ES 350 Chapters 6-9 Quizzes

a.) effect size

A measure that expresses the difference between the experimental and control group in standard deviation units is the: a.) effect size b.) r c.) mean d.) chi square

Standard deviation

An estimate of the variability of the scores of a group around the mean

- One-way ANOVA or repeated measures ANOVA - One factor which can have multiple levels

Simple ANOVA

Variance

The square of the standard deviation

Nonparametric

- Distribution free - Distribution is not normal

Mixed ANOVA

- Do two or more groups change differently over trials (over time)? - Analysis is a between (group) - by - within (trials) ANOVA with repeated measures on trials (trials are time, every 2 weeks). This is also called a mixed ANOVA.

Probability

The fraction of times you expect to see that event in many trials

True variance + Error variance

Total variance = ?

Descriptive statistics

"Describe" the sample (mean, standard deviation)

Meaningfulness

Expected effect size from other studies

- Two-way ANOVA, Mixed-ANOVA, Three-way ANOVA, etc. - Two or more factors, each could have multiple levels

Factorial ANOVA

Zero

No correlation

Repeated-Measures ANOVA

- Does one group change differently over trials (over time)? - An ANOVA with repeated measures on trials (trials are time, every 2 weeks)

Voluntary sample

- More likely to be interested in the study than participants from a random sample - May not represent entire population

Stratified random sampling

- Population is divided/ stratified on some characteristic before random selection - You want a total sample of 200, so you would randomly select 60 freshmen, 60 sophomores, 40 juniors, and 40 seniors

Random sampling

- Randomly selecting 200 students from a college with 10,000 students - Helps to ensure that the sample is representative of the population

Convenience sampling

- Recruiting adults who meet CDC's guidelines for aerobic and strength exercise from fitness centers or gyms - Participants may not represent all individuals who are physically active but do not exercise at these types of facilities

Intact groups

- The researcher assigns the groups - Untrained versus trained; elite versus amateur; etc

Snowball sampling

- When a researcher asks the participants to recruit other people they know - Usually performed when population of interest is small

d.) a statistical hypothesis that assumes that there is no difference among the effects of treatments

A null hypothesis is: a.) nearly always the same as the research hypothesis b.) a statistical hypothesis that assumes that the participants in two treatment groups were unequal before treatment began c.) a statistical hypothesis that assumes that there is a difference among the effects of treatments d.) a statistical hypothesis that assumes that there is no difference among the effects of treatments

c.) effect size

A researcher decides to use an alpha of .01 and a power of .80. To determine the needed sample size the researcher must also ascertain the expected: a.) beta b.) stem-and-leaf distribution c.) effect size d.) skewness

b.) 49%

A researcher finds a correlation of .70 between popularity ratings and self-concept scores. What percentage of common association can be inferred between the two variables?: a.) 35% b.) 49% c.) 60% d.) 70%

b.) an independent samples t test

A researcher sought to find out which of two exercises was more effective in building endurance. One group used exercise A, and another group used exercise B. At the end of study, the researcher should compare the two groups' scores with: a.) a dependent samples t test b.) an independent samples t test c.) the Spearman rank-difference correlation d.) multiple regression

Central tendency

A single score that best represents all scores

a.) Pearson product moment coefficient of correlation

A statistical test that provides information about the relationship between two continuous variables is: a.) Pearson product moment coefficient of correlation b.) ANOVA c.) chi-square test d.) t-test

Moderator

A third variable (typically categorical) that influences (i.e., changes the strength or direction of) the relationship between two other variables.

Mediator

A third variable that explains the relationship between two other variables (sometimes referred to as a mechanism).

b.) influences the strength of the effect of variable X on variable Y

A variable that is a moderator is one that: a.) explains the effects of variable X on variable Y b.) influences the strength of the effect of variable X on variable Y c.) serves as a mechanism from variable X to variable Y d.) has a moderate-size effect on variable Y

Inferential statistics

Allow for inferences from a sample to a population when the sample represents the population

c.) the idea that a normal coin may land on heads 40 times out of 100

An important probability concept is relative frequency. Relative frequency is: a.) the idea that a normal coin will land on heads 50 times out of 100 b.) the idea that a coin that lands on heads 60 times out of 100 is rigged c.) the idea that a normal coin may land on heads 40 times out of 100 d.) all of the above

Multiple regression

Correlating more than one predictor with a continuous criterion variable.

Discriminant function analysis (DFA)

Correlating variables to predict group membership (when there are more than 2 groups.

