Textbook Notes (363,006)
Canada (158,140)
Psychology (1,001)
PSYCH 291 (32)

Chapter Six.docx

2 Pages
Unlock Document

University of Waterloo
John Holmes

[ CHAPTER SIX ] – GETTING THINGS UNDER CONTROL: THE CASE OF CLEVER HANS Snow and Cholera  1850s: outbreak of cholera in London  Dr.’s believed exhalations of victims inhaled by others who then contracted disease  Snow hypothesized spread by water supply, which had become contaminated w/ excrement of victims  One part of London had 2 water companies: upstream & downstream of sewage  Snow chemically tested water: - results: upstream – 37 deaths per 10 000 downstream – 315 deaths per 10 000 Comparison, Control, and Manipulation  By comparing results obtained in diff—but ctrl’d—conditions, scientists rule out certain explanation and confirm others  Essential goal of expmtal design: isolate a variable - outcome will eliminate # of alt theories tht may have been advanced as explanations - weed out max # of incorrect explanations either by directly ctrl’g expmtal situation or obsv’g kinds of naturally occurring situations tht allow them to test alt explanations  Instead, most scientists try to restructure world in ways tht will differentiate alt hypotheses - manipulate variable believed to be cause and obsv’ whether differential effect occurs while other relevant variables constant  Best expmtal design: manipulation Random Assignment in Conjunction with Manipulation Defines the True Experiment  Direct manipulation generates stronger inferences i.e. since design such as Snow’s cannot rule out possibility of spurious correlation  When manipulation combined w/ random assignment, scientists can rule out alt explanations of data patterns tht depend on particular characteristics of subjects - as sample size i↑’s, RA tends to balance out chance factors *RA NOT same as random sampling  Fortunately for researchers, RA works pretty well even w/ relatively small #s (i.e. 20-25)  Confounding variables = extraneous variables tht could affect d.v.  Lack of systematic bias in RA allows us to be confident in any conclusions abt cause—as long as study can be replicated - b/c across series of such expmts, diffs btwn 2 groups on confounding variables will be balanced out The Importance of Control Groups  Drawing ppl’s attention away from necessity of comparative info is precisely what media often does  Field experiment = where variable manipulated in non-lab setting  Gov’s use ctrl groups i.e. w/o ctrl, gov would have no knowledge of what edu & health levels would be w/o program (mothers paid ca
More Less

Related notes for PSYCH 291

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.