PSYC 210- Midterm + Final Review

the size of a small correlation coefficient

0.1-0.3

Which of these is NOT considered a characteristic of standard normal distributions? A. Total area under the curve = 1.0 B. Mean = 0, Standard Deviation = 1 C. Curve is asymmetrical D. You can use the curve to estimate the proportion or percentage of scores that should fall at or below any given Z-score

C. Curve is asymmetrical

What is a variable? A. The way we measure an abstract construct B. An orderly way to assign numbers to observations C. A construct that might differ among individuals D. Coding human behavior into discrete categories

a construct that might differ among individuals

a chi square test is always one-tailed. Why?

always want to compared our chi square error (always positive) to 0 (perfect score)

In this study, we are testing whether two graders give different grades. We took a sample of students graded by Bernadette and another sample graded by Anastasia and compared their grades. Based on this jamovi output, what should we do? p-value is 0.043

reject the null hypothesis because p-value is < 0.05

When looking at confidence intervals, I am 95% sure that my ____ ___ falls within this range.

true population parameter

true of false: all expected proportions in a goodness-of-fit test must be the same

false must add up to 1 but can have differing proportions

I want to see whether time spent exercising predicts how many calories are consumed in the following meal.

simple regression

the quantity interpreted as the change in y (outcome) for one unit increase in x (predictor)

slope/beta estimate

60 students that are doing either fully remote learning, hybrid school, or in-person school are asked to take a math test and a spelling test at the end of the semester. I want to see whether type of learning affects each subjects' score differently.

2-way, mixed design, factorial ANOVA

The proportion of variation in the outcome variable explained by the predictor variable when the correlation between the two is r=0.3

9%

With both Z and t-tests, we compare mean differences to: A. what we would expect to find by chance alone B. slope of the regression line between means C. what we would expect to find in other samples D. correlations between means

A. what we would expect to find by chance alone

If 20% of students have a higher GPA than you, you are in the ____ percentile. A. 80th B. 60th C. 40th D. 20th

A. 80th

Based on the same jamovi output as in the previous question, what might we conclude? A. Anastasia and Bernadette grade differently. Specifically, Bernadette is a harsher grader than Anastasia. B. The difference between Anastasia's and Bernadette's grading is not interesting. C. Anastasia and Bernadette grade differently. Specifically, Anastasia is a harsher grader than Bernadette. D. Anastasia and Bernadette grade similarly.

A. Anastasia and Bernadette grade differently. Specifically, Bernadette is a harsher grader than Anastasia. anastasia mean 74.5 bernadette mean 69.1 bernadette lower mean

The preferred way to display the frequency of variables measured on an interval scale is a: A. Histogram B. Cumulative frequency polygon C. Pie chart D. Relative frequency polygon

A. Histogram explanation: never discussed polygons (not an option) pie charts can be a method but it's not the best because frequencies can be vary close in comparison so it doesn't clearly display the details

An assumption of the independent samples t-test is that the populations from which the samples are drawn have equal variability. This assumption is known as: A. Homogeneity of variance B. Outcomes are normally distributed C. Independence D. Heterogeneity of variance

A. Homogeneity of variance

The standard error of the mean is also like a __________________: A. Measure of the reliability of sample means in a sampling distribution. B. Measure of reliability of a standard deviation in a sample. C. Measure of central tendency. D. Measure of random deviations from a sample mean.

A. Measure of the reliability of sample means in a sampling distribution.

If a distribution is positively skewed (long tail is to the right toward larger numbers), which of the following displays the most likely set of relationships among the three main measures of central tendency? A. Mode < Median < Mean B. Mode = Mean > Median C. Mean < Median < Mode D. Median > Mode > Mean

A. Mode < Median < Mean

Which of these questions could be answered with descriptive statistics alone? A. What is the average GPA in PSYC210? B. Do students perform better on the final relative to the midterm? C. Does the number of hours spent studying predict midterm scores? D. Do males and females have different GPAs?