Parametric

For continuous data, parametric tests should be used

c.) statistically significant but does not have a high degree of meaningfulness

If a researcher finds a small difference in average test scores between a large sample (over 700) of experimental participants and a large sample (same size) of control participants, it is very likely that the difference is: a.) statistically significant and has a high degree of meaningfulness b.) not statistically significant but has a high degree of meaningfulness c.) statistically significant but does not have a high degree of meaningfulness d.) neither statistically significant nor meaningful

c.) all other possible explanations have been controlled

If the null hypothesis is false, one may assume the research hypothesis is the explanation for the results if: a.) p < .05 b.) there is no experimenter bias c.) all other possible explanations have been controlled d.) there is a reasonable number of participants in each group

d.) type II error

If the researcher fails to reject the null hypothesis when there really is a difference, this is an example of a: a.) one-tailed test b.) two-tailed test c.) type I error d.) type II error

a.) low

If two measures have a high positive correlation, and a person has a low score on one measure, her score on the other measure is most likely to be: a.) low b.) high c.) the same score d.) dependent on whether one variable is the cause of the other

b.) membership in one of three or more groups

In discriminant function analysis, one is able to predict: a.) a continuous variable b.) membership in one of three or more groups c.) the probability of an occurrence d.) a multiple criterion variable

c.) a binary outcome variable

In logistic regression, one is able to predict: a.) a continuous variable b.) membership in one of three or more groups c.) a binary outcome variable d.) multiple criterion variables

d.) one criterion from two or more predictors

In multiple regression, one is able to predict: a.) two or more criteria from two or more predictors b.) two or more criteria from one predictor c.) one criterion from one predictor d.) one criterion from two or more predictors

b.) if you were testing a drug that had the potential to save lives but also had serious side effects

In which of the following circumstances would you be likely to set alpha = .01 instead of alpha = .05? a.) if you were conducting a pilot study and wanted to give yourself every opportunity to identify a significant result b.) if you were testing a drug that had the potential to save lives but also had serious side effects c.) if you were not concerned about the risk of making a type I error d.) if you had a very small sample size

Descriptive techniques

Measures of central tendency and of variance

-1.0 to -0.01

Negative correlation

Null hypothesis

No difference or no relationship

Sample size

Number of participants needed to achieve the previously established Power

0.01 to 1.0

Positive correlation

b.) correlation

Prediction studies use which of the following as the basic analysis technique?: a.) ANOVA b.) correlation c.) factor analysis d.) multiple-range comparison

Power

Probability of rejecting a false null

Power (1-Beta) is set at 0.80

Probability of rejecting the null hypothesis when, in fact, it is false (correctly rejecting the null)

Alpha is set at 0.05

Probability of type I error (false-positive; rejecting the null hypothesis when the null is true)

Beta is set at 0.20

Probability of type II error (false-negative; failing to reject the null hypothesis when the null is false)

-1.0 to 1.0

Range of correlation

Semipartial correlation

Removing the influence of a third variable on only one of the two variables in a relationship.

Partial correlation

Taking a third variable out of the relationship between two variables.

True variance ÷ Total variance • R2

Test of magnitude = ?

True variance ÷ Error variance - t and F

Test of significance = ?

Equally likely events

The chances of one event are the same as the chances of another event (e.g., heads/tails, roll of a die)

Variability

The degree of difference between each individual score and the central tendency score

Relative frequency

The observed frequency of an event among other events (e.g., when you toss a coin 100 times, you get 48 heads and 52 tails)

c.) 30% of the total variance is accounted for by the treatments

The researcher obtained a significant F from the ANOVA. Partial n2 was found to be .30. This is interpreted to mean that: a.) 9% of the total variance is accounted for by treatment b.) 15% of the total variance is accounted for by error c.) 30% of the total variance is accounted for by the treatments d.) 70% of the total scores are due to the treatments

c.) skewness

The term that describes the position (right or left; positive or negative) of the hump in the curve of a distribution is: a.) kurtosis b.) the stem c.) skewness d.) the leaves

1. Increase the difference between the groups (i.e., maximize the treatment effect) 2. Keep variance small by using homogeneous groups (i.e., only 10-year-olds) and ensuring a consistent treatment 3. Increase sample size

Three ways to increase the power of an independent samples t test through study design:

Differences between groups

To determine if there is a reliable difference between the means of two or more groups

Correlational techniques

To determine the relationship between two or more variables

Alpha

Type I error rate

Statistical techniques

Used to analyze data from samples and consist of descriptive and inferential techniques

Pearson correlation

Used to describe a linear relationship between two continuous variables (X and Y)

Two-tailed tests

Used when you are predicting a difference but are unsure of the direction (i.e., there will be a difference in scores between girls and boys)

One-tailed tests

Used when you are predicting the direction of the difference between the means (i.e., you expect that girls will have higher scores than boys)

Factorial ANOVA

Used with two independent variables and one dependent variable

Logistic regression

Using a continuous variable to predict a binary variable (e.g., yes or no, female or male).

