PSY 230 Exam 3 Quizlet
With alpha set to .05 two-tail, the area in each tail equals ____.
2.5%
Match the type of alternative hypothesis with the type of test (one- or two-tailed) used. A. Nondirectional alternative hypothesis B. Directional alternative hypothesis
A. Two-tailed test B. One-tailed test
In which of the following scenarios will the power of the experiment be highest?
An experiment to detect a correlation between two variables estimated at r = .80.
Is the following statement true or false? A result that is statistically significant can be assumed to be important as well.
False
The sampling distribution of the mean is the only sampling distribution used in inferential statistics.
False
You conduct a sign test and find that the calculated probability is .067. You are using an alpha level of .05 two-tailed. Given this scenario, is the following statement true or false? Based on the decision rule, you should reject the null hypothesis and conclude that the independent variable has an effect on the dependent variable.
False
H 0 and H 1 are mutually exclusive and exhaustive. (T/F)
True
You are teaching a group of students the fundamentals of statistics and test their knowledge of the subject at the beginning and end of the semester and analyze the difference scores. The correct analytic tool would be
a correlated groups t test
The sample standard deviation, divided by the square root of N , results in the _____________________________.
estimated standard error of the mean
type 2 error
failing to reject a false null hypothesis
When the degrees of freedom are infinite, the critical values in the distribution are the same as the...
z distribution
Type 1 error
Rejecting null hypothesis when it is true
What statistic must be a positive number?
Cohen's d
Statistical power is defined as the probability that the results of an experiment will:
allow rejection of H0 if the independent variable has a real effect.
Your experiment is using a one-tailed test with an alpha level of .05. Your alternative hypothesis predicts an increase in test scores. The correct value of z crit for this test is ____________.
+1.645
The sign test ignores the _________________________.
magnitude of the difference scores
confidence interval formula
mean +- z*SE - for a 95% CI, z will be 1.96, or simplify it to 2 for easier calculation (z could also be t but you don't need to know that. It will pretty much always just be 2 for this class)
The sampling distribution of a statistic gives:
-All of the values that a statistic can take -The probability of getting each value under the assumption that it resulted from chance -Is a probability distribution
In the null-hypothesis population of difference scores, µD = ____.
0
The degrees of freedom for a single-sample t test are calculated as __________________.
N - 1
degrees of freedom for correlated groups t-test
N - 1
Which of the following asserts that the independent variable does not affect the dependent variable?
The null hypothesis.
Which two of the following are assumptions underlying the use of the independent-groups t test?
The sampling distribution of the difference between sample means ( X -bar 1 minus X -bar 2) is normally distributed. There is homogeneity of variance.
Your experiment has an experimental and a control group. There are 10 participants in the experimental group and another 12 in the control group. The best test to use to determine whether there is a difference between the mean scores on a particular variable is to use _____________________________.
an independent-groups t test (unequal sample size)
decision rule (sign test)
because we can calculate the probability of chance events, we evaluate the null hypothesis to determine the probability of our outcome occurring by chance alone.
Now that you've gotten to this chapter, you know it would been preferable to use the _______________ test in place of the sign test in Chapter 10.
correlated groups t
As the size of the real effect increases, the value of Cohen's d __________________.
increases as well
The denominator in the conceptual equation for d is:
population standard deviation
When conducting hypothesis testing with a single-sample t test, if | t obt | ≥ | t crit |, you would _________________________.
reject the null hypothesis
To use the z test, the following values must be known:
sample size, sample mean, population mean, population standard deviation
The standard deviation of the sampling distribution of the mean is also known as the _________________.
standard error of the mean
null hypothesis/research hypothesis =
two sides of a coin (mutually exclusive and exhaustive)
When to use Z test
when we want to test the difference between a sample and a population
The textbook provides an example in which, despite having 100% pluses in the sample, the sample is too small to allow rejection of H 0 using the sign test. (T/F)
True
When possible, you should use the z test rather than the t test because...
it is more powerful
Which of the following are ways to achieve a low beta level when alpha is set to a stringent level (e.g, alpha = .01)? Hint: There are more than two correct answers.
-Use a statistical inference test that is the most powerful for the data. -Control the external conditions of the experiment so that the variability of the data is reduced. -Use a large sample size (N).
How to increase power
-decrease beta -increase N -increase magnitude of effect size of the independent variable -increase alpha (probability of type 1 error)
According to the textbook, experiments with power as high as ____ are desirable but rarely seen in the behavioral sciences.
.80
Power + Beta = ___.
1
degrees of freedom for single sample t-test
N - 1
Match the type of test (one- vs. two-tailed) with the hypothesis for which it is indicated. A. The new treatment will decrease depression scores. B. The new treatment will have an effect on depression scores.
B. Two-tailed test A. One-tailed test
The ______________________ holds that, "regardless of the shape of the population of raw scores, the sampling distribution of the mean approaches a normal distribution as sample size N increases" (Pagano, 2013, p. 306).
