When does sampling error occur?
When a sample statistic is not equal to the population parameter as a result of chance factors.
If a sample mean is different from a particular population �, we can conclude that the sample mean probably represents some other population or that
the sample mean occurred as a result of sampling error.
The key difference between parametric and nonparametric procedures is that parametric procedures
require that certain stringent assumptions be met.
Inferential statistics are used to
decide whether sample data represent a particular relationship in the population.
Which of the following assumptions is common to all parametric statistics?
The population of dependent scores, which must be interval or ratio scores, forms a normal distribution.
Which of the following is correct regarding experimental hypotheses?
They describe the predicted relationship we may or may not find in an experiment.
When is a two-tailed test used?
When a relationship is predicted without stating the direction in which the scores will change.
When is a one-tailed test used?
When a relationship is predicted and the direction in which the scores will change is predicted.
Which of the following is correct regarding statistical hypotheses (null hypothesis and alternative hypothesis)?
They describe the population parameters our sample data represent if there is or is not a predicted relationship.
Which of the following is correct regarding alternative hypotheses?
They describe the population parameters represented by the sample data if the predicted relationship exists.
Which of the following describes the situation if the relationship you are testing in your experiment really exists?
The alternative hypothesis.
Which of the following is true of any one-sample experiment?
We must know the population mean under some condition of the independent variable other than the one being tested.
The null hypothesis describes the
population parameters represented by the sample data if the predicted relationship does not exist.
Which of the following is called the hypothesis of "no difference"?
The null hypothesis.
Which of the following alternative hypotheses would require using a two-tailed test?
H(a) : � does not = 100
Which hypothesis is actually being tested in statistical hypothesis testing?
The null hypothesis.
When can the z-test be used in statistical hypothesis testing?
When the raw score population's standard deviation is known.
The population mean for the Elementary Tenacity Test (ETT) is 150, with ?(x)=25. A recent study of elementary school children participating in a school lunch program obtained the following ETT scores. Use a two-tailed z-test and ? = 0.05.
Z(crit) = � 1.96, z(obt)= 1.77. Fail to reject H(a).
What does the null sampling distribution describe?
The sampling distribution when the null hypothesis is true.
In using a sampling distribution of means for statistical hypothesis testing, the mean of the sampling distribution will always equal
the � described by H(0).
What does alpha always represent in statistical hypothesis testing?
The relative size of the region of rejection.
For a two-tailed test where ? =0.05, Z(crit) is always equal to
� 1.96
If X-bar =82, � =79, ?x =15, and N=25, what is the value of Z(obt)?
1.00
If X-bar =34, � =37, ?x =8, and N =12, what is the value of Z(obt)?
-1.30
If X-bar =53, � =51, ?x =10, and N =15, what is the value of Z(obt)?
0.78
For H(0) : � -50, H(a) : � does not =50, X-bar =52, ?x =3, N =16, and ? =0.05, what is the appropriate outcome of a z-test?
Z(crit) =�1.96, z=2.67. Reject H0 and accept Ha.
For H0 : � ?76, Ha : � > 76, X-bar =78, ?x =5, N =25, and ? =0.05, what is the appropriate outcome of a z-test?
Z(crit) = +1.645, Z=2. Reject H0 and accept Ha.
For H0 : � ?22, Ha : � <22, X-bar =25, ?x =5, N=9, and ? =0.05, what is the appropriate outcome of a z-test?
Z(crit) = -1.645, Z(obt) =1.79. Fail to reject H0.
For H0 : � ?34, Ha: � <34, X-bar =30, ?x =6, N =9, and ? =0.05, what is the appropriate outcome of a Z-test?
Z(crit) = -1.645, Z(obt) =-2.0. Reject H0 and accept Ha.
When statisticians report that the results from an experiment are significant, this means the results
are too unlikely to accept as sampling error.
When experimental results are significant, this means that the ____ hypothesis has been ____.
null; rejected
Which of the following statements does not belong?
The change in the dependent scores was produced by significant sampling error.
Jeri has conducted a study on the average salary of recent graduates in her major at State College. She has randomly selected and surveyed 25 recent graduates from her program. The annual average income of this sample of recent graduates is $34,000. Jeri
Z(crit) =�1.96, Z(obt) =2.5. Reject H0 and accept Ha.
When statisticians report that results are non significant, the results are
not too unlikely to accept as representing the same population.
What happens when the experimental results are nonsignificant?
The null hypothesis has not been rejected.
Suppose you have randomly selected high school students to take a course to improve their SAT scores. You find that the mean of their subsequent SAT scores is not significantly different from the population mean of SAT scores for those students who have n
We have obtained no convincing evidence that the course affects SAT scores.
Which of the following statements is true when H0 is not rejected?
The data do not provide sufficient evidence of a relationship in nature.
Suppose you conduct an experiment and your Z(obt) is statistically significant at +3.45. How would you correctly report this result?
Z(obt) =+3.45; p < 0.05
Suppose you conduct an experiment and the Z(obt) is statistically nonsignificant at -0.65. How would you correctly report this result?
Z(obt) = -0.65; p > 0.05
Suppose that a population is known to have a mean of 80. If a researcher predicts the experimental treatment will produce an increase in the population mean, then the null hypothesis for this statistical hypothesis test would state
� ? 80
For a one-tailed test where the predicted value of the sample mean is larger than the population mean and ? =0.05, Z(crit) is always equal to
+1.645
The Physical Fitness Test (National Level for Girls) shows the national average for 10-year-old girls on "right-angle push-ups" to be � =13. Principal Smyth hypothesizes that her girls at Strong School are significantly above the national mean. If the ?x
Z(obt) = 1.5, so Principal Smyth is wrong.
To determine whether a new drug that is supposed to lower a person's heart rate is effective or not, Dr. Johnson gives the medicine to a random sample of 100 patients with rapid heart rhythm (RHR) and obtains a sample mean of 128. Dr. Johnson knows that t
Z(crit) = -1.645, Z(obt) = 1.75. Reject H0 and accept Ha.
In a one-tailed test, Z(obt) is significant only if it lies
in the tail of the distribution beyond Z(crit) and has the same sign as Z(crit).
When choosing between one-tailed and two-tailed tests,
use a one-tailed test only if you have a convincing reason for predicting the direction.
Which of the following accurately defines a Type I error?
Rejecting H0 when H0 is true
Which of the following represents a Type I error? We say that something
works when it really doesn't.
If you reject the null hypothesis, which of the following may occur?
A correct decision or a Type I error
Which of the following is correct regarding the probability of making a Type I error?
p = ?
Which of the following is the probability of avoiding a Type I error?
p = (1 - ?)
What happens to the probability of committing a Type I error if the level of significance is changed from ? = 0.01 to ? = 0.05?
The probability of committing a Type I error will increase.
What does it mean when a computer printout reads "p =0.03"?
The Z(obt) falls in the extreme 3% of the sampling distribution and the probability of a Type I error is 0.03.
Which of the following accurately defines a Type II error?
Failing to reject H0 when it is false
The power of a statistical test is the probability of
rejecting a false H0
Which of the following tests is considered to be more powerful?
A one-tailed test.