Research Methods Test 2 September 29 th 2011 The Nature of Variables Variable A variable is an event or behavior that can assume at least two values o For example at least two different kinds of chairs in the room Hair color height weight As long as there is more than one category it works o Operational Definitions Brigman 1927 suggested that researchers should define their variables in terms of the operations needed to produce them The spanking study was problematic because the researchers didn t specify what the degree of spanking was Specific definitions need to exist Definitions allow others to replicate your study Independent Variables IV s what is being manipulated Physiological IV o Conditions that alter or change the biological state of the participant o Example temperature drugs food alcohol sleep deprivation Experience IV o Manipulation of the amount or type of training of learning o Example Memory conditioning teaching someone or something to do something Stimulus or environmental IV o An aspect of the environment that the experimenter manipulates o Example basically everything else changing music which would change your environment Participant Characteristics Aspects of the participants such as age sex or personality traits that are treated as if they are independent variables o They are not true independent variables because they cannot be manipulated by the experimenter o What type of studies use these pseudo independent variables Post facto studies o Dependent Variables what is measures Correctness Correct vs Incorrect Rate or Frequency separate but same idea Rate of Frequency how quickly do participants respond in a certain time period in a 5 minute period the rat hit the bar 60 times per min Frequency The number of responses or events that occur within a specified time period number of times children interact during free play How many times the rat hits the bar in an hour Degree or Amount Single number quantifies something that is not normally quantifiable level of life satisfaction self esteem score Latency how quickly did the Ss make a response 15 sec to respond to an Duration how long did your response last held the key down for 30 sec Latency or Duration image on the screen Nuisance Variables Unwanted variable that can increase the range of the DV scores but does not impact the levels of the IV differently Differences between the levels of the IV become more difficult to detect both visually looking at data and with statistical techniques Effects fall equally on all levels of the IV which is different from extraneous which impacts mean of one level compared to another level of IV Scores spread out because peoples score change flatten out because of the nuisance variable range of scores spreads out makes it less clear where the differences between two groups are o For example an experimenter has one group read a list of 10 neutral words and the other group reads 10 synonyms for slow Then they measure the reaction time in participants on a task Participants range in age from 12 78 o Nuisance Variable the age because their reaction time is affected by their age o For example one group is asked to count letters in the words while being shown words on a slide and the other group puts the words in a sentence while being shown Then measure the ability of participants to recall a list of words All groups are studied in a room with a noisy elevator Nuisance Variable Noisy elevator could distract the participants Attention some may be affected and some may not For example One group is given a shot of epinephrine and one group is given a shot of a placebo then measured manual dexterity in room with frequent unpredictable change in temperature Nuisance variable frequent Unpredictable changes in temperature Getting better or worse could depend on the temp Could do better or worse regardless if they got the drug or not Tuesday October 4 th 2011 Controlling Extraneous Variables GOAL Produce groups that are equivalent prior to introduction of the independent variable eliminate extraneous variables and reduce the effects of nuisance variables as much as possible Randomization ensures that each participant has an equal chance of being assigned to any group in an experiment Example level of motivation we want equally motivated people in each experimental group DRAWBACK You can never be fully aware of the variables that technique controls so oyu don t know how effective its been Elimination EV s are completely removed from an experiment Example facial expressions across cultures they re the same Constancy EV is reduced to a single condition that is experienced by all participants no longer a variable only one level o Situation Juan and Nancy are interested in which teaching method is best for teaching stats There are 2 classes and Juan will teach one using Method A and Nancy will teach the other using Method B o What is the problem We can t tell whether the difference is due to the IV the method or the teacher the DV o How can we solve this problem using constancy Only use one teacher only has one value or level o Controls for nuisance variables as well Testing conditions and participant conditions are the same they shouldn t have a wide spread of scores Balancing achieves group equality by equally distributing EV s to all groups Situation Juan takes 25 students and uses Method 1 then Juan takes 25 other students and uses method 2 Nancy takes 25 students and uses method 1 and Nancy takes 25 other students and uses method 2 The idea is that each teacher is now teaching both methods so the EV if any exist is evenly distributed Counterbalancing controls order effects by presenting different treatment sequences Cola challenge example Cola A is tasted then Cola B is tasted We use the same taste cups pour from the same type of container for both colas everyone gets the same amount and then we blind fold subjects o EV s are controlled with constancy and elimination What s the problem Order effect always tasting A before B could skew res ults Counterbalancing Within subject counterbalancing Presentation of different treatment sequences to the same participant Drawback each subject must experience each condition more than once may not want to or be able to present condition more than once May not be time in cola challenge Within group counterbalancing Presentation of different treatment sequences to different participants Cola challenge we will randomly assign half participants to
View Full Document
Unlocking...