A. What is the average GPA in PSYC210? explanation: asking for the average/mean (center of the sample distribution); the others are making judgements/infering

Why is regression analysis so important in the social sciences? A. because it allows us to predict important outcomes B. because it uses both means and standard deviations C. because it gives us an exact outcome for a given predictor D. because it has no variance

A. because it allows us to predict important outcomes

How would you describe the concept of "line of best fit" to someone? A. it is a single line that minimizes deviations, giving us a pretty good estimator of any individual's score on an outcome B. it is a line that maximizes variance, thereby making us relatively confident that we have a line that represents most of our participants C. it is a line that perfectly fits all data points D. it gives us an exact outcome for a given predictor

A. it is a single line that minimizes deviations, giving us a pretty good estimator of any individual's score on an outcome

Pick which best applies to this scenario. I roll a die. Event A: Rolling a 1, 5, or 6; Event B: Rolling a number less than 5. -- These events are: A. Mutually exclusive B. Collectively exhaustive C. Both D. Neither

B. Collectively exhaustive explanation: accounts for all the possible outcomes of the sample space {1,2,3,4,5,6}- sides of a die Event A- 1,5 or 6 Event B (less than 5)- 1,2, 3, 4

What type of test is most appropriate when you want to compare an outcome between the same people at two completely different time points? A. Independent samples t-test B. Paired samples t-test C. t-test for correlations D. Regression and correlation analysis

B. Paired samples t-test

The process of selecting a subset of people from a population such that every person in the population has an equal chance of being chosen for the subset is called: A. Stimulus sampling B. Random sampling C. Standardizing the population D. Population sampling

B. Random sampling

In hypothesis testing, a Type I Error is: A. Failing to reject the null hypothesis when the null hypothesis is false B. Rejecting the null hypothesis when the null hypothesis is true C. Rejecting the null hypothesis when the null hypothesis is false D. Failing to reject the null hypothesis when the null hypothesis is true

B. Rejecting the null hypothesis when the null hypothesis is true

Which of the following is true of interval variables? A. They have a true zero point B. They assume equal intervals between numbers C. Dividing numbers gives meaningful results D. The numbers have no meaning (i.e., they are placeholders)

B. They assume equal intervals between numbers

A one-sample t-test tells us: A. Whether two samples are different B. Whether one sample mean is different enough from a population mean to be considered from a different population C. Whether or not we have met the assumption of homogeneity of variance D. Whether two samples are correlated

B. Whether one sample mean is different enough from a population mean to be considered from a different population

Variance is a(n) ______________ statistic? A. Random B. Descriptive C. Inferential D. Intuitive

B. descriptive explanation: tells us how much data with in a sample vary with each other; the spread of the distribution

The alternative hypothesis for a paired-samples t-test states __________. A. µ1 = µ2 B. µ1 - µ2 not equal to 0 C. µ1 - µ2 = 0 D. µ1 + µ2 not equal to 0

B. µ1 - µ2 not equal to 0

Alpha level corresponds to: A. Cannot answer without additional information B. Power C. The probability of a Type I Error D. The probability of a Type II Error

C. The probability of a Type I Error

What type of statistic allows us to make judgments about the population? A. Random B. Descriptive C. Inferential D. Intuitive

C. inferential explanation: to infer conclusions about the population with the given statistics

If one were testing whether a particular mean was drawn from a particular population and we did not have the population standard deviation, one would use the ______test to statistically answer the question. A. Z B. F C. t D. r

C. t

Roger has 10 Dalmatian puppies, and Anita has 5 Dalmatian puppies. 5 of Roger's puppies have brown eyes, 5 have blue. Two of Anita's puppies have brown spots while the rest have black spots. Every weekend, the owners each pick one of their puppies at random and have a puppy playdate. What is the probability that we have a blue-eyed puppy from Roger OR a brown-spotted puppy from Anita on a playdate this weekend? A. 4/5 or 0.8 B. 9/10 or 0.9 C. 1/5 or 0.2 D. 7/10 or 0.7

