Exam 2 Lecture 1&2: Survey Research

Question 1

Explain Quantification analysis

Answer 1

The numerical representation and manipulation of observations for the purpose of describing and explaining the phenomena that those observations reflect.

    Age:    1=1, 2=2, 3=3, 4=4 (if thhe child is 2, were going to assign a 2 to him)
    Sex:     Male=1, Female=2
    Region: West=1, south=2, north=3
    Political affiliation: democrrat=1, republican=2, independent=3

Question 2

Univariate Analysis

Answer 2

Statistical analysis of one variable.

Ex: (Gender) “In this class, what % male and what % female?”

Question 3

Why would a researcher who has quantified his data want to develop a code category and construct a code book?

Answer 3

To help clarify the connection between the numerical representation with the content.

Question 4

Distributions

Answer 4

How many people occur for a certain attribute and what % they make up

Question 5

Central Tendency

Answer 5

Mean, median, mode
• How are you related to the center?
• Only applies to ordinal, interval, and ratio

Question 6

Standard Deviation

Answer 6

Measure of dispersion around the mean

• How far does the data deviate from the mean?
• Most common measure of dispersion
• NOT a measure of central tendency, but a measure of how far from the mean the data is.

Question 7

Continuous Variable

Answer 7

Variable whose attributes form a steady progression (i.e. age, income)

Question 8

Discrete Variable

Answer 8

Variable whose attributes are separate from one another (i.e. gender, political affiliations)
NO ORDER to either dichotomous or categorical
• Dichotomous: 2 responses (i.e. gender)
• Categorical: More than 2 responses What part of the country you are from

Question 9

Handling “don’t knows”

Answer 9

Turn into missing data, several options: leave it out or substitute
with mean score?

Question 10

Subgroup Comparisons

Answer 10

Description of subsets of cases, subjects or respondents.
Trends in Marijuana Use
8th graders 2001 2002
Somked in your life time 20% 30%
in the last year 23% 50%
in the last 30 days 12% 45%
9th graders?
10th graders?
11th graders?

Question 11

Bivariate analysis

Answer 11

Statistical analysis of two variables that effect each other.

Question 12

Response Rate

Answer 12

Out of the people given the survey, who engaged and completed it?

Question 13

Why does the response rate matter?

Answer 13

he validity of the whole survey depends on the response rate.
Surveys are optional, a 5% response rate does not represent the population.

Question 14

Multivariate Analysis

Answer 14

Two independent variables depicting one dependent variable.

Question 15

why we will most always use multivariate statistics to analyze hypotheses?

Answer 15

hen you start considering more variables, your results become more realistic.

Question 16

What would be the Null Hypothesis of this Hypothesis:

“News use will be positively associated with political knowledge.”

Answer 16

Example of Null Hypothesis: News use will NOT be positively associated with political knowledge. [Testing the opposite of what we are trying to test.]

Question 17

P-Value

Answer 17

Whats the probability the we are wrong? 
ranging from 0 to 1.
The smaller the p-value, the more strongly a test rejects a null hypothesis.
Commonly reported P-values:
    .001
    .01
    .05
        [There must be a p-value .05 or less for us to accept the null hypothesis.]

Question 18

True or False?

As the sampling size increases, sampling error increases.

Answer 18

False.
As the sampling size increases, sampling error DECREASES. sampling error is the conflict that your sample itself (not the data it produces) does not match the whole population.