Class Notes (1,100,000)
CA (630,000)
U of G (30,000)
SOAN (900)
SOAN 2120 (400)
Lecture

SOAN 2120 MARCH 23.docx


Department
Sociology and Anthropology
Course Code
SOAN 2120
Professor
Scott Schau

This preview shows half of the first page. to view the full 2 pages of the document.
SOAN 2120 MARCH 23, 2012
Measure of Dispersion
Range: distance separating the highest and lowest observation recorded
Standard deviation: average dispersion of all values from the mean
Percentiles: division of the sample into various groups of equal size where the
observed values fall
- Inter-quartile range: difference between the 75th and 25th percentile
The Range
- Highest number the lowest number = the range
- Interpretation: The difference between the student who ate the most Kraft
dinners and the student who had the least is 45
Noir and the MCT (measures of central tendency)
Nominal -> yes mode ->no median -> no mean -> no measure of dispersion
Ordinal -> yes -> yes -> no -> no
Interval -> yes -> yes -> yes -> yes
Ratio -> yes -> yes -> yes -> yes
Nominal and ordinal = categorical
Interval and ratio = numerical
BIVARIATE STATISTICAL ANALYSIS
Sub-Group Comparisons
- Statistical descriptions of some variable are broken into subsets of a
population for the sake of comparison
- Description and explanatory
- Comparisons are often based on the assumption of causality
- One variable causes the other
CONTINGENCY TABLES
- 2 variables being compared
Constructing a table for Bivariate Analysis
- AKA contingency tables
- Values of the D.V> are contingent on values of the I.V.
1. Observations are divided into groups according to their attributes of the I.V.
2. Each of these subgroups is then described in terms of the D.V.
3. Table is the ‘percentage’ according to the I.V.
4. Table is read by comparing the I.V. Subgroup with one another in terms of
the same category of the D.V.
MEASURES OF DISPERSION/VARIABILITY
- the variance (o with line(sigma) 2, s2 ) and standard deviation (sigma, s)
- Interpretation of the Standard Deviation
- Indirect indicators of differences
- It is a single number that represents the spread or amount of dispersion in a
set of data
You're Reading a Preview

Unlock to view full version