Research methods exam 2

Interpret different possible outcomes in cross-lag correlations, and make a causal inference from each pattern.

(p.239)

Articulate the difference between mediators, third variables, and moderating variables.

-Third variables are external to the bivariate correlation (problematic) -Mediators are internal to the casual variable and ask "why". means to come in the middle of the other two variables -Moderators mean to make the relationship between the two variable more or less intense

Explain why representative samples may be especially important for many frequency claims.

-interrogate how you obtained the samples -random selection ensues confidence in external validity -external validity relies on random sampling

Identify a mediation hypothesis and sketch a diagram of the hypothesized relationship. Describe the steps for testing a mediation hypothesis.

-start with an association between two variables, A and B -Mediation hypothesis propose a mechanism for a bivariate relationship -Why are these two variables correlated? -Mediators specify a time sequence for the three variables (temporal precedence) Mediators also specify the mechanism

Define three sampling problems that lead to biased samples.

1. Convenience sampling: Uses samples that are chosen merely on the basis of who is easy to access 2. Purposive sampling: is used when you want to study certain kinds of people, so you only recruit those types of participants Ex: If you wanted to recruit people who work out, you might recruit participants from a gym 3. Snowball sampling: This is a variation of purposive sampling in which participants are asked to recommend other participants for the study. Ex: If you wanted to study people who do pilates, you could recruit the people you know who do pilates and then ask them to recommend other people form the pilates classes who might participate . (p.192)

Describe three techniques of nonrandom sampling: purposive, convenience, and snowball sampling.

1. Convenience sampling: Uses samples that are chosen merely on the basis of who is easy to access 2. Purposive sampling: is used when you want to study certain kinds of people, so you only recruit those types of participants Ex: If you wanted to recruit people who work out, you might recruit participants from a gym 3. Snowball sampling: This is a variation of purposive sampling in which participants are asked to recommend other participants for the study. Ex: If you wanted to study people who do pilates, you could recruit the people you know who do pilates and then ask them to recommend other people form the pilates classes who might participate . (p.192)

Distinguish an association claim, which requires that a study meet only one of the three rules for causation (covariance), from a causal claim, which requires that the study also establish temporal precedence and internal validity.

1. Covariance: AS A changes, B changes; e.g., high levels of A go with high levels of B, and low levels of A go with low levels of B 2. Temporal precedence: A Comes first in time, before B 3. Internal validity: There are no possible alternative explantations for the change in B; A is the only thing that Changed (p.240)

dentify three types of correlations in a longitudinal correlational design: cross-sectional correlations, autocorrelations, and cross-lag correlations.

1. Cross sectional Correlations: Whether two variables measured at the same point in time are correlated 2.Autocorrelations: the correlation of each variable with itself across time (p.238)

Explain how to increase the construct validity of questions by wording them carefully and by avoiding leading questions, double-barreled questions, and double negatives.

1. Increase efficiency: Make it easy for respondents to provide accurate responses to questions of interest 2. Use Shortcuts: Response sets: allows a number of question in the same way (strongly agree) Although easier to complete, this can weaken construct validity cu respondents may not be saying what they really think 3. Acquiescence: A type of response in which people answer positively to a number of items instead of looking at them individually. 4. When respondents choose an answer in the middle of the scale for all items. this typically a neutral or an " i don't know" response.

Writing well-worded questions how a variable has been measured through Leading question Double-barreled question Negatively worded question Question order

1. Leading Question: Questions that contain an implied assumption. Ex: do you agree that it is a great idea to legalize marijuana? 2. Double-barreled question: Asking two questions at the same time Ex: Do you enjoy long walks on the beach and naps in a hammock? 3. Negatively worded question: Questions that contain negative wording, which can create confusion for participants when answering. Ex: Do you think there's no way Secretary Clinton shouldn't have won the election? 4. Question Order: Earlier items can influence the way respondents interprets later items. One way to control this is to make diff. versions of the survey questions presented in diff. orders.

Describe the different ways questions can be worded: open-ended, forced- choice, and using rating scales.

1. Open-ended questions: respondents may answer anyway they like. Pro: provides rich info. Con: Can be time-consuming to code and categorize info Ex: What do you think of this class? 2. Forced-choice format: Respondents provide their opinion by choosing the best of two or more options Ex: do you like this class so far? yes or No 3. Likert Scale: Respondents are presented with statement and are asked to use a rating scale to reflect their degree of agreement . Ex: How difficult is this class? -Easy 1 2 3 4 5 6 7 Hard 4. Semantic differential format: Respondents are asked to rate a target object using a numeric scale anchored by adjectives Ex: how spicy is this salsa? -Spicy _ _ _ _ _ _ _ _ Bland

Explain five techniques for random sampling: simple random, multistage, cluster, stratified random sampling, and oversampling.

