Ch. 8

Four potential explanations for correlation

#1 A causes B #2 B causes A #3 A and B are causally reciprocal (depression and poor health status influence each other) #4 association between two variables is due to a "third variable" or confound (depression and poor health status are each caused by poor sleep patterns *confounds are typically unknown

11 guidelines for developing items

#1 items can be developed for uni-dimensional or multidimensional questionnaires #2 items should be written clearly and succinctly to limit ambiguity, use simple language #3 use neutral, non-offensive language #4 minimize the use of negative wording (how much do you like vegetables vs. how much do you not like vegetables) #5 avoid "double-barreled" questions (asking about more than one concept in one question) #6 change the order of wording for some questions to control for response set biases #7 make sure response options are exhaustive and mutually exclusive #8 use rating scales consistently #9 limit the options on a rating scale #10 label or anchor the rating scale points #11 limit amount of time it takes to complete survey

response rates above ____ are recommended and most research is published with response rates ____

75% < 50%

Which of the following describes this survey item: "How often do you not feel like waking up in the morning?" a. The item uses negative wording. b. The item is double-barreled. c. The item includes biased language. d. The item includes language above a high school grade level.

a. The item uses negative wording.

A researcher measures the extent to which the speed at which people eat (in minutes) predicts calorie intake (in kilocalories). Which factor is the predictor variable in this example? a. The speed at which people eat b. Calorie intake c. Minutes and kilocalories d. Type of food consumed

a. The speed at which people eat

Which of the following best describes the formula of the Pearson correlation coefficient? a. The variance shared by two factors, divided by the total variance measured. b. The mean difference between group means, divided by the standard error. c. The variability in group means, divided by the total variability measured. d. The variance in scores for one factor, divided by the variance in scores for the second factor.

a. The variance shared by two factors, divided by the total variance measured.

Adjectives that are given to describe the endpoints of a rating scale to give the scale greater meaning are called: a. anchors. b. bipolar. c. double-barreled. d. jargon.

a. anchors.

A significant correlation shows that two factors are ______ and not that one factor ______ changes in a second factor. a. related; causes b. causal; is related to c. related; is related to d. causal; causes

a. related; causes

The tendency for participants to respond the same way to all items in a survey when the direction of ratings is the same for all items in the survey is called: a. response set. b. statistical error. c. observer bias. d. interviewer bias.

a. response set.

A problem that arises when the direction of causality between two factors can be in either direction is called: a. reverse causality. b. the file-drawer problem. c. restriction of range. d. covariance.

a. reverse causality.

Open-ended items are most often used with the qualitative research design because: a. the responses in the survey are purely descriptive. b. the responses in the survey can be easily coded and scored. c. some responses will be more accurate than others. d. open-ended items have greater power to detect an effect.

a. the responses in the survey are purely descriptive.

The extent to which results in a survey or other research study are consistent with predictions made by an existing theory is called: a. theoretical generalization. b. empirical generalization. c. construct generalization. d. participant generalization.

a. theoretical generalization.

To avoid the problem of restriction of range, the direction and the strength of a significant correlation should only be generalized to a population: a. within the limited range of measurements observed in the sample. b. within a restricted range of values determined prior to collecting data. c. when the researcher can determine cause. d. when all data in the population is collected.

a. within the limited range of measurements observed in the sample.

A researcher could administer a survey orally to one participant at a time or to a small group. What is this type of survey? a. An in-person survey b. A face-to-face interview c. An Internet survey d. A mail survey

b. A face-to-face interview

Which of the following is NOT a method of administering an interview survey? a. By telephone b. By mail c. In-focus groups d. Face-to-face

b. By mail

Which of the following is an example of a double-barreled item for a question rated on a five-point scale from 1 (never) to 5 (often)? a. I enjoy the time I spend doing homework. b. I want to do more homework and have fun. c. I like to attend classes in the morning. d. I find it difficult to find time to study.

b. I want to do more homework and have fun.

Which of the following strategies can increase how many people complete and return a mail survey? a. Including a return envelope with the return postage already paid. b. Including a letter indicating that the survey is required, even if it is not. c. Letting potential respondents know in advance that the survey is being sent. d. Including a cover letter detailing the importance of completing the survey.

b. Including a letter indicating that the survey is required, even if it is not.

