Psych 2005 Final Exam

If there are a few extreme outliers in an equal interval, continuos variable, which is usually the best measure of central tendency?

A. Mean

B. Median

C. Mode

D. Variance

Median

The lowest constraint research method on this list is:

A. Case Study

B. Differential

C. Experimental

D. Naturalistic Observational

E. Survey/Correlational

Naturalistic Observational

I would expect the correlation between students' scores on exam -3 and amores on the final exam in this class to be closest to:

A. -1.5

B. -0.5

C. 0

D. 0.5

E. 1.5

0.5

Which of these was not among the "troubling trio" of study characteristics cited in 2015 in an editorial by the editor of Psychological Science?

A. Low Statistical Power

B. a surprising result

C. a null result

D. A&B

E. B&C

A null result

What does it mean to say that something is significant at the p<.05 level?

A. There's exactly a 5% probability that the results occurred by chance

B. There's less than a 5% probability that the results occurred by chance

C. This result would occur less than 5% of the time if the null is false.

D. This result would occur less than 5% of the time if the null is true.

E. This result would occur less than .05% of the time if the null is true.

This result would occur less than 5% of the time if the null is true.

Which Z score is legitimate and has the greatest magnitude?

A. -5.3

B. -4.0

C. 1.0

D. 3.0

E. 4.5

-5.3

What percentile ranking would a z-score of -2.0 correspond to (roughly)

A. -2.0%

B. 0.5%

C. 2.0%

D. 5.0%

E. 10%

2.0%

In an analysis of variance, if the null hypothesis is true, then

A. it is not possible to make a Type-I error.

B. fewer participants can be included in the experiment.

C. there is less variance among means of samples than if the null hypothesis were not true.

D. the within-groups estimate of the population variance is smaller than the between-groups estimate.

C. there is less variance among means of samples than if the null hypothesis were not true.

"Horse number 5 came in 2nd place in the race, with a time of 57 seconds". What is the type of data corresponding to each of these three numbers?

A. Nominal, Ordinal, Interval

B. Ordinal, Interval, Nominal

C. Ratio, Nominal, Interval

D. Interval, Ratio, Ordinal

E. Nominal,Ordinal,Ratio

E. Nominal, ordinal, ratio

What is the definition of the comparison distribution?

A. The distribution in the population of scores in your hypothesis group

B. The obtained distribution of scores in your treatment group

C. The distribution you would get if in fact there is a relationship between your two variables

D. The distribution of your control group if the null hypothesis is true

E. The sampling distribution you would get if the null hypothesis is true

The sampling distribution you would get if the null hypothesis is true.

Type I error is defined as:

A. Failing to reject the null when you should have confirmed the null.

B. Rejecting the null when you should have confirmed the research hypothesis.

C. Failing to reject the null when you should have rejected the null.

D. Rejected the null when you should have failed to reject the null

E. None of the above.

Rejecting the null when you should have failed to reject the null.

Holding all else constant, as the degrees of freedom decrease, the critical cutoff score:

A. Gets more extreme (further from the middle)

B. Gets less extreme (closer to the middle)

C. Stays the same

D. Answer A when comparing means of samples but answer B when doing correlation

E. Answer B when comparing means of samples but answer A when doing correlation.

A. Gets more extreme (further from the middle)

If a planned study has estimated power of .05, would this be considered "good power" and proceeding with the study would be advised.

A. Probably yes

B. Probably No

C. depends on the type 1 error rate

D. depends on the type 2 error rate

Probably no

The minimum number of studies necessary for a meta-analysis..

A. depends on the studies' sample size

B. Depends on whether 1- or 2- tailed tests were used

C. is 2

D. is 3

E. is 10

is 2

In a study comparing the means of two samples what measure of effect size would you typically use?

A. d

B. r

C. t

D. PRE

E. Impossible to answer question with the information given

A. d

You make up a new scale, and you are pretty sure that it measures what it is supposed to be measuring. Another way to say this is that your scale has pretty good:

A. Test-retest reliability

B. Inter-rater reliability

C. Internal Reliability

D. Contract validity

E. Split-half validity

D. construct Validity

What is NOT true about the standardized regression equation when you have on predictor?

