May 6, 13
What causes economic inequality?
Word of the Day
Probity
o
“The quality or condition of having strong moral principles; integrity, good
character; honesty, decency”
Measuring IQ in
The Bell Curve
Hernnstein and Murray use AFQT (armed forces qualifying test) scores to
measure intelligence
o
The questions aren’t too hard but there’s definitely an aspect of school
achievement rather than innate intelligence (you can definitely do better if
you learned a lot in school)
AFQT scores are converted into
Zscores
to facilitate comparison; they are
standardized
o
A number that ranges roughly from 3 to 3 and it represents how many
standard deviations a particular score is above or below the mean
Measuring socioeconomic status
Hernnstein and Murray measure SES by constructing a SES index comprised of
four variables (each weighted equally, resulting score standardized):
o
Mother’s education
o
Father’s education
o
Parental occupation
o
Family income
To assess the relative influence of intelligence and SES on the probability that a
NLSY respondents would be poor, Hernnstein and Murray use a method of
statistical analysis called
logistic regression
o
The dependent variable in a logistic regression is a binary variable, unlike
OLS regression, where the dependent variable is continuous
Dependent variable in this particular analysis is whether a respondent reported a
household income that was below the poverty line in 1989
Types of variables
Continuous variables
: can take on a large range of values
o
E.g. income or age. Are measured on an interval scale
o
Is used in orderly squares regression (ex: Y = AX + B)
Categorical variables
: can take on only a limited number of values. E.g.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 Moskos
 Sociology, Regression Analysis, Poverty, Bell Curve, Hernnstein

Click to edit the document details