- Relationship between two or more variables (or characteristics). - Whether two variables (or characteristics) vary in the same way.

What does correlational research investigate?

The probability that, given the null is true, the difference between groups is equal or more extreme than the one observed

What does the p-value mean?

d.) 6

What is the median score for the following set of numbers? (3, 11, 8, 13, 5, 3, 6): a.) 8 b.) 5 c.) 7 d.) 6

b.) 4

What is the mode for the following set of numbers? (5, 10, 4, 1, 4, 5, 12, 8, 9, 4): a.) 5 b.) 4 c.) 5.5 d.) 4 and 5

- Shrinkage or population specificity - decrease in validity when prediction equation is used with another population. - Sample size - a rough guideline is 10:1 for participant:variable ratio.

What problems are associated with multiple regression?

b.) establish significance and assess the magnitude of the effect

What two things can statistics do?: a.) establish significance and assess the meaningfulness of the effect (practical meaning) b.) establish significance and assess the magnitude of the effect c.) prove a hypothesis and assess the meaningfulness of the effect d.) prove a hypothesis and assess the magnitude of the effect

Alternative hypothesis

What you actually expect to happen (a difference or a relationship)

a.) type I error

When an experimenter states that the level of significance is at the .05 level, he or she is setting the probability of committing which type of error?: a.) type I error b.) type II error c.) egregious error d.) design error

Single sample t test

When comparing a single sample to a known population

Independent samples t test

When comparing the means from two samples that are independent from one another (e.g., boys vs girls)

Dependent samples t test

When comparing the means from two samples that are related (e.g., twins, pretest/posttest)

a.) analysis of variance

When the purpose of the research is to determine the effects of one independent variable (e.g., four groups) on one dependent variable (e.g., self-concept), the best choice of a statistical analysis is: a.) analysis of variance b.) multiple t tests c.) discriminant analysis d.) MANOVA

a.) There is no difference between the vocabulary scores of average- and high-ability students.

Which hypothesis is stated in the null form? a.) There is no difference between the vocabulary scores of average- and high-ability students. b.) The math achievement scores from School A are significantly higher than the scores from School B. c.) The perceptual-motor development of first-grade girls is higher than that of first-grade boys. d.) There is a positive relationship between attitude toward school and achievement scores.

b.) asking college athletes to recruit their teammates

Which of the following is an example of snowball sampling?: a.) selecting every 20th name from a list of freshmen at a university b.) asking college athletes to recruit their teammates c.) recruiting a third-grade class from a local elementary school d.) randomly selecting names from a high school yearbook

b.) Repeated measures can eliminate the influence of some unwanted variable.

Which one of the following statements does not describe an advantage of repeated measures?: a.) Repeated measures control for individual differences among participants. b.) Repeated measures can eliminate the influence of some unwanted variable. c.) Repeated measures are more economical because fewer participants are needed. d.) Repeated measures allow the researcher to study a phenomenon across time.

d.) all of the above

Which option is a common test statistic?: a.) t b.) F c.) r d.) All of the above

a.) If standard deviation is small, then the mean is likely to be a good representative score for the sample.

Why is standard deviation important in terms of considering the sample?: a.) If standard deviation is small, then the mean is likely to be a good representative score for the sample. b.) If standard deviation is large, then the mode is the best score to represent the sample. c.) If standard deviation is small, then the mean is likely to fall outside of the range of scores. d.) If standard deviation is large, then the mean is likely to be a good representative score for the sample.

Random assignment

You can assume that the groups are equivalent at the beginning of the experiment (you will check that later with statistics), which is one of the most important features of good experimental design that is intended to establish cause and effect

Type I

You can't just run multiple t-tests because you are inflating your ________ __ error rate; you have to account for the multiple comparisons

Random matched assignment

You match the participants for a characteristic that you want to make sure is represented equally across groups