PSYCH 210-Final
Interval estimate
"A range of values used to estimate the population parameter" -confidence interval: a range of vlaues that has a specific probability of containing the value of the population parameter -to create a confidence interval, start with the point estimate and then include a margin of error
Cumulative percentage
(Cf/N)*100
Interaction effect interpretation
(For two-way ANOVA) the effect of (name of one factor) on DV depends on (name of other factor)
Coefficient of determination interpretation
(R squared value ) of the variance in (DV) is explained by (IV)
R squared for regression interpretation
(R squared) of the variance in DV is explained by the set of independent variable
Z
(X-m)/s
Between group variance
- differences between group means - caused by the independent variable plus some error
Why would you be interested in graphing your data before conducting any inferential statistics?
- to see if you have nay outliers that may impact the conclusion you draw -many statistics tests operate under the assumption that you have a normal distribution
When should you use regression?
- to see the strength of the relationship between two variables -to compare multiple variables on outcome of y -when you have a continuous independent variable and continuous dependent variable
Regression allows us to predict one variable from another variable by using the "line of best fit" to give us an estimation of the relation that exists between the two variables. Which of the following is/are limitations of regression
-it doesnt tell us the relative strength of the relationship -it doesnt allow us to truly compare relations between variables
What does the confidence interval depend on?
-the amount of variability -the sample size
Size of the interval depends on:
-variation: more varied= narrower -sample size: larger N= narrower (more info)
If the null hypothesis is confirmed then the correlation coefficient (r) should be___
0.0
A small correlation affect is indicated by a Pearson coefficient of___?
0.1
What are the standard effect sizes for the correlation coefficient r?
0.1, 0.3, 0.5
Steps for hypothesis testing
1. State the hypothesis * Null ,then alternative; words and notation 2. Set the alpha (0.5) 3. Collect data and compute test stat 4. Determine probability (p) 5. Make a decision about the null hypothesis if p, alpha, reject the null if P> alpha, fail to reject the null
How many factors and how many conditions exist within a factorial sleep study comparing the amount of sleep ( 8 vs 4 hours) and reset difficulty (easy vs. hard) to test performance
2 factors, 4 conditions
The factorial anova design requires how many variables
2 or more
A factorial anova compares means across ___ or more ___ variables
2, independent
Eta squared interpretation
47% of the variance in depression scores is accounted for by treatment
Jessica wanted to know how many conditions and factors a 2x3 design would have?
6:2
Roger has 10 Dalmatian puppies, and Anita has 5 Dalmatian puppies. 5 of rogers 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 play date. What is the probability that we have a blue eyed puppy from Roger OR a brown-spotted puppy groom Anita on a play date this weekend?
7/10 or 0.7
If 20% of students have a higher GPA than you, you are in the ____ percentile
80th
Confidence levels and z values
95%: 1.96 99%: 2.58
Dfbetween
=number of groups-1=k-1
In a one way anova, the total sums of square is equal to..? a. The sum of squared deviations b. The sum of square-rooted deviations c. The sum of between groups SS and within group SS d. A and C E. B and
A and C
Which fo the following are correct assumptions of factorial anova? a. Your dependent variable should be continuous b. Each sample has NOt been drawn independently of the other samples c. Your two independent variables should be categorical, independent groups d. A and C are both correct
A and C are both correct
You are analyzing a scatter plot that has a negative correlation. What is true of the x and y values? A. As x increase, y decreases b. As x increases, y increases c. As x decreases, y decreases d. As x decreases, y increase e. A and d are both correct
A and d are both correct
Which of the following is not applicable to a chi square test?
A chi square test can be sued to view frequencies, means and percentages
Concerning Cohens d, what relationship does a large effect size have with type II error rates?
A large effect size decreases type II error rates
Which of the following study scenarios would be best tested using a one-way anova?
A researcher wants to examine for differences in happiness level in fall, winter, spring and summer
Which of the following study scenarios would be testing using a factorial anova?
