Final Exam Review

In an ABAB reversal design, the second "B" period is necessary to rule out:

chance fluctuations

In a cross-sectional study, a difference among groups of different ages may reflect developmental age changes; however, these differences may result from _____ effects.

cohort

Describing Results

comparing group percentage, correlating individual scores, comparing group means

A researcher replicates a past study that manipulates the physical attractiveness of a defendant by using photographs instead of written descriptions. This technique would be an example of _____ replication.

conceptual

type I (false positive)

conclude that something is different when it is not

The significance level chosen by a researcher is dependent on the _____.

consequences of making a Type I versus a Type II error

Single-case experiments were developed from a need to:

determine whether a manipulation has an effect on a single research participant.

The probability of making a Type II error increases when the:

effect size is small

The expected value of t under the null hypothesis _____.

equals 0

A(n) _____ replication is an attempt to replicate precisely the procedures of a study to see whether the same results are obtained.

exact

External validity

extent to which we can generalize findings to real-world settings

Dr. Paul found that college students between the ages of 18 and 23 performed better on a cognitive task in a low-noise condition than in a high-noise condition. Dr. Ben wants to repeat Dr. Paul's study by adding age as a variable—18-23 and 65-74. He predicts an interaction between the age and noise variables. In this case, Dr. Ben is questioning the _____ validity of the original study.

external

When the results of a study can be generalized to other subject populations, the study is said to have _____ validity

external

Three claims

frequency claims, association claims, causal claims

What refers to external validity?

generalizability of the research findings

The principal of a school conducts a survey to compare the number of third grade and sixth grade students who buy their lunch at school. The most appropriate way to describe the results of this survey would be to compare:

group percentages

When the independent variable has no effect on the dependent variable, the effect size statistic will:

have a value of 0.00

Events that occur between the first and second measurement period but are not part of the manipulation are called _____ effects.

history

Aden finds that, on an average, men have higher starting salaries than women. In order to conclude that the differences in starting salaries are true differences and not a result of random error, Aden would employ the use of _____ statistics.

inferential

Elaine has read a number of studies on the effect of physical attractiveness on the judgment of an individual's personality characteristics. She then writes a paper in which she categorizes the findings and draws conclusions based on her summaries of the studies. Elaine has most likely conducted a _____.

literature review

Central Tendency

mean (M), median (Mdn), mode

In a _____, the researcher combines the actual results of a number of studies in which the analysis consists of a set of statistical procedures that employ effect sizes to compare a given finding across many different studies.

meta-analysis

A researcher wants to test a hypothesis according to which the mean rating of guilt will be higher for unattractive defendants than for attractive defendants. The appropriate statistical test would be the

one-tailed t-test

In the context of one-group pretest-posttest design, maturation effects occur when:

participants change over time and become bored or fatigued.

A regression equation is used to:

predict a score for Y from a known score of X.

A Type I error occurs when one:

rejects the null hypothesis when it is true

Type II (false negative)

say nothing is going on when something is -Know how alpha, sample size and effect size relate to probability of making at Type I or Type II error!

With respect to Pearson r, the absolute size of r is the coefficient that indicates the:

strength of the relationship between two variables

In a multiple baseline across situations design, _____.

the same behavior is measured in different settings

One solution to the problem of generalizing to other experimenters is to use _____.

two or more experimenters

Sampling Distributions

➢All statistical significance decisions are based on probability distributions ➢Sampling distributions ➢Probability distribution of a given statistic based on a random sample ➢Based on the assumption that the null hypothesis is true

➢Degrees of freedom (df): Number of scores free to vary once the means are known

➢One-tailed versus two-tailed tests

significance level

➢Researchers traditionally used a .05 or a .01 significance level in the decision to reject the null hypothesis ➢Specifies the probability of a Type I error if the null hypothesis is rejected ➢Significance level chosen and the consequences of a Type I or a Type II error are determined by the use of the results

➢F test or analysis of variance: Used when:

➢There are more than two levels of an independent variable ➢Factorial design with two or more independent variables has been used ➢Ratio of 2 types of variance: ➢Systematic variance (between-group variance) & Error variance (within-in group variance) ➢Larger F ratio can lead to significant results

Descrptive Statistics

-Allow researchers to make precise statements about the data -Need 2 statistics to describe data (Central tendency: How participants scored overall, Variability: How widely the distribution of scores is spread) -These 2 numbers summarize the information contained in a frequency distribution