Central Limit Theorem
________________________ is used to convey effect size in an independent-groups t test.
Cohen's d
When the results of an experiment are not statistically significant, we can conclude that the null hypothesis is true.
False
When to use a t-test
compare 2 means (except for single sample t test)
To use the single-sample t test, the following values must be known:
the sample standard deviation the sample size the population mean the sample mean
You perform an independent-groups t test and then calculate the effect size and confidence interval. You find that the 95% CI ranges from -1.4 to +1.6. Based on this information you know that _____________________________.
The null hypothesis should be retained.
degrees of freedom
The number of individual scores that can vary without changing the sample mean. Statistically written as 'N-1' where N represents the number of subjects.
Which of the following statements are true regarding the t distribution?
The t distribution is symmetrical around a mean of zero. The t distribution approaches the shape of a normal curve as the number of degrees of freedom increases. The shape of the distribution varies by the number of degrees of freedom.
For which test is homegeneity of variance assumed?
independent samples t-test
Which one of the following is associated with decreased power in an independent-groups t test?
high sample variability
bidirectional
nondirectional or two-tailed
homogeneity of variance
situation in which the dependent variables/variances of two groups do not differ significantly between or among groups
The mean of the sampling distribution of the mean equals _____.
μ
between groups design
A research design in which a single individual does not provide data for more than one condition or group.
What is the value of the standard error of the mean when sigma is 10 and N is 100?
1
Which value is not used to calculate Zobt?
sample standard deviation
sampling distribution of a statistic
the distribution of values taken by the statistic in all possible samples of the same size from the same population
The 95% confidence interval is an interval such that ________________________.
the probability is .95 that the interval contains the population value
You conduct a small, single experiment and are unable to reject H0. Of the following, the most plausible interpretation is that _________________________.
there may have been inadequate power to detect a small real effect
Match the symbol or abbreviation to its meaning. 1) α 2) H 0 3) H 1
1) Alpha level 2) Null hypothesis 3) Alternative Hypothesis
Match the description to the outcome: 1) You reject H 0 when H 0 is true. 2) You reject H 0 when H 0 is false. 3) You retain H 0 when H 0 is false.
1) Type I Error 2) Correct Decision 3) Type II Error
A statistics instructor keeps meticulous records of final examination grades in PSY 230 courses she has taught. The mean score for all of the final exams she has administered is 76.23 (SD = 11.45). The mean of the final examination scores from 30 randomly selected students who had just completed the course was 80.73. Using the z test and an alpha of .05two-tail, determine whether the mean score for this sample is significantly different from the mean of the population of scores she has collected.
2.15
The more powerful the experiment, the higher the probability that that the null hypothesis will be rejected if it is false. (T/F)
True
degrees of freedom for independent samples t-test
N - 2
For the sampling distribution of X -bar to be considered normal, at least one of two conditions must be met. Which ones are they?
N ≥ 30 The population of raw scores must be normal.
You conduct a z test using an alpha level of .05 two-tail ( z crit = ± 1.96). The value of z obt = -1.5. Do you reject or retain the null hypothesis?
Retain the null hypothesis
Holding other factors constant, increasing the sample size (N) will increase power. (T/F)
True
Holding other factors constant, increasing the size of the real effect will increase power. (T/F)
True
An experiment is conducted with too few participants to provide sufficient power to detect the real effect that exists between two variables. As a result, the null hypothesis is retained even though a real effect exists. This is an example of _____________.
Type II Error
single sample t test
a hypothesis test in which we compare a sample from which we collect data to a population for which we know the mean but not the standard deviation
z-score
a measure of how many standard deviations you are away from the norm (average or mean)
When using the sign test, you determine the probability of the outcome by consulting the _______________.
binomial distribution table
The values that bound the confidence interval are called...
confidence limits
Two groups were matched on or more important characteristics. What test should you use for this?
correlated groups t-test
The ______________ test treats difference scores as raw scores and tests whether these scores are a random sample from a population of difference scores having a mean of zero.
correlated-group t
As the power of an experiment increases, the probability of making a Type II error ___________________.
decreases
Power _________ with more stringent alpha levels (e.g., using alpha = .01 instead of alpha = .05).
decreases
The _______________ for any statistic is the number of scores that are free to vary when calculating that statistic.
degrees of freedom
Cohen's d is used to ___________________________.
determine the magnitude of a real effect
In chapters 12 and 13, you learned techniques to compare a sample mean to a population mean. A major limitation to the single-sample experiment is that
in the majority of cases, a population mean (mu) is not available
According to the textbook, a power analysis can be particularly useful in the following two circumstances:
initially designing an experiment interpreting the results of an experiment
The ______________ is an actual or theoretical set of population scores that would result if the independent variable had no effect.
null-hypothesis population
This chapter introduces a research design in which participants are tested two times, resulting in paired scores. The researcher then calculates the difference between the paired scores for use in further analyses. This research design is called a _______________ design.
repeated measures
The standard deviation ( SD) of the sampling distribution of the mean is equal to __________________________________.
the SD of the raw-score population divided by the square root of N