Inferential Statistics

Question 1

While descriptive statistics are used to ____ ____, inferential statistics are used to make ____ about a ____ based on ____ ____ from a ____ drawn from that ____ and to do so with a predefined degree of confidence. In this section, the concept of statistical inference is explained. In Section IV, specific inferential statistical tests are described.

Answer 1

Summarize Data; Inferences; Population; Data Collected; Sample; Population

Question 2

The techniques of statistical inference allow an investigator to make ____ about the ____ between ____ in a ____ based on the ____ ____ in a ____.

Answer 2

Inferences; Relationship; Variables; Population; Relationship Observed; Sample

Question 3

The psychologist in Study #1 will want to determine if there is a relationship between training in the self-control procedure and scores on an academic achievement test for all children who have received a diagnosis of ADHD. Since the psychologist won’t have access to the entire population of children with this disorder, he will evaluate the effects of the self-control procedure on a sample of children drawn from the population. The psychologist will then use an ____ ____ ____ to analyze the data he collects from the sample, and the results of the test will enable him to make an ____ about the effects of the procedure on the achievement test scores for the population of children with ADHD. Inferential statistical tests accomplish this task through the use of a ____ ____.

Answer 3

Inferential Statistical Test; Inference; Sampling Distribution

Question 4

____ ____ and ____ ____: To understand inferential statistics, it’s necessary to first distinguish between ____ ____ and ____ ____. As noted above when conducting a research study, an investigator does not have access to the ____ ____ of ____ but, instead, ____ ____ ____ based on ____ ____ ____. In other words, an investigator uses a sample statistic to estimate a ____ ____.

Answer 4

Population Parameters and Samples Statistics; Sample Values and Population Values; Entire Population of Interest; Estimates Population Values; Obtained Sample Values; Population Parameter

Question 5

Sample statistics and population parameters are designated with different symbols.

Answer 5

Question 6

____ of ____ ____: Due to the effects of random (chance) factors, it’s unlikely that any sample will perfectly represent the ____ from which it was ____. As a result, an estimate of a population parameter from a sample statistic is always subject to some ____, In other words, because of the effects of ____ ____, ____ ____ deviate from population parameters and from statistics obtained from other samples drawn from the ____ ____.

Answer 6

Characteristics of Sampling Distribution; Population; Drawn; Inaccuracy; Sampling Error; Sample Statistics; Same Population

Question 7

The relationship between sample statistics and a population parameter can be described in terms of a ____ ____, which is a frequency distribution of the means or other sample values of a very large number of equal-sized samples that have been randomly selected from the same population. Keep in mind that a sampling distribution is not a distribution of individual scores but a ____ of ____ ____. A sampling distribution is important in inferential statistics because it allows a researcher to determine the ____ that a sample having a ____ ____ or other value could have been ____ from a ____ with a ____ ____.

Answer 7

Sampling Distribution; Distribution of Sample Statistics; Probability; Particular Mean; Drawn; Population; Known Parameter

Question 8

To better understand what a sampling distribution is, assume that the psychologist in Study #1 defines his population as “all children in the 6th grade who have received a diagnosis of ADHD,” and, for that population, an academic achievement test has a mean of 50 and a standard deviation of 10. The psychologist repeatedly selects random samples of 25 children from this population; and, for each sample, he administers the achievement test and calculates the mean score. The psychologist has collected a set of sample means and finds that, while some of the sample means are equal to the population mean of 50, because of the effects of ____ ____, some means are larger than the population mean and some are smaller. The psychologist finds that his distribution of sample means, or ____ ____ of the ____, resembles the distribution depicted in Figure 10. As shown in that figure, the ____ ____ of the ____ is normally shaped and its mean is equal to the population mean of 50.

Answer 8

Sampling Error; Sampling Distribution of the Mean; Sampling Distribution of the Mean

Question 9

Researchers do not actually construct a sampling distribution of the mean by obtaining a large number of samples and calculating each sample’s mean. Instead, they depend on ____ ____ to tell them what the sampling distribution would look like. The sampling distribution defined by probability theory is called a ____ ____ ____ and is based on the assumption that an ____ ____ of ____-____ ____ have been ____ ____ from the ____ ____.

Answer 9

Probability Theory; Theoretical Sampling Distribution; Infinite Number of Equal-Sized Samples; Randomly Drawn; Same Population

Question 10

The characteristics of a sampling distribution of the mean are specified by the ____ ____ ____.