A researcher wants to test if there are differences in happiness level as function of gender (male, female, non-binary) and marital status (married, single)
Point estimate
A value of the sample statistic is used to estimate the population parameter Problems: we know the sample statistic will vary from sample to sample due to sampling error
For what type of test would a non-normal distribution be used: a. T-test b.z-test c. ANOVA. D. None of these
ANOVA
Which of the following statements is false? a. Multiple regression can handle all th question that we do with factorial anova b. ANOVA can handle all the question we have with regression
ANOVA can handle all the question with regression
Turkey test
ANOVA post-hoc test HSD= the minimum different between two means that is necessary for significance
Standard error
Across multiple samples, the average difference between values of the sample statistic and the value of the population parameter
Assumptions of regression/correlation: A. Interval or ratio scales b. Linear relationship c. Normal distributions for X and Y d. None of the above e. All of the above
All of the above
The sample mean a. Tells us what we would expect to find if we kept sampling b. Allows us to test the null hypothesis c. Adds in some "wiggle" room because it will never be the exact population mean d. All of the above
All of the above
Which fo the following tests could you put a confidence interval around? A. Difference between correlated means b. Correlation coefficient c. Difference between independent means d. All of the above
All of the above
Which of the following is not an assumption for factorial anova testing? a. Continuous dependent variable b. Categorical independent variable c. Homogeneity of variance d. All of the above are assumptions
All of the above are assumptions
Which wya can you not measure effect size? a. Cohens d b. R^2 you can meaure effect size with this c. Eta^2 d. Omega^2 e. All of these are correct
All of these are correct
It is concluded that the f statistic was near 1.0. What does this mean
All samples can from the same distribution
Which fo the following in not an effective way to convey the strength of a particular relationship?
Alpha
What is a variable
An item that might differ among individuals
What effects CI and margin of error?
As confidence level increases, margin of error increases as sample size increases, margin of error decreases as sample standard deviation increases,margin of error increases
If you have a graph and there is a negative correlation, what is true about the x and y values?
As x increases, y decreases
What phrase indicates main effect?
Average
If you have one sample mean, an ANOVA test and t-test can both be performed. A. True b. False
B. False
Which is the term regarding one way anova for when you are observing different participants once in each group?
Between groups
When we run a 2-way between-subjects factorial analysis of variance, we are partitioning the ____ into three meaningful parts
Between groups variance
Which of the following is considered a limitation of regression? a. Not showing us a line of best fit describing the relationship between two variables B. Not telling us the relative strength of a relationship c. Not allowing us to truly compared relations between variables d. Both b and c
Both b and c
Of the following Cohen's d values, which indicates the largest effect size? A. 0.3 B.0.1 C.-0.5 D.0.2
C.-0.5
What variable type is necessary to perform a chi squared test?
Categorical
Which type of variable do we use with a chi-square
Categorical
Observed and expected frequencies are compared in which type of test?
Chi square
What is one difference between multiple regression and a chi-square test? a. Multiple regression can only handle discrete variables b. Chi-square can only have discrete variables c. Chi-square is technically not a statistical test d. Multiple regression compares observed frequencies
Chi-square cna only handle discrete vairables
Which of the following statistics is not useful in calculating the confidence interval range?
Chi-square significance value
What reason is not correct as to why chi-squared testing is considered a non-parametric test?
Chi-square testing deals with continuous (interval, ration) variables best represented by means rather than medians
R squared
Coefficient of determination
Which of the following is not a reason why we like to use effect size
Cohen's d is the unstandardized size of the difference
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:
Collectively exhaustive
How does the chi-square test differ from other hypothesis tests?
Compares categorical variables
Reliability of a smaple statistic
Consistency of the sample results mean is most reliable estimate of the population central tendency
A _____ variable has theoretically infinite values
Continuous
Both regression and correlation deal with ___ outcomes
Continuous and ratio
What is not an assumption of factorial anova? A. Continuous independent variable b. Interval or ratio outcome c. Homogeneity of variances d. Independence of observations
Continuous independent variable
Which analysis technique should i use for the following scenario? I am very interested in the relationship between the number of trees in a city and the average temperature within the city. I think less trees might relate to higher temperatures, or higher temperatures relate to less tree growth, but the order is interchangeable
Correlation
The chi-square analysis test is unique to the other test form this semester in teh fact that:
Critical values increase as the degrees of freedom increase
Which of these is NOT considered a characteristic of standard normal distributions?
Curve is asymmetrical
According to the central limit theorem, as the sample size increases, the standard error ____
Decreases
Variance is a ____ statistic?
Descriptive
In a simple analysis of variance (non-factorial), which of the following statements is nit true
Dfbetween=number of groups-number of people per group
What is one thing that confidence interval cannot estimate?
Difference between two dependent means
Which is true about correlation
Extreme scores can inflate correlations
How do you calculate f for a one-way anova
F=Msbetween/MSwithin
If you have more than two means and more than one independent variable, what test should you use?
Factorial ANOVA
Which of the following would be best to use if you wanted to test the effect of the quantity of a drug taken and the effect of gender on the reduction of a migraine?
Factorial anova
You are given a data set which contains the race, sex, and amount of caffeine consumed per week of a sample group of college students. With this data set, you are asked to determine if and how race and sex effect amount of caffeine consumed. Which test would best allow you to do this?
