COMM 201 Exam 2

If you read that the mean equals 42 on a test, what percentage of the participants have scores higher than 42?

Impossible to tell

A hypothesis is a statement about the relationships you expect to find between two or more variables.

True

A population consists of every individual of a type you want to study.

True

A questionnaire is a specific set of questions that respondents answer

True

A sample is a part of a population selected for study.

True

A spurious relationship occurs where a relationship between variables has been found but is actually explained by another variable the researcher was not focused on.

True

At its simplest, empiricism can be defined as research based on observation.

True

Basically, probability sampling means turning the selection of sampling units over to a mechanism over which the researcher has no control.

True

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

True

Control groups are experimental groups not exposed to any experimental variable.

True

Double-barreled questions ask two questions simultaneously but allow for only one answer.

True

Exploration is curiosity-based research.

True

Findings from web-based surveys may not be generalizable to the wider population.

True

Convenience sampling is sampling based on convenience to the research participants.

False

Convenience, quota, and snowball are all types of probability sampling

False

Cross-sectional surveys capture information over an extended period of time.

False

Dichotomous questions force respondents to select one of three possible answers.

False

Generally, it is not necessary to pretest a well-designed questionnaire.

False

Generally, most experimental designs are successful in reproducing "real world" conditions.

False

Inferential statistics allow us to make an inference about a wider population with 100 percent certainty.

False

Most survey designs provide a basis for assessing causal relationships among variables

False

Non-probability sampling means that every unit has an equal chance of being selected.

False

One advantage of surveys is the increasing willingness of consumers to participate in them

False

Random sampling ensures that a sample will be diverse.

False

Random sampling is an example of non-probability sampling.

False

Survey results typically explain why respondents answered the way they did.

False

Surveys give a good understanding of the "whys" behind the survey answers.

False

The larger the sample size, the less confidence we can have that the sample statistics reflect population parameters.

False

The mean is appropriate to describe highly skewed distributions.

False

To pilot a survey is to run it a second time after a survey to check for any changes.

False

Two-tailed hypotheses state the direction of the relationship between variables.

False

Generally most people are happy to respond to telephone surveys.

False; a major disadvantage is people don't want to respond to surveys

In experimental design control groups are groups that are exposed to the experimental variable.

False; control groups are the base line for experiements

Open-ended questions are the most common format in most surveys.

False; researchers look for specific answers

Question format and wording have little effect on respondents' answers to survey questions.

False; this is the most important element in a survey

Focus groups bring together a small group of people in order to elicit their reactions in their own words to a message, issue or product.

True

For a sampling distribution (the distribution of sample results), the standard deviation is called the standard error.

True

Generally, research findings have greater credibility if they are capable of prediction.

True

In a statistically perfect world, data conform to a symmetrical, so-called normal curve

True

In panel studies, the same group of individuals is retained to answer questions over time.

True

Inferential statistics are based on the assumption that the sample studied is randomly selected.

True

Inferential statistics are based on the assumption that the sampled population has normally distributed characteristics.

True

Inferential statistics help us make generalizations about a wider population from studying a smaller sample of it.

True

Inferential statistics let us calculate a level of certainty when we project results from a sample to a wider population.

True

Non-probability samples are based on a sampling judgment by the researcher.

True

Non-probability sampling has an advantage of convenience over probability sampling.

True

One advantage of surveys is that respondents are able to answer large numbers of questions rapidly.

True

One purpose of experimental method is to determine whether variables have a causal relationship to other variables.

True

Probability sampling means that every unit has an equal chance of being selected.

True

Quota sampling attempts to replicate in a sample the features that the researcher thinks are important in the population.

True

Sampling frames are the master lists from which a sample is selected,

True

Sampling is the process of selecting individual units from a population for study.

True

Sampling theory says that we do not need large samples as long as we can live with a level of uncertainty about the population we are trying to understand.

True

Sampling units are the units of a population selected for study

True

Snowball sampling relies on members of a network to introduce the researcher to other members of the network.

True

Stratified random sampling ensures that all the groups of interest to the researcher are proportionately represented in a sample.