Answer 10

Central Limit Theorem

Question 11

Regardless of the shape of the distribution of individual scores in the population, as the ____ ____ ____, the sampling distribution of the mean approaches a ____ ____.

Answer 11

Sample Size Increases; Normal Distribution

Question 12

The mean of the sampling distribution of the mean is ____ to the ____ ____.

Answer 12

Equal to the Population Mean

Question 13

The standard deviation of the sampling distribution of the mean is ____ to the ____ ____ ____ ____ by the ____ ____ of the ____ ____.

Answer 13

Equal to the Population Standard Deviation Divided by the Square Root of the Sample Size

Question 14

The standard deviation of a sampling distribution of the mean is known as the ____ ____ of the ____ It provides an ____ of the extent to which the ____ of any ____ ____ ____ ____ from a ____ can be expected to ____ from the ____ ____ as the result of ____ ____. In other words, like other standard deviations, it is a measure of ____, but it is a measure of variability that is due to the effects of ____ ____.

Answer 14

Standard Error of the Mean; Estimate; Mean; One Sample Randomly Drawn; Population; Vary; Population Mean; Sampling Error; Variability; Sampling Error

Question 15

The standard error of the mean formula indicates that the size of the standard error of the mean is affected by the ____ ____ ____ and the ____ ____ (_): The ____ the population standard deviation and the ____ the sample size, the ____ the standard error and vice versa.

Answer 15

Population Standard Deviation; Sample Size (N); Larger; Smaller; Larger

Question 16

For Study # 1, the ____ ____ ____ predicts that the sampling distribution of the mean is normally shaped, its mean is equal to 50, and its standard deviation (the standard error of the mean) is equal to 2.

Answer 16

Central Limit Theorem

Question 17

Note that, if the sample size had been 9 instead of 25, the standard error would increase to 3.33 (10 divided by the square root of 9 = 10/3 = 3.33). In other words, the ____ the ____ ____, the ____ the standard error of the mean. One implication of this is that the smaller the size of the sample, the greater the ____ for ____ when using a ____ ____ to ____ a ____ ____. Another implication is that, for any given population, there is a “____” of ____ ____, with a different distribution for each ____ ____.

Answer 17

Smaller; Sample Size; Larger; Probability for Error; Sample Statistic to Estimate a Population Parameter; “Family” of Sampling Distributions; Sample Size

Question 18

Although this discussion of sampling distributions has focused on the sampling distribution of the mean, a sampling distribution can be derived for any ____ ____ — i.e., a ____ ____ can be obtained for standard deviations, proportions, correlation coefficients, the difference between means, and so on. In each case, the basic characteristics of the sampling distribution are similar to those of the ____ ____ of the ____.

Answer 18

Sample Statistic; Sampling Distribution; Sampling Distribution of the Mean

Question 19

The sampling distribution is the ____ of ____ ____. It is the sampling distribution that enables a researcher to make ____ about the ____ ____ ____ in the ____ based on obtained ____ ____.

Answer 19

Foundation of Inferential Statistics; Inferences; Relationship Between Variables in the Population; Sample Data

Question 20

An inferential statistical test enables an investigator to determine the probability of obtaining a sample with a particular value by comparing the obtained sample value to an appropriate (1) ____ distribution. When the sample value of interest is a mean, the comparison distribution is the sampling distribution of the (2) ____, which is the distribution of means that would be obtained if a large number of equal-sized random samples were drawn from the same (3) ____ and the mean of each sample was calculated. While many sample means would equal the population mean, because of the effects of (4) ____, some means would be lower than the population mean and some would be higher.

Answer 20

(1) sampling; (2) mean; (3) population; (4) sampling error

Question 21

In inferential statistics, a sampling distribution is not actually constructed by obtaining a large number of samples. Instead, a theoretical sampling distribution is derived from probability theory. According to the (5) ____. Theorem, the sampling distribution o the mean is (6) ____ shaped; its mean equals the (7) ____ and its standard deviation, the (8) ____ of the mean, is equal to the population (9) ____ divided by the square root of the (10) ____.

Answer 21

(5) Central Limit; (6) normally; (7) population mean; (8) standard error; (9) standard deviation; (10) sample size (N)

Question 22

An investigator usually conducts a research study to test the hypothesis that an independent variable has an ____ on a ____ ____. In Study #1, the research hypothesis might be, “If children with ADHD are taught the self-control procedure, then their academic achievement test scores will increase.” This hypothesis could be tested in several ways. One way would be to use an ____ ____ ____ to ____ the ____ achievement test score for a group of 6th grade children with ADHD who have received training in the procedure to the ____ ____ for 6th grade children with ADHD.

Answer 22

Effect on a Dependent Variable; Inferential Statistical Test to Compare the Mean; Population Mean

Question 23

Alternatively, an inferential statistical test could be used to ____ the ____ ____ the ____ obtained by two groups of children who have and have not received the training. In either case, the statistical test would ____ the ____ ____ ____ to the ____ ____ ____, and the results of the test would indicate whether an observed effect of the self-control procedure was due to ____ ____ or to the ____ of the ____.

Answer 23

Compare the Difference Between the Means; Compare the Obtained Sample Value; Appropriate Sampling Distribution; Sampling Error; Effects of the Procedure

Question 24

Testing a research hypothesis about the effects of an IV on a DV involves the following steps: (1) Translate the verbal research hypothesis about the relationship between independent and dependent variables into ____ ____ ____ ____ — the ____ ____ and the ____ ____. (2) ____ the study and ____ the ____ ____ with an ____ ____ ____. (3) Decide, on the basis of the results of the statistical test, whether to ____ or ____ the ____ ____.

Answer 24

Two Competing Statistical Hypotheses; Null Hypothesis; Alternative Hypothesis; Conduct; Analyze the Obtained Data; Inferential Statistical Test; Retain or Reject the Statistical Hypothesis

Question 25

____ the ____ ____: An investigator tests a verbal research hypothesis by simultaneously testing ____ ____ ____ ____. The first of these, the ____ ____, is stated in a way that implies that the independent variable does not have an effect on the dependent variable.

Answer 25

Define the Statistical Hypothesis; Two Competing Statistical Hypothesis; Null Hypothesis

Question 26

The second statistical hypothesis, the ____ ____, states the opposite of the null hypothesis. It is expressed in a way that implies that the independent variable does have an effect. Usually it is the alternative hypothesis that most closely resembles the ____ ____ ____. However, it is always the null hypothesis that is first ____ or ____. The decision to reject or retain the alternative hypothesis is ____ and is always the ____ of the decision for the ____ ____ — i.e., if the null hypothesis is ____, the alternative hypothesis is ____ and vice versa.

Answer 26

Alternative Hypothesis; Verbal Research Hypothesis; Rejected or Retained; Secondary; Opposite; Null Hypothesis; Retained; Rejected

Question 27

The null hypothesis is always expressed in terms of a ____ ____ ____ that implies ____ ____ between ____ and ____ ____. In the above example, the null hypothesis is that the mean test score of the population of children who have received training in the self-control procedure is the same as the mean score of the population of children who have not received the training. In other words, the null hypothesis predicts that the self-control procedure will have no effect on achievement test scores, and, consequently, that children who have received training will be indistinguishable from children who have not.

Answer 27

Specific Population Parameter; No Relationship; Independent and Dependent Variables

Question 28

Prom the perspective of the null hypothesis, any ____ ____ between the ____ ____ and the ____ ____ will be due to ____ ____ rather than the self-control procedure.

Answer 28

Observed Difference; Sample Mean; Population Mean; Sampling Error

Question 29

The alternative hypothesis predicts that there is a ____ ____ ____ and ____ ____. Prior to a research study, it is not possible to assign an ____ ____ to the alternative hypothesis since that value is ____ and will, ideally, be revealed by the ____ ____. Consequently, the alternative hypothesis just states the ____ of the ____ ____. Like the null hypothesis, the alternative hypothesis is always expressed in terms of a ____ ____.

Answer 29

Relationship between Independent and Dependent Variables; Exact Value; Unknown; Study’s Outcome; Opposite; Null Hypothesis; Population Parameter

Question 30

Note that there are two possible ____ ____. A ____ (“____-____”) ____ ____ merely states that the null hypothesis is false. It does not predict whether the population parameter estimated by the obtained sample statistic will be ____ ____ or ____ ____ the parameter predicted by the ____ ____. In the above example, the alternative hypothesis is a nondirectional one. It states that the population mean is not equal to 50.