A. The intercept is always 0

B. PRE is always the same as r-squared

C. The interpretation of the slope is in z-score units

D. There is only one criterion variable

E. Beta is always the same as b

Beta is always the same as b

If your unstandardized regression equation for sweet tooth (X) predicting candy liking (Y) is

Yhat = 6.7 + .25X. This means:

A. With every one unit increase in sweet tooth we expect a .25 unit increase in candy liking

B. With every one z-score increase in sweet tooth we expect a .25 z-score increase in candy liking

C. With every .25 unit increase in sweet tooth we expect a one unit increase in candy liking

D. With every .25 z-score increase in sweet tooth we expect a one z-score increase in sweet tooth

With every one unit increase in sweet tooth we expect a .25 unit increase in candy liking.

If you increase the alpha (p-value) of your significance test (from .05 to .10):

A. PRE gets smaller

B. Statistical significance becomes less likely

C. Type 1 error (false positive) rate gets bigger

D. Type 2 error (false negative) rate gets bigger

E. Power gets smaller

C. Type 1 error (false positive) rate gets bigger

Increasing effect size is one way to increase power because:

A. It changes the research hypothesis (Step 1)

B.It makes the variability in the comparison distribution less extreme (Step 2)

C. It makes the critical cutoff score less extreme (Step 3)

D. It makes the score in your sample likely to be more extreme (Step 4)

It makes the score in your sample likely to be more extreme

According to "scientific Utopia" which of these is an ineffective strategy for prevention false results?

A. Author, review and editor checklists

B. conceptual replication

C. Raising the barrier for publication

D. both A and B

E. Both B and C

Both B and C

When you do the 5 steps of hypothesis testing to test the significance of a correlation:

A. you must use a two-tailed test

B. you use a t-table distribution

C. the N in you resample doesn't affect the likelihood of significance

D. A and B

E. A and C

you use a t-table distribution

4I think the dogs on my block are unusually long and I want to test this hypothesis. I know the population mean of dogs lengths from wiki, but not the SD.

A. Z test

B. Single sample t test

C. t test for dependent means

D. t test for independent means

E. Correlation

Single sample test

Which of these is not one of Nosek & Bar-anan's "Utopia I" recommendations for changing scientific communication?

A. Anonymous peer review

B. Disentangling publication from evaluation

C. Full Embrace of Digital Communication

D. Grading Evaluation System and Diversified Dissemination System

E.OpenAccesstoAllPublishedResearch

Anonymus peer review

what are Utopia 1: Stages for changing scientific communication.

1.) full embrace of digital communication

2.) open access to all published research

3.) disentangling publication from evaluation

4.) grading evaluation system and diversified dissemination system

5.) publishing peer review

6.) open, continous peer review.

Z score formula

Z=X-M/SD

* a raw score minus the mean score divided by the SD

*changes raw score into z score

Formula to change a Z score to a raw score

X=(Z)(SD)+M

The mean of any distribution of Z scores is always what?

zero

How is a z score related to a raw score?

a z score is the number of SD a raw score is above or below the mean.

What is the ideal method of picking out a sample study

random selection.

population parameters

the mean, variance and SD of a population

Sample Statistics

descriptive statistics, such as the mean, SD and variance

Expected relative frequency

what you expect to get in the long run if you repeat the experiment many times.

long-run relative-frequency interpretation of probability

understanding of probability as the proportion of a particular outcome that you would get if the experiment were repeated many times.

Subjective interpretation of probability

way of understanding probability as the degree of one's certainty that a particular outcome will occur.

Mutually exclusive

if one outcome happens, the others can't happen

*head or tails is mutually exclusive

multiplication rule

use this to figure the probability of getting both or two (or more) independent outcomes.

Conditional probabilities

conditional probability is the probability of one outcome, assuming some other outcome will happen.

What is the percentage of a normal curve?

-50% of scores are above the mean.

-34% are between 1 SD above and the mean

-14% are between 1 and 2 SD above the mean

The median is typically a better measure of central tendency than the mean in which of the following cases?

A. the distribution is bimodal

B. the distribution displays strong kurtosis

C. the distribution is highly skewed

d. the distribution is composed of responses on a nominal variable.

the distribution is highly skewed

Which of these is an example of a ration level of measurement

A. Temperature

B. reaction time

C. Politcal affiliation

D. Personality scale

reaction time

An educational psychologist is curious about why the standardized test scores at a particular institution are two standard deviations lower than the national average. So he sits in the classrooms of a random selection of instructors at the institution to watch them and evaluate their efficacy. He is on the lookout for unusual teaching methods that could contribute to lower-than-average scores. Which research method is he employing?

A. Differential

B. Case Study

C. Experimental

D.. Naturalistic observation

Naturalistic observation

In many psychological studies of infants, researchers want to know if an infant can recognize, visually, that two object are different. Since the infants can't yet talk, researchers often measure differences in the amount of time an infant spends looking at the various stimuli to determine if they can tell the difference between them. In this type of study, looking time differences would be considered a(n)

A. independent variable

B. Dependent variable

C. fact

D. psychological construct

E. Operational definition

-dependent variable

-fact

-operational definiton

Which of these describes the shape of a frequency distribution that has clearly been affected by a floor effect?

A. Skewed left

B. negatively skewed

C. skewed right

D. positively skewed

E. deduced

F. induced

skewed right

positively skewed

Suppose a researcher conducts a two-tailed hypothesis test with a sample of 1 and obtains a result of p = 0.034. Within which of the following ranges could the sample's Z-score fall?

Less than -1.96

Greater than 1.96

between 0 and 1.64

greater than 2.58

Between -1.64 and -1.96

less than -1.96

greater than 1.96

Bodo's owner observed that Thomas Jefferson did not eat any of his bagels last semester. Worried about his business, the owner set out to determine how representative this was of the typical UVa student's consumption of Bodo's Bagels. Suppose previous market research showed that the mean number of Bodo's Bagels a UVa student eats per semester is 24, with a standard deviation of 4. What is the mean of the distribution of Z scores the owner compiles for this set of data during his frantic study?

A. 4

B. -4

C. Cannot determine from information given

D. 0

E. 1

0

The results of a study measuring reaction time in response to a stimulus show a mean of 3.50 seconds and a standard deviation of 1.30 seconds. This allows us to calculate that a participant with a Z score of +1.5 took __________ seconds to respond to the stimulus

5.45

A particular standardized test has a population mean score of 75 and standard deviation of 7.5, and the scores are normally distributed. If a person scores in the 95th percentile on this test, then this person's score is

87.3

* must recall that 1.64 is the Z score below which 95% of scores fall.

Score= (1.64*7.5) = 12.3+75= 87.3

The three ethical principles for human research highlighted in the Belmont report are

Autonomy, beneficence, justice

Here is an excerpt from the Abstract of a recently published paper titled "Female Chess Players Outperform Expectations When Playing Men."

Previous studies have found that stereotype threat is activated in female chess players when they are matched against male players. I used data from over 5.5 million games of international tournament chess and found no evidence of a stereotype-threat effect. In fact, female players outperform expectations when playing men. Further analysis showed no influence of degree of challenge, player age, nor prevalence of female role models in national chess leagues on differences in performance when women play men versus when they play women.

Based only on what can be inferred from this excerpt, would you say that this research design was correlational or experimental? Why?

Correlational, because the author's data are from actual chess matches and the independent variable, whether a woman's match was against another woman or a man, is not randomly assigned.

What's the point of Geoff Cumming's slogan about a confidence interval, "It might be red!"?

It's a caution for us to keep in mind that the confidence interval may not capture the true population mean.

A ___________ occurs when there is an actual difference between the populations being studied, but the researcher fails to reject the null hypothesis.

Type II, or false negative

Which of the following is a consequence of increasing the sample size of a study?

A. Reduced false positive

B. Reduce standard error

C. increase effect size

D. Reduced false negative error rate

-reduced standard error

-reduced false negative error rate.

An education researcher selects two professors at a university with the highest ratings from student evaluations. He wants to know what makes these professors so well-liked. He examines students' comments and interviews the professors about their teaching methods.

What level of constraint does this best represent?

A. correlational research

B. case study research

C. differential research

D. experimental research

E. Naturalistic observational research

case study research

The variance of a sample is a "biased" estimate of the population variance because...

A. a sample is generally shaped like a t- distribution

B. the sample is generally less variable than the population

C. the sample generally does not have enough degrees of freedom

D. the sample mean is a biased estimate of the population mean

the sample mean is generally less variable than the population

Last spring, Professor Smyth taught Intro to Social Psychology at 6pm on Tuesdays and Thursdays. He is curious about whether the students were more likely to miss class on Tuesdays or Thursdays (his hunch is that students are more likely to miss on Thursdays, since he's heard some students say that the weekend starts on Thursday). Which of the following tests would be most appropriate for his study of the data from last spring's class?

dependent means t test

dependent means t-test

compares the means of two related groups to determine whether there is a statistically significant difference between these means.

Independent means t test

determines whether there is a statistically significant difference between the means of two unrelated groups.

Single sample t test

sample mean is being compared to population mean but population variance is unknown.

Which of the following is true for both the t test for independent means and the t test for dependent means?

A. pretest/postttest experimental designs are common

B. Population variances are estimated from the information in the sample of scores actually studied.

C. the population means are unknown

d. The sample scores (in some form) are eventually compared to a t distribution.

B. Population variances are estimated from the information in the sample of scores actually studied.

C. the population means are unknown

D. The sample scores (in some form) are eventually compared to a t distribution.

A t distribution for df=20 will have ______ tails compared to the Z distribution, so the cut off scores for that t distribution will be _______.

A. fatter; less extreme

B. thinner; less extreme

C. fatter; more extreme

D. thinner; more extreme

C. fatter; more extreme

When figuring the pooled population variance estimate in a t test for independent means,

A. the variance of at least one of the original populations must be known, as opposed to estimated, but the other can be estimated from sample scores.

B. the variance estimates based on each of the samples are averaged in such as way as to give more influence to the estimate based on more participants.

C. the variance of BOTH of the original populations must be known, as opposed to estimated.

D. the scores from both samples are combined to form a single sample, and the estimated variance is figured in the usual way using this combined sample.

B. the variance estimates based on each of the samples are averaged in such as way as to give more influence to the estimate based on more participants.

Which of the following can be accomplished with low-constraint research methods?

A. Negating a general proposition

B. Establishing a causal relationship

C. establishing a general proposition

D. Exploratory research

A. Negating a vernal proposition

D. Exploratory research

Power is the probability that

A. The research hypothesis will not be accepted incorrectly

B. if the research hypothesis is false, the experiment will support the null hypothesis.

C. a type I error will not be made

D. if the research hypothesis is true, the experiment will support it.

D. if the research hypothesis is true, the experiment will support it.

In actual practice, the usual reason for determine power before conducting a study is

A. to determine the number of participants needed to have a reasonable level of power.

B. to anticipate the likelihood that the experiment will need to be repeated.

C. to ensure that regardless of whether the research hypothesis is true, the experiment will yield a significant result.

D. to eliminate the possibility that a mistake may occur.

to determine the number of participants needed to have a reasonable level of power.

Which of these best descries the comparison distribution for a dependent means t test.

A. distribution of individual scores

B. Distribution of differences between means

C. Distribution of means

D. Distribution of means of difference scores

D. Distribution of means of difference scores.

What is the false negative error percentage for a study with N=400, alpha =.05 and power = 65%

35%

When participants respond to (unintended) cues from the experimenter, the study is affected by ____________

experimenter reactivity

Why do dependent means studies (e.g., repeated measures of the same subjects, or measures of "yoked" pairs of subjects) often have much larger Cohen's d effect sizes--and more power--than other kinds of research designs?

