twice as hot as 2 deg F-E.g., 50 IG not twice as intelligent as 25 IQ-Ratio Scale oEverything interval data has with the difference that there IS absolute zero-Zero is lowest value-True 0 represents lack of or absence of value-Examples:-Food consumption-Reaction time-Accuracy oCan do mathematical operationsoCan make relationship statements based on ratios-4 is twice as much as 2-How to determine appropriateness of measureoConsider hypothesis oConsider operational definition of variables -What measure makes most sense-What instrument will you use oThen ask..-Is it reliable measure-Is it valid