1. Simple Random: 2. Cluster: Clusters of participants within a population of interest are randomly selected, and then all indiviauals in each selected cluster are used. Ex:Suppose your population of interest is preschools within the city you live in. You would randomly selected 20 preschools, and then all of the children in those 20 schools would participate

Steps in testing Mediation

1. Test path c 2. test path a 3. test path b 4. regression (test c'): DV is behavior problem IVs are physical activity and recess Does the recess beta get smaller when physical activity is controlled for? Then physical activity is a mediator

Explain why experiments are superior to multiple-regression designs for controlling for third variables.

1. even though multivariate designs analyzed with regression statistics can control for third variables, they may not be able to establish temporal precedence. 2. second problem is that researchers cannot control for variables they do not measure. even though multiple regression controls for any third variables the researchers masure in the study, there could be an important third variable- one they did not consider-that accounts for the association.

Construct validity can be threatened by: Observer bias Observer effects reactivity

1.Observer Bias: When observers see what they expect to see. expectations can influence observer ratings 2. Observer effects: when participants confirm observer expectations Ex; Bright and Dull rats (p.173) 3. Reactivity: Occurs when people change their behavior in some way the they know another person is watching

Stratified random sampling

A multistage technique in which the researcher selects specific demographic categories (race, gender) and then randomly selects individuals form each category. EX: lets say the that you wanted your sample to reflect the racial makeup of your community. You would obtain info on the various racial groups and their prevalence, and then have your sample reflect that.

Indicate the population that a given sample might represent.

A population that a given sample would represent would be where the population is a bag of chips and the sample is a couple chips of the bag to see if you will like them and assume that you will enjoy the rest of the chips in the bag.

Interrogate the construct validity of an association claim, asking whether the measurement of each variable was reliable and valid.

An association claim describes the relationship between two measured variables, so it is relevant to ask about the construct validity of each variable. How well was each of the two variables measured? (p.210)

Quantitative Variables

Are numerical in nature Ex: mood on a scale from 1-10

Explain why representative samples may be especially important for many frequency claims

Because you are reporting on how often something happens in a population. Ex: 50% of registered voters are still undecided about who they are voting for in the upcoming elections. In this case, random sampling techniques are crucial for high external validity

2. Cluster:

Clusters of participants within a population of interest are randomly selected, and then all indiviauals in each selected cluster are used. Ex:Suppose your population of interest is preschools within the city you live in. You would randomly selected 20 preschools, and then all of the children in those 20 schools would participate

Analyze a correlational study in which at least one variable is categorical by looking at a bar graph and computing the difference between the two means.

Each person is not represented by one data point; instead, the graph shows the mean marital satisfaction rating for all the pople who met their spouse in person. in a bar graph you would examine the difference between the group averages to see whether there is an association. (p.208)

Survey/poll

For our purposes, these two terms meant same thing. They are a method of asking people questions face-to-face, on the phone, on written questionnaires, or online

Categorical Variables

Have general categories with no numerical information associated with it. Ex: favorites type of sandwich

Explain why it is more important to ask how a sample was collected rather than how large the sample is.

In order to optimize the margin of error of the estimate. the margin of error estimate is a statistic that quantifies the degree of sampling error in a study results. this is extremely important if you're trying to predict the outcome of the national presidential election

Over sampling

Is a variation of stratified random sampling in which a researcher over-represents one or more groups. EX: if you wanted to make sure that you had Chinese individuals in your sample, you might over-represent them in your sample at a higher rate than they are found in the population

1. Simple Random:

Is to visualize this process, imagine that each memeber of the population of interest has his or her name written on a ticket. the tickets are tossed into a hat and stirred, and someone reaches in and selects a number of tickets equal to the size of the designed sample. the people whose names are on the selected tickets will make up the sample

Consider why journalists might prefer to report single studies, rather than parsimonious patterns of data.

Journalist tend to report only results from the latest studies instead of providing a comprehensive review of studies conducted in the area. when they report only one study at a time they are selectively presenting only part of the scientific process. science is cumulative. context is important and journalist should summarize an entire body of evidence as well as discussing theory when making a claim

Explain how longitudinal designs are conducted.

