Psychology 2802 - Research Methods II - Final Exam
1. Week 8!: Thinking More Deeply about Hypothesis Testing, Power, & Effect Sizes.
2. Another name of ANOVA is?: An omnibus test.
This tests whether the explained variance in a set of data is significantly greater than the unexplained variance, and tests
if the current model outperforms the null model. The significance value is the typical 0.05.
3. Recall the steps in null hypothesis significance testing (NHST).: - Specify the null hypothesis (H0) ("no effect"
statement).
- Choose an alpha level.
- Compute test statistics and their associated probability values.
4. The statistical significance level is denoted by alpha. What does this mean?-
: This is how much type 1 error we are willing to accept!
5. What does the p value indicate?: p value is the odds of getting a finding that extreme if there is no actual effect.
6. We always assume that there are in the null hypothesis.
If there were no effect, it would look like a distribution.: errors.
normal.
7. Define the normal distribution.: - A unimodal pattern of data, with the mode occurring in the centre of the
distribution and values dropping off sharply in a symmetrical pattern on both sides of the mean.
- Can be used to estimate binomial probabilities.
8. To comprehend the visualization of NHST:
- Let's say we have a value that is in the right tail of the distribution. The question becomes " because we are
assuming there is no effect, is this score a score that does not belong to this distribution? Does it belong to the
alternative hypothesis instead?
- So we overlap two normal distributions in a graph (like a venn diagram). Something in the right tail of the
H0 would actually be pretty low in the H1.
- An inferential statistic is compared to some critical value. If it that value, we
have significance. This is the cut off for the rejection region.: exceeds.
9. Define sampling error.: - We anticipate fluctuations/deviations from the expected value just by chance.
- It is the difference between the measurements observed in a data set and what would be expected from the
population values.
, Psychology 2802 - Research Methods II - Final Exam
10.Our null hypothesis (H0) is that the coin is fair - the probability of getting a head (or tail) on any given flip
is 0.5. The HA is that the coin is not fair (the probability of getting a head ` 0.5).
What are the decisions we can make based on this example?: - Correct deci- sion:
- The coin is fair, and we do not reject the H0.
- Correct decision:
- The coin is unfair, and we reject the H0.
- Type 1 error:
- We conclude the coin is unfair, when in fact the H0 is true. The probability of a type I error is the same as the value of
±.
- Type 2 error:
- We fail to reject the null hypothesis of a fair coin when the coin is actually unfair.
11.What are Type I and Type II errors, respectively?: - Type I:
- Alpha.
- Probability of accepting HA when H0 is true, meaning deciding that there is an effect when there really isn't.
- Type II:
- Beta (5ý)
- Probability of accepting H0 when HA is true, meaning deciding that there is not an effect when there actually is.
12.1 - 5ý =: ?- The power of the test (how likely we are to detect a real effect of a certain magnitude, given your
sample size).
- So, power is the inverse of beta.
13.In the context of comparing two means, what is the sampling distribution of the mean?: The pattern of mean
values obtained when drawing many random samples of a given size from a population and computing the mean for each
sample.
14.An important property of sampling distributions is that as sample size
, the variability (variance, standard deviation of the sampling distribution
.: increases; decreases.
15.What is the standard error? How is it calculated?: - The standard deviation of a sampling distribution.
, Psychology 2802 - Research Methods II - Final Exam
- This value is calculated by dividing the standard deviation by the square root of the sample size.
16.What is variability?: Variability refers to the divergence of data from its mean value
17.Explain the difference between standard deviation and variance.: - Stan- dard Deviation:
- The average deviation of values from the mean; it is the square root of the variance.
- Variance:
- The average squared deviation of values from the mean value.
18.What does the Standard Error of the Mean (SEM) measure?: Measures how far the sample mean (average) of
the data is likely to be from the true population mean.
19.Explain central limit theorem.: A theorem that says with a large sample size, the sampling distribution of the
mean will be normal or nearly normal in shape.
20.Explain the normality assumption.: Residuals are normally distributed.
21.Explain the homogeneity of variance/homoscedasticity assumption.: - The regression model assumes that each
residual iõis generated from a normal distribu- tion with mean 0 with a standard deviation Ãthat is the same for every
single residual.
- Variance of Y is the same across the range of X values.
22.What are the three common criticisms of NHST?: - 1. The over-reliance on p as an indicator of effect size of
importance.
- 2. The arbitrary nature of a reject/fail-to-reject decision based on p.
- 3. The overemphasis on a and type 1 errors, leading to underpowered research studies.
23.Explain some of the issues with relying on the p value.: - It refers only to statistical significance.
- Does not refer to the magnitude of the effect.
- Does not refer to the theoretical or practical importance of the result.
24.Recall what effect sizes are.
What are the three categories of effect sizes that we look at in this course?: - An effect is a primary measurement tha
you use to test your hypothesis, and the effect size is the magnitude of that effect.