Answer 30

Alternative Hypothesis; Nondirectional (“Two-Tailed”) Alternative Hypothesis; Greater Than or Less Than; Null Hypothesis

Question 31

A ____ (“____-____”) ____ ____ not only states that the null hypothesis is false, but also predicts whether the population parameter estimated by the Obtained sample statistic will be greater than or less than the parameter specified in the null hypothesis. A directional hypothesis for Study #1 would predict that the mean for children With ADHD who have been trained in the procedure will be ____ than the population mean of 50.

Answer 31

Directional (“One-Tailed”) Alternative Hypothesis; Greater

Question 32

Although it might seem logical to use a ____ ____ ____ in most research Studies, the convention is to use a ____ ____ unless there are ____ or ____ grounds for choosing a ____ ____. The psychologist in Study #1 would Probably use a nondirectional alternative hypothesis if the self-control procedure had never been evaluated as a method for increasing academic achievement test scores of 6th grade children with ADHD, but a directional hypothesis if the procedure had already been found effective for 4th and 5th grade children with ADHD.

Answer 32

Directional Alternative Hypothesis; Nondirectional Hypothesis; Experimental or Theoretical; Directional One

Question 33

Hypothesis testing involves first translating the verbal research hypothesis into two competing statistical hypotheses: The (1) ____ hypothesis is stated in a way that implies that the independent variable does not have an effect on the dependent variable and that any observed effect is the result of (2) ____. In contrast, the (3) ____ hypothesis states the opposite of the null hypothesis and is expressed in a way that implies that the independent variable does (4) ____ the dependent variable. The alternative hypothesis can take one of two forms.

Answer 33

(1) null; (2) sampling error; (3) alternative; (4) have an effect on

Question 34

A (5) ____ alternative hypothesis predicts whether the population value will be greater or (6) ____ the population value specified in the null hypothesis; while a (7) ____ alternative hypothesis states only that the population value is not equal to the value stated in the null hypothesis.

Answer 34

(5) directional; (6) less than; (7) nondirectional

Question 35

____ the ____ and ____ a ____: After stating the null and alternative hypotheses and collecting the sample data, an investigator analyzes the data using an inferential statistical test such as the _-____ or ____ of ____. The choice of a statistical test is based on several factors including the ____ of ____ of the ____ to be ____. (The selection of a statistical test is described in Section IV.)

Answer 35

Analyze the Data and Make a Decision; T-Test; Analysis of Variance; Scale of Measurement; Data to be Analyzed

Question 36

The inferential statistical test yields a _, an _, or other value that indicates where the obtained sample statistic falls in the appropriate ____ ____. That is, the test indicates whether the statistic is in the ____ ____ or the retention region of the ____ ____: The ____ ____, or “region of unlikely values,” lies in ____ or ____ ____ of the ____ ____ and contains the sample values that are not likely to occur simply as the result of ____ ____. The ____ ____, or “region of likely values,” lies in the ____ ____ of the sampling distribution and consists of the values that are likely to occur because of ____ ____ ____.

Answer 36

T; F; Sampling Distribution; Rejection Region; Retention Region; Sampling Distribution; Rejection Region; One or Both Tails; Sampling Distribution; Sampling Error; Retention Region; Central Portion; Sampling Error Only

Question 37

When the results of the statistical test indicate that the obtained sample statistic is in the rejection region of the sampling distribution, the ____ ____ is ____ and the ____ ____ is ____. The investigator concludes that the sample statistic is ____ ____ to have been ____ by ____ ____ and that the independent variable has had an ____ on the ____ ____. Conversely, if the statistical test indicates that the sample statistic lies in the retention region of the sampling distribution, the ____ ____ is ____ and the ____ ____ is ____. In this case, the investigator concludes that the independent variable has ____ ____ an ____ and that any observed effect is due to ____.

Answer 37

Null Hypothesis is Rejected; Alternative Hypothesis is Retained; Not Likely; Obtained by Chance Alone; Effect; Dependent Variable; Null Hypothesis; Retained; Alternative Hypothesis is Rejected; Not Had an Effect; Error

Question 38

____: The size of the rejection region is defined by ____ (α), which is also known as the ____ of ____. If alpha is .05, then _% of the sampling distribution represents the ____ ____ and the remaining _% ____ the retention region. The ____ ____ always lies in ____ or ____ ____ of the ____ ____; that is, in the portion of the sampling distribution that contains sample values that are least likely to occur as the result of ____ ____ ____. The size of alpha is set by the ____ prior to ____ or ____ the ____. In other words, it is the experimenter who decides what proportion of the sampling distribution will represent the ____ of ____ ____. In psychological research, alpha is usually set at _ or _.

