SOC 3811

1

• SOC 3811
• Basic Social Statistics

2
Class overviewCompare means of two groups

• Assignment 4 correction
• Concept review
• Two sample t-test different cases
• Assignment 5

3
Simple regression model
4
Interpretation

• Education has a positive influence on the
  respondents age when his/her first child was
  born.
• the slop 0.61
• For each additional year of schooling, it delays
  when the respondent had his/her first child born
  by 0.61 year (about 7.3 months).

5
Multiple Regression Model
6
Interpretation

• Education and Professional type both have
  positive influence on the age when the
  respondents first child was born.
• the slop for Educ 0.495
• the slop for PROF 1.360
• Controlling for professional type, every
  additional year of schooling delays when the
  respondents first child was born by 0.50 year
  (about 6 months).
• Controlling for education, being in a managerial
  position delays when the respondents first
  child was born by 1.36 year (about 1 year and
  4months).

7
Multiple Regression Model with Interaction term
8
Interpretation

• No interaction effect based on this data.
• Being in a managerial position does not mediate
  the influence of education on the respondents
  age when the first child was born.

9
Independent samples T-test
10
F-test

• Ho variances are equal
• Ha variances are not equal
• If Sig. (p value)gt.05 ? cant reject Ho
• (variances are
  equal)
• If Sig. (p value).05 ? reject Ho
• (variances are
  not equal)

11
T-test

• Ho
• Ha
• Calculating z/t score
• (note the formula of is different for cases)
  

12

• Calculating z/t
• For any two means, the difference will also fall
  in a certain range. We can guess the range in
  which it typically falls
• one-tail test two-tail test

-1.645
-1.96
1.96
13
Dependent samples T test
14
95 Confidence Interval

• If 95 C.I. captures the null value (0) ? cant
  reject the null hypothesis
• If 95 C.I. doesnt capture the null value (0) ?
  reject the null hypothesis

15
Example 1
16
Example 1
17
Example 1
18
Independent samplesUnequal variance

19
Example 2
20
Example 2
21
Example 2
22
Independent samples / Equal variances
23
Example 3
24
Example 3
25
Dependent samples
26

• Assignment 5 due next lab
• Occupation , Industry are not continuous
  variables!!
• Notice how the values ordered!
• Dont forget to pick up your assignment.