- 3 categories:
1. Week 8!: Thinking More Deeply about Hypothesis Testing, Power, & Effect Sizes.
2. Another name of ANOVA is?: An omnibus test.
This tests whether the explained variance in a set of data is significantly greater than the unexplained variance, and tests
if the current model outperforms the null model. The significance value is the typical 0.05.
3. Recall the steps in null hypothesis significance testing (NHST).: - Specify the null hypothesis (H0) ("no effect"
statement).
- Choose an alpha level.
- Compute test statistics and their associated probability values.
4. The statistical significance level is denoted by alpha. What does this mean?-
: This is how much type 1 error we are willing to accept!
5. What does the p value indicate?: p value is the odds of getting a finding that extreme if there is no actual effect.
6. We always assume that there are in the null hypothesis.
If there were no effect, it would look like a distribution.: errors.
normal.
7. Define the normal distribution.: - A unimodal pattern of data, with the mode occurring in the centre of the
distribution and values dropping off sharply in a symmetrical pattern on both sides of the mean.
- Can be used to estimate binomial probabilities.
8. To comprehend the visualization of NHST:
- Let's say we have a value that is in the right tail of the distribution. The question becomes " because we are
assuming there is no effect, is this score a score that does not belong to this distribution? Does it belong to the
alternative hypothesis instead?
- So we overlap two normal distributions in a graph (like a venn diagram). Something in the right tail of the
H0 would actually be pretty low in the H1.
- An inferential statistic is compared to some critical value. If it that value, we
have significance. This is the cut off for the rejection region.: exceeds.
9. Define sampling error.: - We anticipate fluctuations/deviations from the expected value just by chance.
- It is the difference between the measurements observed in a data set and what would be expected from the
population values.
, Psychology 2802 - Research Methods II - Final Exam
10.Our null hypothesis (H0) is that the coin is fair - the probability of getting a head (or tail) on any given flip
is 0.5. The HA is that the coin is not fair (the probability of getting a head ` 0.5).
What are the decisions we can make based on this example?: - Correct deci- sion:
- The coin is fair, and we do not reject the H0.
- Correct decision:
- The coin is unfair, and we reject the H0.
- Type 1 error:
- We conclude the coin is unfair, when in fact the H0 is true. The probability of a type I error is the same as the value of
±.
- Type 2 error:
- We fail to reject the null hypothesis of a fair coin when the coin is actually unfair.
11.What are Type I and Type II errors, respectively?: - Type I:
- Alpha.
- Probability of accepting HA when H0 is true, meaning deciding that there is an effect when there really isn't.
- Type II:
- Beta (5ý)
- Probability of accepting H0 when HA is true, meaning deciding that there is not an effect when there actually is.
12.1 - 5ý =: ?- The power of the test (how likely we are to detect a real effect of a certain magnitude, given your
sample size).
- So, power is the inverse of beta.
13.In the context of comparing two means, what is the sampling distribution of the mean?: The pattern of mean
values obtained when drawing many random samples of a given size from a population and computing the mean for each
sample.
14.An important property of sampling distributions is that as sample size
, the variability (variance, standard deviation of the sampling distribution
.: increases; decreases.
15.What is the standard error? How is it calculated?: - The standard deviation of a sampling distribution.
, Psychology 2802 - Research Methods II - Final Exam
- This value is calculated by dividing the standard deviation by the square root of the sample size.
16.What is variability?: Variability refers to the divergence of data from its mean value
17.Explain the difference between standard deviation and variance.: - Stan- dard Deviation:
- The average deviation of values from the mean; it is the square root of the variance.
- Variance:
- The average squared deviation of values from the mean value.
18.What does the Standard Error of the Mean (SEM) measure?: Measures how far the sample mean (average) of
the data is likely to be from the true population mean.
19.Explain central limit theorem.: A theorem that says with a large sample size, the sampling distribution of the
mean will be normal or nearly normal in shape.
20.Explain the normality assumption.: Residuals are normally distributed.
21.Explain the homogeneity of variance/homoscedasticity assumption.: - The regression model assumes that each
residual iõis generated from a normal distribu- tion with mean 0 with a standard deviation Ãthat is the same for every
single residual.
- Variance of Y is the same across the range of X values.
22.What are the three common criticisms of NHST?: - 1. The over-reliance on p as an indicator of effect size of
importance.
- 2. The arbitrary nature of a reject/fail-to-reject decision based on p.
- 3. The overemphasis on a and type 1 errors, leading to underpowered research studies.
23.Explain some of the issues with relying on the p value.: - It refers only to statistical significance.
- Does not refer to the magnitude of the effect.
- Does not refer to the theoretical or practical importance of the result.
24.Recall what effect sizes are.
What are the three categories of effect sizes that we look at in this course?: - An effect is a primary measurement tha
you use to test your hypothesis, and the effect size is the magnitude of that effect.
- 3 categories:
