Lecture12-February+18th-to+post

# Lecture12-February+18th-to+post -  ...

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview:   Tutorial quiz 9 due Today    Quiz 10 available today after class    Due date is TUESDAY, feb 23rd, before class    Exercise 4 will be posted next week. Deadline  will be moved    As usual…    3 weeks left! Plan ahead to complete experimetrix  requirement!    Mean = 163 (SD = 33)    Range = 90‐245    Added 5 points to everyone    Higher score is now 250    Back to experimental designs…    Allows to establish cause‐eﬀect relationships,  BUT…    To be able to do that we need to ensure that  our study has…    INTERNAL VALIDITY    Note that we can NEVER prove causality! We can  only show to what degree it is PROBABLE!   1.  2.  Covariation  Temporal precedence  3.  Eliminate spuriousness  Measure other variables of concern    Ensuring extraneous variables don’t turn into  CONFOUNDS    Watching violent TV + Acting violent + Living in a violent family Acting violent + Living in a violent family + Watching violent TV   What it means to establishing internal validity?    Threats to internal validity    Simple experiment    Pretest‐posttest design  Method Pros Cons Matching Keeps matched variable constant between conditions • Finding matching participants is difficult • Selection bias (by another variable) Balancing Prevents confounding by the variable • Selection bias (by another variable) Random Produces equivalent Assignment groups Works poorly with small samples Limiting Eliminates some Reduces external validity Populations extraneous variables Nonequivalent groups Subjects may be divided to groups in a biased fashion. History Events may occur between multiple observations. Maturation Participants may become ‘older’ or fatigued. Regression to the mean Subjects may be selected based on extreme scores. Attrition Differential loss of subjects from groups in a study may occur. Testing Taking a pretest can affect results of a later test. Instrumentation Changes in instrument ‘calibration’ or observers may change results.   Other threats?    Diﬀusion of treatment  ▪  Pp already have information about study    Participant and experimenter eﬀects  ▪  Single and double‐blind experiments    Sensitivity of measure  ▪  Avoid ﬂoor and ceiling eﬀects  ▪  Variability between scores necessary to detect  diﬀerence!    Make sure groups are equal before  manipulation    Balancing, matching, etc.    Make sure groups are equal before  manipulation    Make sure manipulation actually works    Use a Manipulation Check  ▪  Explicit measure of the   independent variable  ▪  Embedded questions  Mood: Happy vs. Sad  Measure  mood after  Performance  induction Ask questions  Performance  after completion       Make sure groups are equal before  manipulation    Make sure manipulation actually works    Make sure to use a good control group    No‐treatment control vs. Placebo control    Make sure groups are equal before  manipulation    Make sure manipulation actually works    Make sure to use a good control group    Make sure to control for PP and experimenter  eﬀects    Single and double‐blind    Make sure groups are equal before  manipulation    Make sure manipulation actually works    Make sure to use a good control group    Make sure you control for PP and experimenter  eﬀects    Make sure you use a sensitive measure    Check for ﬂoor and ceiling eﬀects    Between vs. Within designs    Between‐Subjects Designs    Advantages and disadvantages    Matched‐pairs design    Within‐Subjects designs    Threats to internal validity    Minimizing threats    Mixed designs     Compare 2 or more conditions (control vs.  experimental)     See if average score on dependent measure (DV)  diﬀer between conditions    If diﬀerences exist, researcher can  demonstrate eﬀects of “treatment” (the IV)    Diﬀerent groups of people are exposed to the  diﬀerent levels of the IV and compared on the  dependent measure    IV manipulated between groups  Group A Words APPLE Group B Words+pics APPLE IV= type of stimulus to be recalled DV= number of words recalled Number of words recalled ? Number of words recalled Do the scores differ?   Diﬀerent groups of people are compared on  the dependent measure    e.g., the simple experiment    We can have more than two groups (or more than  one IV)  ▪  Groups: words, pictures, words+pics, etc…  ▪  IV: type of stimulus, location on screen, abstract vs.  concrete nouns, noise vs. no‐noise, incidental vs.  intentional encoding, etc…..    Same group of people is exposed to diﬀerent  levels of the IV and compared on the  dependent measure    IV manipulated within a group  Group A Words APPLE + Words+pics APPLE Number of words recalled ? Number of words+ pics recalled Do the scores differ?   Same group of people is compared on the  dependent measure    IV manipulated within a group    Can have more than one IV  ▪  Type of event, memorability of event, etc…    Between vs. Within designs    Between‐Subjects Designs    Advantages and disadvantages    Matched‐pairs design    Within‐Subjects designs    Threats to internal validity    Minimizing threats    Mixed designs     Each individual has one score    If we have 30 scores from group A and 30 from  group B = study has 60 participants    As many groups as the levels of the IV    Can be experimental or quasi‐experimental    E.g., When IV is a participants variable    Can compare more than 2 groups    Advantages    Scores are independent of other scores    Always an option when comparing treatment  conditions    Disadvantages    Need large number of participants    Existing Individual diﬀerences (non‐equivalent  groups)  ▪  Can turn into confounds  ▪  Can mask treatment eﬀects    Matched‐Pairs design  Control   Pro: Reduce error variance    Con: need a large pool of people  Experimental   Between vs. Within designs    Between‐Subjects Designs    Advantages and disadvantages    Matched‐pairs design    Within‐Subjects designs    Threats to internal validity    Minimizing threats    Mixed designs     Same sample of individuals participates in all  the treatment conditions    AKA repeated measures design    Advantages  Increased ability to detect treatment eﬀects  ▪  Decrease random error due to Individual diﬀerences    Need less participants    But…..     Disadvantages     Time‐related threats  ▪  History  ▪  Maturation  ▪  Attrition  ▪  Instrumentation    Disadvantages     Time‐related threats    Order Eﬀects  ▪  Variations in response behavior due to order of  conditions  ▪  Decrease internal validity    Practice eﬀect    Performance improves on later measures    Minimize with practice prior to experiment    Fatigue eﬀect    Performance declines on later measures    Minimize with shorter & interesting tasks    Treatment Carryover eﬀect    Earlier treatment aﬀects later treatment    Minimize by increasing time between treatments    Sensitization eﬀect    Performance changes due to hypothesis guessing    Minimize by preventing participants from noticing  treatment changes    Reduce number of conditions    Change sequence of conditions    Randomized Within‐Subjects    Randomized blocks     Counterbalanced Within‐Subjects    Reduce number of conditions    Change sequence of conditions    Randomized Within‐Subjects    Randomized blocks     Counterbalanced Within‐Subjects  ▪  Latin‐square design  ▪  Matrix of n elements were each element appears  exactly once in each column and in each row    A study that combines between‐ and within‐  participants designs    One variable ‘within’     One variable ‘between’  Within Memorability High experimental training control Between Low Number of Number of correct rejection correct rejection Number of Number of correct rejection correct rejection ...
View Full Document

## This note was uploaded on 06/21/2011 for the course PSYCHOLOGY Psych 41 taught by Professor Castelli during the Winter '10 term at UC Davis.

Ask a homework question - tutors are online