D. 7/10 or 0.7

Why would you be interested in graphing your data before conducting any inferential statistics? A. To see if you have any outliers that may impact the conclusions you draw B. Many statistics tests operate under the assumption that you have a normal distribution C. Jamovi will not let you conduct analyses without graphing your data first D. Both A and B

D. Both A and B A. To see if you have any outliers that may impact the conclusions you draw B. Many statistics tests operate under the assumption that you have a normal distribution

A _________________ variable has theoretically infinite values. A. Dependent B. Discrete C. Ordinal D. Continuous

D. Continuous

Using letter grades (A, B, C, D, and F) to classify student performance is an example of a(n) __________ scale. A. Ratio B. Continuous C. Interval D. Ordinal

D. Ordinal explanation: there's an order/ranking but don't have specific intervals and can't multiple or add these letter grades

Why do we prefer to use standard deviation (SD) over variance when we have interval or ratio data? A. SD is simpler to calculate B. Variance is in raw units, making it more interpretable C. We do not prefer SD to variance D. SD is in raw units, making it more interpretable

D. SD is in raw units, making it more interpretable explanation: variance squares the statistic and the units (i.e # of drinks squared doesn't make sense or dogs squared)

In a hypothesis test, the critical region consists of __________. A. Sample values that provide proof that the null hypothesis is true B. Sample values that are highly likely to be obtained if the null hypothesis is true C. Sample values that provide proof that the null hypothesis is false D. Sample values that are very unlikely to be obtained if the null hypothesis is true

D. Sample values that are very unlikely to be obtained if the null hypothesis is true

The standard error of the mean is the ______________ of the sampling distribution of means. A. Variance B. Mean C. Skewness D. Standard deviation

D. Standard deviation

Why do we transform scores? A. To make life more complicated B. To get a mean and standard deviation C. To change scores to raw units D. To make different distributions comparable

D. To make different distributions comparable

When would the median be the most effective way to describe a distribution? A. When the data are normally distributed B. The median is never appropriate C. When the data are nominal D. When the mean is skewed by outliers

D. When the mean is skewed by outliers

a p-value correction method that involves multiple all p-values by the number of tests that were run

bonferroni correction

Chi square tests are the only ones we have learned with this type of outcome variable

categorical or nominal

Park rangers who relocate bears recorded their species and observed whether the bears remained in their new location, moved back, or moved to another location. They want to know if there is an association between species and outcome of relocation.

chi-square test of independence (association)

According to the Central Limit Theorem, as the sample size increases, the standard error

decreases

The equation for this item is column 1 total number (C1) divided by overall total number of ppl (N) then multiplied by the row 1 (total number (R1)

expected value for cell (1,1) or E11

This is the test statistic for an ANOVA

f-ratio

this increases power by reducing the standard error of each distribution

increasing sample size

I am testing whether cities with billboards about drunk driving (vs. no billboards) have fewer DUIs

independent samples t-test

Though shark attacks and ice cream sales are not correlated, they are not causally linked. This is because temperature acts as this type of confound.

lurking variable

Based on the graph relating two variables to each other, these are the effects you might expect to be significant

main effect A main effect B no interaction between A and B

What type of skew does this frequency distribution exhibit?

negative

the p-value of my t-test is obscured, but i see that the confidence interval includes my comparison value (0) and i have cohen's d of 0.4. I can say this about my experiment

nothing there is no significnat result so effect size doesn't matter

this is the degrees of freedom of denominator (dfwithin) of a one way ANOVA

number of ppl - number of groups (N-k)

the term used to describe that ANOVAs compare all groups simultaneously, instead of individually

omnibus test

These two effect sizes have a similar interpretation: they explain the variance explained in the outcome by the predictor variable (s).

r squared eta squared

The two main categories of effect sizes, with an example of each

r-squared, eta squared (associations) cohen's d (differences)

equation for the chi-square goodness of fit statistic

sum of (Oi - Ei)^2/Ei for all groups i

I want to compare UNC's average SAT score to the U.S population and I know the mean and standard deviation of the population.

use a z-test

A regression line is provided as y=5.6x + 13.42. 13.42 represents this quantity

y-intercept