Inferential statistics:

-Help make conclusions on the basis of sample data -Results of a given study are based only on data obtained from a single sample of participants (not entire population) -Would the results hold up if the experiment were conducted repeatedly, each with a new sample -Give the probability that the difference means reflects random error rather than a real difference

Mode

-Most frequent score -Indicates central tendency when scores are measured on nominal scales

Median

-Scores that divides the group in half (50% scoring below & 50% scoring above the median) -Indicates central tendency when scores are measured on an ordinal, interval, and ratio scales

Which significance level would minimize the probability of a Type I error?

.01

Identify the risk associated with pretests.

A pretest tends to induce subjects to behave differently than they would without the pretest.

Which of the following would a researcher be least likely to do when conducting a literature review?

A researcher is least likely to calculate an effect size for all the studies reviewed.

To examine how a reward influences a desired behavior, a mother first counts the number of times her son makes his bed over a two-week period. For the next two weeks, she gives him a reward every time he makes his bed. Following this period, she stops rewarding him and again counts the number of times he makes his bed. This procedure would be an example of a(n) _____ design.

ABA

Adrian found no significant difference in the amount of money spent on entertainment on those students who live on campus versus those who live off campus. Based on this finding, Adrian would:

Accept the null hypothesis

Amelia realized that her 7-year-old daughter, Violet, was especially motivated by money. Amelia began a reinforcement program whereby Violet earned 5 cents every time she brushed her teeth. A month later, Amelia instituted a payment schedule of 10 cents every time Violet went to bed on time without complaining. Once these behaviors were firmly established, Violet began earning money for every book she read. What kind of single-subject design did Amelia employ?

Across behaviors multiple-baseline design

Professor Aaron finds that when he smiles and makes eye contact with Jeanne, she becomes more responsive to his questions. He tries the same behavior on David, Chris, and B.J. and finds that it also influences their responses to his questions. What type of single-case design did Professor Aaron employ?

Across subjects multiple-baseline design

Which of the following examples best represents the use of an interval scale?

Assessing students' ratings of their professors' performance on a five-point scale ranging from poor to excellent

Which of the following accurately describes the relationship between concepts?

Between-groups variance = systematic variance

Regression

Can be used to make prediction about 1 variable from another known variable -Must have high correlation -Must be linear! -Uses calculations used to predict a person's score on one variable when that person's score on another variable is already known -The higher the correlation coefficient, the more accuracy in the prediction.

_____ in quasi-experimental designs is more difficult than in true experiments because quasi-experimental designs lack the important features of true experiments such as random assignment to conditions.

Casual Inference

Which of the following are two general methods for studying individuals of different ages?

Cross-sectional and longitudinal research designs

Correlation Coefficient

Describes how strongly variables are related to one another

Power of statistical test:

Determines optimal sample size based on probability of correctly rejecting the null hypothesis

Ratio

Equal intervals Absolute zero (ex. time, weight, length, & other physical measures) Can be summarized using mean or arithmetic average

_____ variance is the deviation of the individual scores in each group from their respective group means.

Error

T-test

Examines whether TWO groups are significantly different from each other ➢t value - Ratio of two aspects of data ➢Difference between the group means ➢Variability within groups

A student is interested in the effect of environmental conditions on task performance. She makes participants complete a series of math problems under different conditions of temperature—cold, warm, and hot, and different noise conditions—quiet and noisy. The most appropriate test to analyze the data would be a(n) _____.

F-test

Null hypothesis

H0-Population means are equal Observed difference due to random error Independent variable had NO effect

research hypothesis

H1 - Population means are not equal Independent variable had no effect

statistical significance

Indicates that there is a low probability that the difference between the obtained sample means was due to random error -Reject Null hypothesis (accept research hypothesis, I.e. that the Iv had an effect)

Interval

Intervals between levels are equal in size Can be summarized using mean or arithmetic average No absolute zero

Probability

Likelihood of the occurrence of some event or outcome ➢Used in statistical inference ➢How unlikely does a result have to be before we decide it is significant? ➢Alpha level: Probability required for significance ➢If probability is very low, we reject the possibility that only random or chance error is responsible for the obtained difference in means

Statistically, significant results mean that the results are:

Likely to be due to true differences between the groups.