Factorial anova
Which of the following is true about factorial anova
Factorial anova is comparing the effect of multiple groups of two independent variables on a dependent variable and on each other
In this study, we are utilizing an effect size to measure which has ore of a positive impact on academic success, the fear of failure or the prospect of academic success. Higher scores on each individual variable indicated higher levels of academic success. Fear of failure was calculated to have a mean value of 5.4 while prospect of success had a mean value of 7.5. We calculated a d value of 3.2. Therefore, fear of false is 3.2 standard deviation better than the prospect of success on academic success
False
If the r is closer to 1 or 01, but it is not equal to 1 or -1, this means he linear model:
Fits well
Sampling error
For a single sample, the difference between the sample statistic and the population parameter
A researcher runs a multiple regression model with anxiety as the outcome and number of cups of coffee and number of hours slept as the predictors. The unstandardized slope for cups of coffee was estimate to be -0.2. What is the correct interpretation of this number?
For each additional cup of coffee assumed, anxiety is expected to decrease by 0.2 points, holding constant numbers of hours slept
Null for t test
For independent groups, H0: muy-mud=0 for related groups, H0=muD=0
A priori (before the experiment) power analyses are useful tools because they
Give us the minimum number of participants needed to achieve 80% power
Which is an example of something that could be tested using one-way anova?
Happiness levels for low, medium, and high income
Which of these is not an assumption when using factorial anova
Heterogeneity of variance
What is not an assumption of regression/ correlation?
Heteroscedasticity
The preferred way to display the frequency of variables measured on an interval scale is a :
Histogram
Which of the following is not an assumption for chi-square
Homogeneity of sample
An assumption of the independent samples t-test is that the population from which the samples are drawn have equal variability. This assumption is known as:
Homogeneity of variance
Which of the following is not an assumption fo chi-squares
Homogeneity of variances
What does the f-ratio tell us
How large the differences between groups are when you take into account the differences within individual groups
Regression refers to ___
How much of an outcome cna be determined by a predictor
2-way ANOVA
IV: 2 or more, discrete DV: continuous descriptive state: M, s test stat: F effect size: eta squared
Correlation
IV: continuous DV: continuous descriptive stat; scatter plot and r test stat; r effect size; r squared
Chi square goodness of fit test
IV: discrete DV: discrete, one descriptive stat; f test stat; chi squared effect size; nope
Chi square test for independence
IV: discrete DV: discrete, two descriptive stat: f test stat: chi squared effect size: Cramers V or phi
t test
IV: discrete, one DV: continuous descriptive stat: M, s test stat: t effect size: r squared, d
ANOVA
IV: one, discrete DV: continuous descriptive stat: M, s Test stat: F effect size: eta squared
Multiple regression
IV; continuous, two or more DV; continuous descriptive stat: beta effect size: R squared
Which of the following statements about anova and f tests is true?
If your f value is larger than your critical f statistic, the null hypothesis can be rejected
How is a chi square test imitar to an independent sample t test?
In both , you are comparing a sample to a population
Reporting results guidelines
Include the test statistic, degrees of freedom, and probability if the result is significant, then the report should also include effect size
What type of statistic allows us to make judgements about the population?
Inferential
Which term fits this definition: "the effect of one factor is different depending on the level of the other factors"?
Interaction effect
All of these are aspects of regression but which of the following
Is a casual test
What is a benefit for using anova over other tests?
It is an omnibus test so it does not inflate type I error
What is not true about the correlation coefficient (r)?
It is the percent of variance explained by a variable
What does the word "factorial" mean in a factorial anova
It's a two by two design, i.e its cross sectional has 2+ independent variables
If the null hypothesis fo ra one-way anova is true, then we have
Just error variance
Correlation allows us to :
Know the relative strength of a relationship
For chi-square, critical vlaues get ___ as degrees of freedom get __ which is the opposite form a T and f test
Larger, larger
The ___ minimizes the difference between your predicted outcome and the outcome you actually observed a. Correlation b. Line of best fit c. Scatter plot d. R statistic
Line of best fit
Factorial design allow us to study both __ and __ effects of the independent variables on dependent variables
Main and interaction
In factorial anova, the ___ is the effect of one factor, ignoring the other a. interaction effect b. Main effect c. Degrees of freedom d. Crossed effect
Main effect
What are we looking for when using a factorial anova
Main effects and interactions
How does a larger sample size affect interval width?