It's because the variability of difference scores, taken from the same or yoked subjects, tends to be less than the variability of scores between different, independent subjects. Since the variability of scores is the basis of the denominator of Cohen's d effect size, less variance will yield larger effect sizes. Power increases as effect sizes are larger.

if we elected participants on the basis of extremely high to low scores on a test, the most likely validity is

A. attrition

B. diffusion of treatment

C. testing bias

D. Regression to the mean

Regression to the mean

If a human observer becomes more proficient in the course of a study, the type of threat to internal validity is called a change in

A. proficiency

B. Instrumentation

C. regression to the mean

D. research bias

B. instrumentation

The most effective control method for reducing the possibility that unknown variable may affect the dependent variable is

A. Objective measurement

B. automation

C. random assignment to condition

D. stratified random sampling

C. random assignment to condition.

Which of the following is true for the F-tests

A. F-tests cannot tell you the direction of a significant effect

B. F-tests are always two tailed

C. The critical-F for a given alpha varies according to numerator and denominator degrees of freedom

D. F-test are used to determine if three o more groups come from the same underlying population

C. The critical- F for a given alpha varies according to numerator and denominator degrees

D. F-tests used to determine if three or more groups come from the same underlying population.

A. F-tests cannot tell you the direction of a significance test.

In regression, the baseline error (SStotal) in the prediction of your criterion variable, Y, is derived from the deviations of Y scores from

A. X scores

B. the mean of X

C. y scores squared

D. x scores squared

E. the mean of Y

E. the mean of Y

Which of these random assignments approaches is best to use when sample sizes available for experimental conditions are small

A. Free random

B. Matched random

C. random within blacks

D. blind Random

B. matched random

The type of validity most focused on the demonstration of causation is know as ________ validity

internal

The difference between a prediction rule's predicted score for someone on a criterion variable and that person's actual score on that variable is called_______

error

Unintentional cues from an experimenter or study structure about "how to behave" as a study participant are known as _________

demand characteristics

In a regression analysis, if SSerror= 50 and SStotal=200, what is the proportionate reduction is error (PRE)

.75

What is a comparison distribution?

A comparison distribution is a distribution to which you compare the results of your study.

Cutoff scores for two tailed test?

1.96

Cutoff score for a one tailed test?

1.64

Distribution of means

a distribution composed of many means that are calculated from all possible samples of a given size, all taken from the same population

30 or more individuals for a normal curve

mean of a distribution of means

the mean of a distribution of means of samples of a given size from a population;

it comes out to be the same as the mean of the population of individuals

Variance of a distribution of means

variance of the population divided by the number of scores in each sample

Standard error

same as SD of distribution of means

Standard error of distribution of means

square root of the variance of a distribution of means; also called Standard error of the means (SEM) and Standard error (SE)

What is the best estimate of a population mean? Why?

the sample mean because it is more likely to have come from a population with the same mean than from any other population.

Alpha

probability of making a type I error, same a significance level

Beta

probability of making a Type II error

Effect size

standardized measure of difference (lack of overlap) between populations. effect size increases with greater difference between means.

*think of it as how much something changes after a specific intervention.

d

effect size or Cohen's d

m1-m2/ Sd

effect size conventions

Small= .2

Medium= .5

Large= .8

meta-analysis

a procedure for statistically combining the results of many different research studies

statistical power

probability that the study will give a significant result if the research hypothesis is true.

Why is statistical power important?

-it can help determine how many participants are needed for a study you are planning

-understanding power can help you make sense of results that are not significant or results that are statistically but not practically significant

What is the relationship of power to beta?

-beta if 100% minus power.

-its the probability of not getting a significant result if the research hypothesis is true. (reject the null)

What 2 main factors does the statistical power of a study depend on?

1. how big an effect (the effect size) the research hypothesis predicts

2. how many participants are in the study (sample size)

The smaller the population standard deviation becomes, the greater the power is

...

Less extreme significance level such as ( p < .10 or p < .20) means what for power?

it means more power

*this is because more area is shaded on the normal curve