Comm. 201 Exam 2

Front 1

Advantages of Surveys

Back 1

1.) Respondents can answer large numbers of questions rapidly.
2.) Many people can be surveyed rapidly.
3.)You can make generalizations with a known level of confidence from your sample to a wider population.

Front 2

Disadvantages of Surveys

Back 2

1.) Questions with a limited response options (yes/no) will give you numbers but no understanding as "why"
2.) Most survey designs do not allow us to access causal relationships.
3.) An increasing unwillingness of consumers to participate in them.
4.) Deciding whether an answer is valid or not.

Front 3

Cross Sectional Survey

Back 3

typically a "slice of life" in that they capture what is going on at one point in time. (ex: a public opinion poll about a consumer product could have very different answers from one day to another).

Front 4

Trend

Back 4

measure the same items over time but draw different samples from the population each time.

Front 5

Cohort

Back 5

groups of people defined, most typically by having an event in common.

Example: all females in our class born in 1989; the graduating class of 2011

Front 6

Panel

Back 6

a group of individuals is sampled and recruited and the same individuals are retained to answer questions over time.

Front 7

Question Writing

Back 7

the 4 main questions that are asked on all surveys: sex, religion, marital status and age.

Front 8

Open Ended

Back 8

allows respondents to answer in their own words.

Front 9

Dichotomous

Back 9

force respondents to choose from 2 possible answers

Front 10

Multiple Choice

Back 10

provide several possible answers

Front 11

Likert Scale

Back 11

statements which respondents are asked to locate their level of agreement somewhere between "strongly agree" and "strongly disagree"

**Example: our in class surveys

Front 12

Problems with survey wording

Back 12

Easy to misinterpret.

Front 13

Double Barreled Questions

Back 13

ask two questions simultaneously but only allow for one answer

Front 14

Social Desirability Bias

Back 14

??

Front 15

Advantages of Phone Surveys

Back 15

Most households have phones.
Can survey large samples in short time.

Front 16

Advantages of Mail Surveys

Back 16

Give respondents time to consider questions and ability to answer in any order.

Good for delivering questions on complex issues that require thought.

Front 17

Advantages of Internet Surveys

Back 17

Can be administered quickly
Can target special interest groups
Can be emailed or posted to a Web Site.

Front 18

Snowball Sampling

Back 18

Rely on members of a network to introduce you to more members of a different network.

ex: vegetarians. or vector recos

Front 19

Systematic Sampling

Back 19

It's a system.

Ex: in a phone book, you might take every 10th person on the list

Front 20

Cluster Sampling

Back 20

Going from big to small.

First sample larger units (states, provinces, counties) then sample towns and cities, then city blocks, then individual addresses

Front 21

Frequency

Back 21

Number of times something occurs

Front 22

Frequency Table

Back 22

Everything compiled into a table.

Front 23

Inferential Statistics

Back 23

Helps us generalize about a wider population from a smaller sample of it.

Front 24

Range

Back 24

The maximum value minus the minimum value.

ex: range of scores on a test in class is between a 5% and a 75% so the range is 70%

Front 25

Variance

Back 25

measure the extent of which scores in a data set vary.

Front 26

Standard Deviation

Back 26

The square root of variance

Front 27

Disadvantages of Phone Surveys

Back 27

Typically limited to a few short questions

Consumer resistance

Caller ID's, etc. people don't answer

Front 28

Disadvantages of Mail Surveys

Back 28

Low response rate (people might throw them out)

No way of knowing who completed the survey.

Only targets people who are literate.

Front 29

Disadvantages of Internet Surveys

Back 29

Might not be scientifically valid- only reflects the views of people who chose to respond.

Different browsers might view the survey differently (can't control the survey presentation)

May not know who completed the survey

May need email address, or phone number to drive respondents to web site.

Front 30

Population

Back 30

Consists of every type of individual you want to study.

Front 31

Population VS. Sampling Frame

Back 31

??

Front 32

Sample

Back 32

a selected segment of a population presumed to represent that population. (Red, Blue, and Purple rectangles on powerpoint)

Front 33

1936 Gallup vs. Literary Digest forecast illustrate about sampling?

Back 33

They sampled only people who owned tv's and phones (?) which shows that they only surveyed wealthy people and that isn't a good random measure of a survey.

Front 34

Census

Back 34

study of every member of a population.

Front 35

Census vs. Sampling?

Back 35

??

Front 36

Non-probability samples

Back 36

based on a judgment by the researcher.

Front 37

Convenience Sampling

Back 37

based on convenience to the researcher.

Front 38

Quota

Back 38

one of the first survey designs that attempt to bring a scientific approach to survey research.

ex: the cop who needs to give people tickets to get his quota. so then think that we want to get 8 on-campus students and 2 off-campus students to take our survey. That is our quota.

Front 39

Probability Sampling

Back 39

Involves random selection of the sample units.

Front 40

Simple Random Sampling

Back 40

throwing dice, drawing names out of a hat, and lotteries. There is no predicting what specific names or numbers will be sampled. (the luck of the draw)

Front 41

Stratified Sampling

Back 41

a way to "force" random groups into your sample.

(you set aside a certain % for a specific "group" such as vegetarians, etc.)

Front 42

Causal Relationship

Back 42

a relationship between variables in which changes in one demonstrably result in changes in another.

Front 43

3 Elements of Causality

Back 43

1. A must precede B in time
2. If one thing changes, the other must change (covariance)
3. One variable must change the other, and not something else.

Front 44

Covariance

Back 44

If one thing changes, the other must change.

Front 45

Control

Back 45

removes all other possible variables from the experimental design so we can be sure that our treatment variable and only our treatment variable is causing any change we see.

Front 46

Control Group

Back 46

Groups not exposed to any experimental variable.

Front 47

Random Assignment

Back 47

the use of random selection to assign research participants to experimental groups.

Front 48

Mean

Back 48

the average

Front 49

Median

Back 49

the middle

Front 50

Mode

Back 50

the number used most often

Front 51

Measures of Central Tendency

Back 51

the mean, median and mode

Front 52

Confidence Level

Back 52

the calculated probability of a value being true. **typically for communication research a confidence level of 95 is used, meaning that usually 95 out of 100 a reported value will occur if a population is repeatedly sampled.

Front 53

Confidence Interval

Back 53

a range of values, estimated from a sample, within which a value for a population is estimated to fall.