Chapter 7 - Single-Sample t Test
the critical value for a one-tailed z test with alpha = .05 is always
+1.65 or -1.65
which of the following alpha values creates a greater probability of a type II error?
.01
which of the following alpha values creates a greater probability of a type I error?
.05
which of the following alpha values results in more statistical power?
.05
as N increases, the t critical value is closer to
0
degrees of freedom (df) for a single-sample t test are computed as
N-1
T/F: the shape of the t curve is different for every sample size
T
degrees of freedom
a heuristic that tells us which version of the distribution to use
you can also use the single-sample t statistic when you need to determine if
a sample mean is significantly different from any number of 'theoretical' interest
when performing a t test, increasing the sample size will _________ the amount of sampling error expected. this means the denominator of the t test will be ________
decrease; smaller
the number in the parentheses in the character string "t(14)=2.22, p<0.5, =.57" is the
degrees of freedom
error term
denominator of the z test
the degrees of freedom are used to
determine the critical value
when performing a single-sample t test, which of the following assumptions is the most difficult to assess?
homogeneity of variance
what does the single-sample t test determine?
if the difference between a sample mean and a population mean is likely to be due to sampling error
will smaller sample sizes lead to larger or smaller critical t values?
larger
if the research hypothesis indicates that scores will decrease, the critical value will be
negative
what sign should you always use for a two-tailed research hypothesis?
not equal sign
one-tailed significance tests have...
one critical region that is either on the positive or negative side of a distribution
why is your decision to conduct a one-tailed rather than a two-tailed test critically important?
one- and two-tailed tests have diff. critical regions and therefore may lead to diff. conclusions about the null hypothesis
it is acceptable to write this notation when you are computing your statistical tests by hand
p > .05 or p < .05
when using a one-tailed significance test, if the research hypothesis predicts an increase (or positive change), the critical region will be on which side of the distribution?
positive
if the obtained t value is farther from zero than the critical value, you should
reject the null hypothesis
how is the standard error of the mean calculated when the population standard deviation is not known?
researchers use the standard deviation of the sample data to compute an estimate of expected sampling error
as the sample size increases, the critical region for a t test
stays the same size (equal to 5% of the distribution) but its location changes
what is the research hypothesis for a two-tailed test?
that the sample and population means will differ, but does not indicate which will be higher than the other
why will the critical values for a one-tailed t test with alpha = .05 change based on the sample size?
the distribution of t values is not always normal in shape
a researcher wants to assess people's knowledge of a topic by using a 10-question true/false test. which value could be of theoretical interest to this researcher and, therefore, function as a null hypothesis?
the researcher might compare the mean number of correct answers to 5, the average number of correct answers people would get if they were simply guessing on every question of the test
what is the null hypothesis for a two-tailed test?
the sample and population means will be the same
when computing an effect size for a single-sample t test, the denominator is
the sample standard deviation
one of the differences between a z for a sample mean test and a single-sample t test is that
the single-sample t test uses the sample standard deviation to compute an estimate of the typical amount of sampling error
the only computational difference between the z for a sample mean formula and the single-sample t formula is the way
typical sampling error is computed
when should the single-sample t test be used?
when the population standard deviation is not known
when should you conduct a one-tailed test?
when the research hypothesis predicts scores will either increase or decrease
