Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
24 Cards in this Set
- Front
- Back
|
Using a statistic to make conclusions about an unknown parameter. |
statistical inference |
|
|
s 2 = (1 − 2)2 + (1 − 2)2 + (1 − 2)2 + (2 − 2)2 + (5 − 2)2 5 − 1 = 3 |
Compute the variance |
|
|
randomization |
The method of is used in experiments to address the problem of lurking variables. It assigns treatments to experimental units randomly so that there is no association between the explanatory variable and any lurking variables. |
|
|
Suppose we have an approximately bell-shaped distribution of a quantitative variable x. The mean is x¯ = 100 and the standard deviation is s = 10. Also suppose we define an outlier as any observation with a z-score such that |z| > 2 (i.e., z < −2 or z > 2). This implies that an observation of x would be classified as an outlier if . |
x < 80 or x > 120 (e.g., x = 75 or x = 125) |
|
|
This means that we will conclude that the the observed association between year and beak depth |
is statistically significant |
|
|
In the finch study described above, the response variable is |
beak depth |
|
|
When estimating the mean of a population distribution using the mean from a random sample of observations, which of the following distributions must have the same mean? |
the population and sampling distributions |
|
|
Which of the following properties of the sampling distributions of x¯ and pˆ are affected by increasing the sample size? |
standard deviation and shape |
|
|
Standard deviation of sampling distribution |
σ / √ n |
|
|
Proportions: standard deviation |
√ p(1 − p) / n Mean is probability of the side |
|
|
A sampling distribution is the probability distribution of . |
A statistic |
|
|
Give the confidence interval for estimating θ. |
Point estimate + or - margin of error Ex: 12 ± 2 ⇔ (10, 14) |
|
|
A researcher wants to use this sample of observations to compute a confidence interval for the mean eruption duration for the entire year. The sampling distribution of x ____________be assumed to be approximately normal because ___________ |
could, the sample size is very large |
|
|
Indirect questioning methods like the “unrelated question” method and the “mirrored question” method are sometimes known as randomized response methods. What is being randomized with these methods through a device such as a 6-sided die? |
the question a person answers |
|
|
Decreasing the significance level (α) will [increase, decrease] the probability of a Type I error. Decreasing α will also [increase, decrease] the probability of a Type II error. |
Decrease, Increase |
|
|
significance test was conducted using the hypotheses H0 : µ = 0 versus Ha : µ > 0. The computed value of the test statistic was t = 2. The p-value is therefore the probability that , under the assumption that H0 is true. |
t ≥ 2 |
|
|
In a significance test the null hypothesis is not rejected if . |
the p-value is greater than the significance level |
|
|
Type I error is the error of a null hypothesis. |
rejecting, true |
|
|
Which of the following designs would result in two independent samples of observations? |
The researchers randomly assign each Hobbit to one of two groups. The Hobbits in one group are administered Vegemite, and the Hobbits in the other group are administered Marmite. |
|
|
2. If for each outcome the observed and expected counts are equal, then the value of the X2 test statistic will be , and the p-value will be . |
0,1 |
|
|
the previous problem the degrees of freedom for the χ 2 -distribution when computing the p-value would be . |
4 |
|
|
Which of the following statements does not characterize nonparametric tests? |
They do not require the calculation of p-values. |
|
|
Several sampling designs can be used in a mark and recapture study. We discussed two: direct sampling and inverse sampling. If we use the Lincoln-Petersen estimator to estimate N, which of the following does not depend on which design was used? (a) the standard error of the sampling distribution of Nˆ |
the estimate of N |
|
|
The apparent reversal of the association between two variables depending on whether or not we condition on or control for a third lurking variable is known as |
Simpsons paradox |