Makes it narrower
Negatively skewed distribution
Mean<median<mode
The standard error fo the mean is also like a ____
Measure of reliability of sample means in a sampling distribution
r2: 0.9 is a:
Medium effect
If a distribution is positively skewed, which of the following displays is the most likely set of relationships among the three main measures of central tendency
Mode<Median<Mean
Positively skewed distribution
Mode<median<mean
When looking at the f ratio, if your numerator is larger than your denominator which of the following can you conclude about your result?
More likely not due to chance
Which of the following is incorrect in regards to one way anova testing?
Mstotal=Msbetween+MSwithin
Which are true for regression? a. Must have at least 2 variables (predictor and outcome) b. Just be categorical outcome c. It is rarely used amongst psychologist d. Both a and b
Must have at least 2 variables (predictor and outcome)
df
N-2
If a science teacher tells her class: "all those who got 100 on the science test got 20 on the English test, and all of those that got 100 on the English test got 20 on the science test", she is saying that the correlation between the science test and the English test is :
Negative
Which fo the following is not true about effect sizes
Omega squared cannot be sued
Standard deviation interpretation
One average, (name of variable) scare are (value of s ) points away fro the mean
Point biserial correlation
One variable is continuous, the other is dichotomous (correlation coefficient)
If i were to test a smaple in which the data is continuous with more than two means, but one independent variable which test would i use?
One way anova
If you want to compare two group means, conduct a ___ analysis and if you want to examine the effect of two categorical variables (factors) on an outcome, conduct a___ analysis
One way anova, two way anova
Why d we tend to use two-tailed tests in psychology?
One-tailed tests might miss an effect in the opposite direction
What is the difference between one-way anova and chi-squared tests?
One-way anova has continuous dependent variables and chi-square has categorical dependent variables
A one-way ANOVA compared group means of ___ factors(s), and ___ take into consideration interaction effects of the factors in question a. One; does not b. One;does c. Two; does not d. Two;does
One; does not
Using letter grades to classify student performance is an example of an ___ scale
Ordinal
What type of test is most appropriate when you want to compare an outcome between the same people at two completely different time points?
Paired samples t-test
A 95% confidence interval indicates that 19 out of 20 samples (95%) from the same population will produce confidence intervals that contain the population ___
Parameter
Which of the following would require a repeated-measures (within-subjects) ANOVA?
Participants are tested on how well they can draw by looking at a mirror before completing a coordination task in front of a mirror and after the task is over. We also get a third mirror drawing from them a week later. We are interested in the changes to their mirror drawing speed before the task ,immediately after the task ,and a week later
Factorial anova is an extension of one-way anova by:
Partitioning variance within the "between" group variable
Researchers want to conduct a chi-square analysis to exit polling results form the 2018 midterms. Which of the following dependent variables would they use a chi-square test for?
Political party affiliation
To test which means differ we can use
Post hoc test and planned contrasts
Pairwise comparisons, made after finding that F is significant, that are used to determine which Paris of means are significantly different are known as:
Post hoc tests
Which of the following tests is used to find which samples are significantly different from the others after an anova test
Post-hoc test
When R is squared, you get ___ variance that two variables share
Proportion of
Why is omega-squared considered "better" than r-squared when interpreting effect size?
R tends to overestimate the true population parameter rho
What measure of effect size is preffered for multiple regression
R-squared
Which of the following is true about an r-squared value?
R-squared is the percent of variance in Y that is related to X R-squared. An be used to describe the seize of an effect
Which value represents the percentage of shared variance between two variables in a regression model? a. r b. F c. r2 d. Z
R2
The process of selecting a subset of people form a population such that every person in the population has an equal chance of being chosen for the subset is called:
Random sampling
You are interested in whether or not eating junk food befor ebed can predict sleep quantity. You should use which test?
Regression
If i were interestin in determining if two means different from each other and the 95% confidence interval of my mean difference from 5.24 to 12.59, what would i conclude?
Reject the null hypothesis because the confidence interval does not include the value of my null hypothesis (zero)
In hypothesis testing, a type I error. Is:
Rejecting the null hypothesis when the null hypothesis is true
Why do we prefer to use standard deviation (SD) over variance when we have interval or ratio data?
SD is in raw units , making it more interpretable
Confidence interval for population mean
Sample mean +- z(standard error) M+-(1.96)(s/square root of n)
Which of the following is not an assumption of chi-squared test?
Sample size greater than 30
In hypothesis testing, the critical region consists of ___
Sample values that are very unlikely to be obtained if the null hypothesis was true
A researcher runs a multiple regression model with satisfaction with life as the outcome and sense of community and self-efficacy as the predictors. They obtain the following results: sense of community: estimate= 3.0, standardized estimate= 0.8, p=0.2 self-efficacy: estimate=3.0, standardized estimate=0.6, p=0.001 which, if any, is the string predictor of satisfaction with life and why?