Longitudinal designs can provide evidence of temporal precedence by measuring the same variables in the same people at different times

Differences between Mediation, Moderation, and Third-variable problem continued...

Mediation: why are the two variables related? A leads to B because A leads to C which leads to B Moderation: When, for whom, or under what conditions are two variables related? A is related to B for one type of C but not for the other type of C. C type 1: A to B, C type 2: A to B Third- variable problem: two variables are correlated, but only one because they are both linked to a third variable. A is related to B but only because C is related to A and C is related to B

Describe how observational techniques for measurement are different from survey techniques.

Observational techniques is when researchers watch people or animals and systematically record their actions, whereas survey techniques is when researchers try to learn about a phenomenon just by asking people questions and by how they ask them.

Explain the value of pattern and parsimony in research.

Parsimony is the degree to which a good scientific theory provides the simplest explanation of some phenomenon. In the context of investigating a casual claim, parsimony measn the simplest explanation of a pattern of data- the best explanation that requires making the fewest exceptions or qualifications

Explain how question order can change the meaning (and validity) of a question.

Question Order: Earlier items can influence the way respondents interprets later items. One way to control this is to make diff. versions of the survey questions presented in diff. orders.

Explain how the correlation coefficient, r, represents strength and direction of a relationship between two quantitative variables.

R has two qualities: direction and strength. Direction refers to whether the association is positive, negative, or zero Strength refers to how closely related the two variables are- how close "r" is to 1 or -1.

Explain ways to improve the construct validity of observations by reducing observer bias and target reactivity.

Researchers need well-trained observers! having a clear rating scale or codebook is important (p.174 chart) Masked Research design: Prevents observer bias and observer effects by using a masked design. The observers do not know to which conditions the participants have been assigned, and they are not aware of what the study is about (p. 175)

Explain ways to increase the construct validity of questions by preventing respondent shortcuts (such as nay-saying), biases (such as trying to look good), or simple inability to report.

Self reporting and observational data

Define dependent variables and predictor variables in the context of multiple-regression data.

Th dependent variable (criterion) is the variable most interested in understanding or predicting; it is almost always specified either in the top row or in the title of a regression table The predictor variable are the rest of the variables measured in the regression analysis (p.246)

Multistage Sampling

Two random sample are collected. Stage 1: a random sample clusters is selected from your population of interest. Stage 2: From those selected clusters, a random sample of people is chosen Ex: randomly select 20 preschools and then randomly select 20 children from each preschool.

Understand why a random sample is more likely to be a representative sample and why representative samples have external validity to a particular population.

When external validity is crucial, researchers need to obtain a representative sample. the best way of getting such a representative sample is by using SRS in which every member of the population has an equal chance of being selected for the sample

Interrogate the statistical validity of an association claim, asking about features of the data that might distort the meaning of the correlation coefficient, such as outliers in the scatterplot, effect size, and the possibility of restricted range (for a lower-than-expected correlation). When the correlation coefficient is zero, inspect the scatterplot to see if the relationship is curvilinear.

When researchers suspect a curvilinear association, the statistically valid way to analyze it is to compute the correlation between one variable and the square of the other (p.220)

Interrogate the external validity of an association claim by asking to whom the association can generalize.

ask whether the association cna generalize to other people, places, and times. Ex: consider again the association between media multitasking frequency and ability to multitask. to interrogate the external validity of this association, the first questions would be who the participants were and how were they selected.

Explain how multiple-regression designs are conducted.

helps address questions of internal validity by ruling out third variables - Pick the variable you really want to predict. its called the DV -The other two variables are called IVs -Usually, all three variables are intercorrelated. -Multiple regression can allow you to see if one variable can predict the DV, "controlling for" the others.

Identify and interpret data from a multiple-regression table and explain, in a sentence, what each coefficient means.

when looking at a multi-regression table, you will see as column labeled beta and there will be a beta value for each predictor variable. Beta is similar to "r" with a positive beta indicating a positive relationship between the predictor and the criterion variable and so on with negative being negative and zero meaning no relationship. in the column labeled p or sig, if p is less than .05, the beta is statistically significant, when p is greater than .05, beta is not significant.

Consider times when an unrepresentative sample may be appropriate for a frequency claim.

you need to evaluate whether the sample bias cause is relevant to the claim Ex 1: traffic in the morning/radio call in the morning regarding it Ex 2: shoe shoppers rating of a shoe