Section 2.6 and Data Ethics

# Section 2.6 and Data Ethics - SECTION 2.6 THE QUESTION OF...

This preview shows pages 1–3. Sign up to view the full content.

SECTION 2.6 - THE QUESTION OF CAUSATION Often we are interested in showing that changes in the explanatory variable cause changes in the response variable. CAUSATION When x and y are associated variables, where x is the explanatory variable and y is the response variable, causation occurs when changes in x cause changes in y. What can we consider good evidence for causation? We conducted a well designed experiment where all other variables that cause changes in the response variable were controlled. (This is often not a realistic situation). See the note in Chapter 3 about the principles of experimental design. ESTABLISHING CAUSATION IN OBSERVATIONAL STUDIES How can we establish causation if an experiment is not possible or realistic? The association is strong. The association is consistent over many studies. The alleged cause precedes the effect in time. The alleged cause is plausible. CAUTION: WATCH OUT FOR LURKING VARIABLES A lurking variable is a variable that is neither a response variable nor an explanatory variable in the study but may influence the interpretation of relationships among those variables. OTHER RELATIONSHIPS EXPLAINING ASSOCIATION Common Response : The observed association between the variables x and y is explained by a lurking variable z. Confounding : Two variables are confounded when their effects on a response variable cannot be distinguished from each other. The confounded variables may be explanatory variables or lurking variables.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
EXAMPLES Identify the lurking variable in these relationships. Does the example show common response or confounding? Illustrate with a diagram. a. The more fire fighters who are sent to a fire, the greater the dollars in damage that are reported. b. A study showed that the more years of education a worker has, the larger their income. c. When ice cream sales increase, so do murder rates. d. A news report said more money per person was spent on Alcohol in 2003 than the previous year. It also reported that teachers salaries had been raised. Can we conclude that teachers were spending their extra money on alcohol? e. Grades tend to be higher in smaller classes. Do smaller class sizes cause grades to be higher? f .
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 02/28/2012 for the course STAT 301 taught by Professor Staff during the Spring '08 term at Purdue.

### Page1 / 4

Section 2.6 and Data Ethics - SECTION 2.6 THE QUESTION OF...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online