Sense of community because it has a larger standardized estimate vlaue
Which of the following statistical values would be best to determine the main effect of sex on income
Sex significance value
Within group variance
Spread or dispersion of scores within each group - caused by error (individual differences, sampling error, incontrolled caravels etc.)
The standard error fo the mean is the ____ of the sampling distribution of means
Standard deviation
In correlation data, we ______ data in order t make distributions comparable
Standardize
If we were testing whether a particular mean was drawn from a particular population and we did not have the population standard deviation, we would use the ____ test to statistically answer the question
T
Which is not of the big three measures of effect size?
T-statistic
If you do an ANOVA test with two groups what test is that equivalent to? a. F-test b.p-test c. T-test d.d-test
T-test
In regression, residual refers to :
The difference between the predicted value of an outcome and the actual observed value
The main effect refers to__
The effect of one factor, after collapsing over the other
In a 2-way analysis of variance, when we say we have an interaction, we mean that:
The effect of one independent variable on a dependent variable differs as a function of a second independent variable
Probability interpretation
The likelihood that (name of statistic) occurred by chance is (p value)
In a 2-way analysis of variance, when we say we have a MAIN EFFECT, we mean that:
The means for the levels of factor A after collapsing over Factor B are significantly different from one another
Alpha level corresponds to
The probability of type I error
R-squared can be interpreted as:
The proportion of variance in Y that is accounted for/ explained by X
If your chi-square critical value is 3.0 and your observed sum of chi-squares is 3.45, then:
The relationship is statistically significant, because the observed alum is greater than the critical value
Which is not an example of effect size
The standard deviation
For a t-test, what would a d-value of 1.0 mean
The two groups mean differ by a standard deviation of 1.0
What does it mean if a research design is described as 4x4x4 factorial design
There are three factors with four levels each
Confidence confidence interpretation
There is a (strength, direction) direction between IV and DV AND EITHER: - As IV increases, DV decreases -People who have more IV tend to have less DV
What does it mean when we choose a confidence level of 95%
There is a 95% probability that a confidence interval will contain the true population mean
Cramer s V interpretation
There is a ___ relationship between IV and DV (same guidelines as r)
After running a regression analysis, we find that the R^2 between the two variables is 0.8. What can be concluded from this?
There is a strong correlation between the two variables
A correlation coefficient of -0.82 tells us
There is a very string negative relationship between x and y
Why is Cohen's d similar to z-scores?
They are both standardized
Which of the following is true of interval variables?
They assume equal intervals between numbers
What makes f values in one-way ANOVA test different from t-tests?
They can only be positive
Why do we transforms scores?
To make different distributions comparable
Dfwithin
Total number of scores-number of groups= N-k
Two-way chi-square tests are best for which kind of variables?
Two or more categorical variables
The alternate hypothesis for a two-tailed paired samples t-test states:
U1-u2 not equal to 0
The size of the interval depends on:
Variation and sample size
If the confidence interval is 3.21< mu<4.88, and we are working with 95% confidence , what can we conclude about the population mean?
We are 95% confident that the true mean falls within this interval
A 95% confidence interval around a given sample statistic can be interpreted as:
We are 95% confident the true population parameter is between the upper and lower bounds of the interval
If we were to run a n f-test, and got a value of -1.0, what would we conclude from out findings?
We made an error in out test calculations
Which of these questions could be answered with descriptive statistics alone?
What is the average GPA in PSCU 210?
When would it be best to use a chi-square? - when are you trying to determine sample means -for regression and correlation studies -when it has to do with life and death -for main effects and interactions
When it has to do with life and death
When is the difference between mean considered unimportant, even if it's statistically significant?
When its smaller than 0.2 standard deviations
When should you use a one-way anova test/
When testing if there are statistically significant differences between the means of three or more
When would the median be the most effective way to describe a distribution?
When the mean is skewed by outliers
When are confidence intervals useful?
When you want to find out how a sample statistic compares to the population
A one-sample t test tells us:
Whether one sample mean is different enough from a population mean to be considered from a different population
Regression
Y hat=bx+a Se (standard error of the estimate ) IV and Dv are continuous
Does chi-squares critical value increase as degrees of freedom increase?
Yes, unlike t-tests and ANOVA
You are conducting a one-sample t test and decide to use a 90% confidence interval. What is the best interpretation of this interval/
You are 905 sure that this (computed) interval contains the true population mean
Which of the examples below represents and interaction effect?
You wish to conduct your own basic experiment using 2 foods ( hot dogs and ice cream) and 2 condiments ( mustard and chocolate syrup) and you wish to measure enjoyment of the combination