True

Surveys are used primarily for reasons of speed and cost-effectiveness.

True

Systematic sampling means sampling every nth person on a list

True

The focus of external validity is on whether the experiment has captured the external world that the researcher is investigating.

True

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

True

Two characteristics of the scientific method are observation and the attempt to rule out alternate explanations.

True

Variables are the aspects of a construct that are capable of being measured

True

With appropriate sampling, you can make generalizations with a known level of confidence from a survey sample to a wider population.

True

With inferential statistics we do not need large sample sizes as long as we are prepared to accept a known level of uncertainty in our projections from a sample.

True

With random assignment of subjects into experimental and control groups, we can assume that any observed difference between groups should be due only to the variable we are manipulating (the treatment or independent variable).

True

One problem with surveys is having to decide whether the responses received are valid.

True; usually it is up to the responder's interpretation

To be satisfied that X does cause Y, we need to be assured of which of the following?

X must precede Y in time; must vary together and Y must be cause by X and not something else (elements of causality)

We can reduce or eliminate the influence of possibly relevant variables in an experiment by ...

random assignment to experimental groups

Cross Tab on sex of the driver and CELL PHONE use

10.7% of female drivers used a cell phone; 6.5% of male drivers used a cell phone; 93.5% of male drivers did not use a cell phone; Altogether 843 male drivers were observed; The results suggest that female drivers are more likely to use a cell phone than male drivers

Cross Tab on sex of driver and adequate turn signal use

14.9% of females used the turn signal inadequately ; 20.4% of males used the turn signal inadequately ; Of those who used the turn signal adequately, 51.6% were male ; Altogether 481 male drivers were observed ; Altogether 903 drivers were observed ; Male drivers seem to be more likely to use the turn signal inadequately than female drivers

If you read that the median equals 42 on a test, what percentage of the participants have scores higher than 42?

50%

The properties of a normal curve are such that _____ of the values under it occur plus or minus one standard deviation from the mean.

68% + or - 1 standard deviation

The properties of a normal curve are such that _____ of the values under it occur plus or minus two standard deviations from the mean.

95% + or - 2 standard deviations

Which of the following research approaches is most likely to involve statistical analysis?

Content Analysis

Which of the following approaches is best suited to assess whether there are causal relationships among variables?

Experiments

Deduction means REASONING FROM OBSERVATIONS TO A THEORY

FALSE

Induction means reasoning from theory to observations that will test the theory.

FALSE

"To what extent do my sample data reflect the wider population from which I sampled?" is a question that inferential statistics cannot answer.

False

A census is a study of every member of a sample.

False

A variable that causes change in another variable is referred to as the dependent variable.

False

Abduction means reasoning from a probable cause to its effects.

False

Level of measurement between ordinal and ratio

Interval

"I am a happy person" "- 1-strongly disagree; 2-disgree; 3-neutral; 4-agree; 5-strongly agree." This is an example of... (select all that apply!)

Interval and Likert Scale

The mean is an appropriate measure of central tendency in case of which level(s) of measurement? (select all that apply!)

Interval and Ratio

Which two levels of measurement allow researchers to use more advanced statistical analyses?

Interval and Ratio

If you ask participants to name the country they were born in, which level of measurement are you using?

Nominal

Lowest level of Measurement

Nominal; naming level

Level of Measurement that uses ranking order

Ordinal

Content Analysis

Quantitative method used to assess media; compare advertising world with real world

Good experimental design requires -

Random Assignment; control group; pre-test; post-test

'How many siblings do you have?' - this exemplifies the __________ level of measurement.

Ratio

Which level of measurement has an absolute zero?

Ratio

Peer Review

Scholars in the same field assess the work and give feedback on ways to improve it

Public Opinion Research

Surveys - researcher asks questions important to them (quantitative) Focus groups - capture opinions that the audience thinks are important (qualitative)

If most participants have similar scores but a there are a few very high scores, what effect will the very high scores have on the mean?

The scores will raise the mean

Which of the following experimental designs has a control group?

two-group pre-test, post-test design; most common design