Answer 38

Alpha; Alpha; Level of Significance; 5%; Rejection Region; 95%; Retention Region; One or Both Tails; Sampling Distribution; Sampling Error Only; Experimenter; Collecting or Analyzing the Data; Region of Unlikely Values; .05 or .01

Question 39

When the results of an inferential statistical test indicate that the obtained sample value lies in the rejection region of the sampling distribution, the study’s results are said to be ____ ____. For example, when alpha has been set at .05 and the statistical test indicates that the sample value is in the rejection region, the results of the study are “____ at the _ ____.”

Answer 39

Statistically Significant; Significant at the .05 Level

Question 40

____- ____ ____-____ ____: Some inferential statistical tests can be conducted as either a ____- or ____-____ ____. When a two-tailed test is used, the rejection region is ____ ____ ____ the ____ ____ of the sampling distribution. If alpha is set at .05, 2.5% of the rejection region lies in the positive tail of the distribution and _% lies in the ____ tail. With a one-tailed test. the entire rejection region is placed in only ____ of the ____.

Answer 40

One- Versus Two-Tailed Tests; One- or Two-Tailed Test; Equally Divided Between the Two Tails; 2.5%; Positive; 2.5%; Negative; One; Tails

Question 41

It is the ____ ____ that determines whether a one- or two-tailed test should be conducted. A two-tailed test is used when the alternative hypothesis is ____, while a one-tailed test is used when the alternative hypothesis is ____. If a directional alternative hypothesis predicts that the sample statistic will be greater than the value specified in the null hypothesis, the entire ____ ____ lies in the ____ ____ of the sampling distribution (as in the bottom distribution in Figure 1 1 If a directional alternative hypothesis predicts that the sample statistic will be less than the value specified in the null hypothesis, the ____ ____ is located in the ____ ____.

Answer 41

Alternative Hypothesis; Nondirectional; Directional; Rejection Region; Positive Tail; Rejection Region; Negative Tail

Question 42

The results of an inferential statistical test indicate whether the obtained sample value falls within the region of likely values or unlikely values in the (1) ____ distribution. When the results of the statistical test indicate that the obtained sample value falls in the region of unlikely values, the null hypothesis is (2) ____ and the alternative hypothesis is (3) ____. Conversely, when the results indicate that the sample value falls in the region of likely values, the null hypothesis is (4) ____ and the alternative hypothesis is (5) ____.

Answer 42

(1) sampling; (2) rejected; (3) retained; (4) retained; (5) rejected

Question 43

The size of the (6) ____ region (region of unlikely values) is defined by alpha. A researcher sets alpha before collecting or analyzing the data. In psychological research, alpha is usually set at .01 or (7) ____. When alpha is .01, this means that (8) ____% of the sampling distribution is the region of unlikely values, while the remaining (9) ____% is the region of likely values. The region of unlikely values is always placed in one or both (10) ____ of the sampling distribution so that it contains the sample values that are least likely to occur as the result of sampling error alone.

Answer 43

(6) rejection; (7) 05; (8) 1; (9) 99; (10) tails

Question 44

When the results of a study are “statistically (11) ____, “ this means that the obtained sample value is in the (12) ____ of the sampling distribution and that the investigator has rejected the (13) ____.

Answer 44

(11) significant; (12) rejection region; (13) null hypothesis

Question 45

____ ____ ____: Regardless of whether an experimenter decides to retain or reject the null hypothesis, there are two possible outcomes of his or her decision: The decision can be either ____ or in ____, and an experimenter can never be ____ ____ which type of decision has been made.

Answer 45

Consider Decision Outcomes; Correct or In Error; Entirely Certain

Question 46

Decision Outcomes

Answer 46

Question 47

____ ____: As indicated in Figure 12, there are two decision errors — a ____ _ ____ and a ____ _ ____. A ____ _ ____ occurs when an investigator rejects a true null hypothesis. For instance, if the psychologist in Study #1 concludes that the self-control procedure increases achievement test scores but the apparent improvement in scores is actually a consequence of sampling error, the psychologist has made a ____ _ ____. (Keep in mind that it is unlikely — but not impossible — to obtain a sample value in the rejection region of the sampling distribution as the result of ____ ____.)