A researcher determines that the people buy more clothes in larger clothing stores. Which of the following is a possible confound variable for this correlation? a. Patrons have more money when they visit a large clothing store b. Larger clothing stores have more clothing to choose from c. Small and large clothing stores had identical items on sale d. Smaller clothing stores have more clothing to choose from

b. Larger clothing stores have more clothing to choose from

A researcher measures the extent to which years of marriage predict perceptions of forgiveness. Which factor is the criterion variable in this example? a. Years of marriage b. Perceptions of forgiveness c. Both years of marriage and perceptions of forgiveness d. Perceptions of forgetfulness

b. Perceptions of forgiveness

Response scales that have points above (positive values) and below (negative values) a zero point are called: a. anchors. b. bipolar scales. c. double-barreled scales. d. psychometrics.

b. bipolar scales.

The extent to which the values of two factors (X and Y) vary together is called: a. homogeneity. b. covariance. c. directionality. d. response rate.

b. covariance.

The extent to which results in a survey or other research study are consistent with data obtained in previous research studies is called: a. theoretical generalization. b. empirical generalization. c. construct generalization. d. participant generalization.

b. empirical generalization.

The goal of a focus group is to: a. detect differences between groups. b. get participants talking to each other to share their ideas and experiences on a predetermined topic. c. determine the extent to which two or more group means are significantly different. d. conduct an experimental session to help participants stay more focused.

b. get participants talking to each other to share their ideas and experiences on a predetermined topic.

A ____ response rate can lead to a ________. a. high; nonresponse bias b. low; nonresponse bias c. high; response set pitfall d. low; response set pitfall

b. low; nonresponse bias

A problem that arises when the range of data for one or both correlated factors in a sample is limited or restricted, compared to the range of data in the population from which the sample was selected, is called: a. homogeneity of variance. b. restriction of range. c. causal fallacy. d. response set.

b. restriction of range.

Each of the following is an example of a written survey, EXCEPT: a. in-person survey. b. telephone survey. c. mail survey. d. Internet survey.

b. telephone survey.

Pearson test

both variables are assessed on an interval or ratio scale

spearman test

both variables are assessed on an ordinal scale association between health status (poor to excellent) and level of depression (none, low, moderate, high)

phi test

both variables are dichotomous association between college student status and presence of a sleep disorder (no vs. yes)

According to psychometrics, to construct a response scale we should keep the scale between ________ points. a. 1 to 2 b. 1 to 11 c. 3 to 10 d. 2 to 9

c. 3 to 10

Which of the following correctly identifies the survey research design? a. A design used to determine factors that cause changes in behavior. b. A design used to manipulate the conditions to which groups are assigned. c. A design used to quantify, describe, or characterize an individual or group. d. A design used to observe participant behavior.

c. A design used to quantify, describe, or characterize an individual or group.

Do not describe a correlation beyond the range of data observed in a sample in order to avoid what limitation for interpreting a correlation? a. Homogeneity of variance b. The causal fallacy c. Restriction of range d. Response set

c. Restriction of range

________ items are mostly used in quantitative research, whereas ________ items are mostly used in qualitative research [fill in the blanks]. a. open-ended; partially open-ended b. restricted; partially open ended c. restricted; open-ended d. partially open-ended; restricted

c. restricted; open-ended

The measurement of two or more factors to determine or estimate the extent to which the factors are related or change in an identifiable pattern is called: a. the survey research design. b. the experimental research design. c. the correlational research design. d. the qualitative research design.

c. the correlational research design.

Each of the following is an appropriate strategy for using rating scales consistently, except: a. use only one rating scale for all items in the survey. b. use scales for each item that have similar anchors at each end of the scale. c. use many different rating scales will different anchors to ensure that participants get used to the changing scales throughout the survey. d. if scales are different, then clearly indicate the change in the rating scale for the next group of items.

c. use many different rating scales will different anchors to ensure that participants get used to the changing scales throughout the survey.

strength value

can be -1 to +1

direction value

can be positive or negative

high response rate increases ___________ in the representativeness of the sample for a broader population and generalizing the findings to that population

confidence

_____________ statistic is used to reflect the direction and strength of the association between two or more factors

correlation coefficient (r)

Which of the following are three limitations for interpreting the correlation coefficient? a. Direction, strength, and covariance b. Causality, associability, and restriction of range c. Variability, associability, and outliers d. Causality, outliers, and restriction of range

d. Causality, outliers, and restriction of range

Which of the following rules used to write valid and reliable survey items is violated in this survey item: "Misogynistic men do not make good boyfriends?" a. The item used negative wording. b. The item uses higher than a high school-level vocabulary. c. The item is double-barreled. d. The item used negative wording and the item uses higher than a high school-level vocabulary.

d. The item used negative wording and the item uses higher than a high school-level vocabulary.