A teacher displays the results of a test on a notice board. As per the results, half the students scored more than 70 percent in the test, while the remaining scored less than 70 percent. Which measure of central tendency does this scenario represent?

Median

Nominal

No numerical, quantitative properties levels represent different categories or groups

Researchers studying the effectiveness of a diet on heart disease divided the study's participants into two groups—those with Type A personalities and those with Type B personalities. Which scale of measurement characterizes these personality variables?

Nominal

Mean

Obtained by adding all the scores and dividing by the number of scores Indicates central tendency when scores are measured on an interval or ratio scales

Dr. Jayden is studying the effect of exercise on cholesterol level. He first measures his patients' cholesterol level before recommending an exercise program and after one month of participating in an exercise program, he measures their cholesterol level again. What type of research design has Dr. Jayden employed?

One group pretest-posttest design

A professor at a university ranks subjects based on students' preferences identified through a survey. He ranks science first, mathematics second, and management third. What type of measurement scale has the professor employed?

Ordinal

When testing the differences between means, the null hypothesis suggests that any observed difference is due to _____.

Random error

Which of the following is a measure of variability?

Range

Ordinal

Rank the levels from lowest to highest

A graduating college student takes the Graduate Record Exam and scores high marks. Six months later the student retakes the exam after completing all undergraduate coursework, but scores relatively low. Other than the boring coursework, what is most likely to account for the lower scores?

Regression toward the mean

Sumaira took an aptitude test for a position with Accountants Unlimited. She was hired the following week. In this scenario, the predictor variable is Sumaira's _____.

Score on the aptitude test

The serious flaw associated with the nonequivalent control group design is that ____ occur.

Selection differences

Which of the following describes a sequential design?

Studying groups of 10- and 15-year-olds, and then studying these individuals 2, 4, and 6 years later

In attempting to study police officers' attitudes toward their supervisors, Alex surveys 25 police officers working in the day shift. In this case, what can help Alex ensure that his findings have external validity?

Surveying officers from all shifts in the department

What is most likely to be true of a study conducted on a group of males to analyze the effects of room temperature on task performance?

The findings of the study cannot be generalized to females.

What does a Solomon four-group design assess?

The impact of taking the pretest

Dana measures the height of four-and five-year-olds. To her surprise, she finds no correlation between height and age. What is most likely responsible for this result?

The range of the variables has been restricted

Which of the following best describes a longitudinal study on children's development?

The same children are tested at 1, 3, 5, and 10 years of age.

The null hypothesis is rejected whenever:

There is a low probability that the obtained results could be due to random error.

In order to study the effects of watching violent programs on children's aggressiveness, a researcher observes children's behavior after they watch 30 minutes of violent programs on television. The researcher concludes that television violence causes aggressiveness. A problem in this research is that:

There is no control group

A researcher asked participants to rate the quality of two well-known brands of paper bags— Prime and Zenith. Prime was rated higher than Zenith with mean ratings of 5.50 and 3.25 respectively. This difference was statistically significant at the .05 probability level. The research hypothesis for this study suggests that:

There is no difference between Prime and Zenith in term of quality.

When comparing the differences in the ratings of responsibility for an automobile accident between male and female drivers, the null hypothesis would suggest that:

There is no difference in the ratings of responsibility between male and female drivers

Which of the following statements is true about ratio scales?

They have an absolute zero point

Which of the following statements is true about bar graphs?

They use a separate and distinct bar for each piece of information.

Why are conceptual replications considered important in the field of social sciences?

They use complex variables that can be operationalized in different ways.

A correlation coefficient is always used______.

To describe the strength of the relationship between two variables

sample size

Total number of observations ➢As sample size increases, confidence that the outcome is actually different from the null hypothesis expectation increases

Ethan concludes that there is no difference in the driving ability of drivers who have consumed one can of beer and those who have consumed three cans of beer. However, there actually is a difference in the driving ability of the drivers. In this case, Ethan has made a(n)______error.

Type II

Pearson product-moment correlation coefficient (Pearson r)

Used when both variables have interval or ratio scale properties -Provides information about the strength and the direction of relationship -Values range from 0.00 to +/- 1.00 -Can be described visually using scatterplots

A Type II error occurs when one:

accepts the null hypothesis when it is false.

Inferential statistics _____.

are used to make conclusions about the data