Using an in-person survey can be advantageous because the researcher can do all of the following except: a. be there to explain the survey. b. observe participants take the survey. c. answer any questions participants may have while they complete the survey. d. convince all participants to participate in the study.

d. convince all participants to participate in the study.

A low response rate to a survey can limit the ________ of a survey research study. a. number of items b. interrater reliability c. internal validity d. external validity

d. external validity

The advantage of automated phone interviews is that: a. it can save time compared to interpersonal phone interviews. b. it can reduce the likelihood of an interviewer bias. c. it can increase the response rate of participants. d. it can save time compared to interpersonal phone interviews and it can reduce the likelihood of an interviewer bias.

d. it can save time compared to interpersonal phone interviews and it can reduce the likelihood of an interviewer bias.

All of the following are key drawbacks of administering mail surveys except: a. participant response rates are typically low. b. it can be expensive. c. there are fewer post offices. d. it is less time consuming for researchers.

d. it is less time consuming for researchers.

One way to avoid a response set pitfall is to: a. mix up the items in a survey so that ratings are all on the same end of the scale for a given measure. b. mix up the items in a survey so that ratings do not vary from one question to another. c. mix up the items in a survey so that only one rating is possible for a given measure. d. mix up the items in a survey so that ratings are not all on the same end of the scale for a given measure.

d. mix up the items in a survey so that ratings are not all on the same end of the scale for a given measure.

A survey item must be simple, meaning all of the following except: a. everyone who takes a survey should be able to understand it. b. items should use less than a high school-level vocabulary. c. participants should not be confused about what the item is asking. d. participants should be slightly confused as to not know what the items are asking.

d. participants should be slightly confused as to not know what the items are asking.

An outlier can change the ________ of a relationship between two factors. a. causality b. direction, but not the strength c. strength, but not the direction d. strength and direction

d. strength and direction

Restricted items are most often used with the quantitative research design because: a. it allows for the analysis of an infinite number of possible responses. b. the respondents are not restricted in their responses to the survey items. c. the responses in the survey are purely descriptive. d. survey responses can be easily entered or coded for the purposes of statistical analysis.

d. survey responses can be easily entered or coded for the purposes of statistical analysis.

Language that is offensive or could potentially be considered offensive by a respondent is all of the following except: a. is an example of biased language. b. could influence a participants response. c. can be avoided by following APA guidelines. d. used to eliminate sensitive participants.

d. used to eliminate sensitive participants.

if reliability analysis is conducted on all items or on subscale items only, alpha for one or more subscales should __________ the alpha for all items

exceed

covariance

extent to which values of two factors vary together (or variance shared between two factors)

most time consuming survey

face to face

another name for restricted items

forced choice

______ bias may be present in face to face interviews

interviewer bias

a numeric scale reflecting rate or level of agreement with a statement of question

likert scale

__________________ is used for prediction purposes for correlational research

linear regression

telephone surveys have ( low | high ) response rates

low

increase in the value of one factor is associated with a decrease in the value of another factor

negative correlation

mutually exclusive

not dependent on each other, distinct and separate ME: what is your age? a) less than 10 yrs b) between 10 and 20 not ME: ******

point-biserial test

one variable is dichotomous, other is interval or ratio association between biological sex and health status

participants can answer how they choose (no restricted or forced multiple choice options)

open ended survey -common with qualitative research designs -responses often are coded into nominal or ordinal categories

a few restrictive options but at least one option that allows participants to respond in their own words

partially open-ended items

increase in the value of one factor is associate with an increase in the value of another factor

positive correlation

the best fitting straight line to a set of data points, line that minimizes distance that all data points fall from it

regression line

response rates will be higher when for written surveys

research is present than when asked to complete them via phone, mail or the internet

likert scale is a type of _________ item

restricted

a restricted number of options to which participants must respond

restricted items

a graphical depiction of discrete data points that can generally illuminate the direction of strength of association

scatterplot

a series of questions or statements to quantify differences in characteristics, behaviors, experiences, and perceptions

surveys

low response rate can only be generalized to

the sample of participants who completed the survey