Answer 47

Decision Errors; Type I Error; Type II Error; Type I Error; Type I Error; Chance Alone

Question 48

The probability of making a Type I error is equal to ____ (α). As the value of ____ ____, the probability of rejecting a true null hypothesis also increases. For example, increasing the value of alpha from .01 to .05 increases the Probability of making a ____ _ ____ from I chance in 100 to I chance in 20. Because an investigator sets the value of alpha, he or she has ____ over the ____ of making a ____ _ ____.

Answer 48

Alpha; Alpha Increases; Type I Error; Control; Probability; Type I Error

Question 49

The other decision error, a ____ _ ____, occurs when an investigator retains a false null hypothesis. In Study #1, if the psychologist concludes that the self-control procedure does not improve achievement test scores when it actually does, the psychologist has made a ____ _ ____. The probability of making a Type Il error is equal to ____ (ß). Although beta is ____ ____ by an investigator and cannot be ____ ____ for a particular study, the probability of making a Type TI error can be ____ ____: A Type Il error is more likely when alpha is ____. the sample size is ____, and the independent variable is not administered in ____ ____.

Answer 49

Type II Error; Type II Error; Beta; Not Set; Directly Calculated; Indirectly Influenced; Low; Small; Sufficient Intensity

Question 50

There is an ____ ____ between Type I and Type Il errors: As the probability of making a Type error ____, the probability of making a Type Il error ____ and vice versa. Consequently. the selection of a level of significance depends, in part, on the ____ of making these ____ ____.

Answer 50

Inverse Relationship; Increases; Decreases; Seriousness; Two Errors

Question 51

For some research, a Type I error (rejecting a true null hypothesis) is considered ____ ____. In these situations, the experimenter will choose level of significance that ____ the probability of making a Type I error (e.g., .01 rather than .05). In other situations, it is more important to avoid making a ____ _ ____ (retaining a false null hypothesis). When this is the case, a ____ ____ of ____ is preferred (.10 or .05 rather than .01).

Answer 51

More Problematic; Minimizes; Type II Error; Larger Level of Significance

Question 52

____ ____: As shown in Figure 12, there are also two possible correct decisions. An investigator can make a ____ ____ by ____ the null hypothesis when it is ____ or by ____ the null hypothesis when it is false. It is the ____ ____ of correct decision that an investigator ordinarily wants to make. When a statistical test enables an investigator to reject a false null hypothesis, the test is said to have ____ ____. Obviously, researchers always want to ____ ____ whenever they conduct a research study.

Answer 52

Correct Decisions; Correct Decisions; Retaining; True; Rejecting; False; Second Type; Statistical Power; Maximize Power

Question 53

____ ____: A null hypothesis (true or false) is more likely to be rejected when alpha is _ than when it is _. (However, because ____ ____ also increases the probability of making a Type I error, alpha is usually set no higher than _ in psychological research.)

Answer 53

Increase Alpha; .05; .01; Increasing Alpha; .05

Question 54

____ the ____ ____: A correct decision is more likely to be made when the sample size is 50 than when it is 25.

Answer 54

Increase the Sample Size

Question 55

____ the ____ of the __: ____ the ____ of the __ increases the likelihood that its effects on the DV will be detected. The effects of the IV are maximized by administering the IV for a ____ ____ ____ of ____ or in ____ ____.

Answer 55

Increase the Effects of the IV; Maximizing the Effects; IV; Long Enough Period of Time; Sufficient Intensity

Question 56

____ ____: When potential sources of ____ and ____ ____ are ____, it’s easier to detect the effects of the IV. One way to reduce error is to make sure the __ ____ is ____. Another way is to reduce within-group variability by ____ ____ ____ or using a ____-____ ____.

Answer 56

Minimize Error; Random and Systematic Error are Controlled; DV Measure is Reliable; Controlling Extraneous Variables; Within-Subjects Design

Question 57

____ a ____-____ ____ ____ ____: A ____-____ test is more ____ than a two-tailed test as long as it is ____ used.

Answer 57

Use a One-Tailed Test When Appropriate; One-Tailed; Powerful; Appropriately

Question 58

____ a ____ ____: ____ ____ ____, such as the t-test or ANOVA, are more ____ than nonparametric tests.

Answer 58

Use a Parametric Test; Parametric Statistical Test; Powerful

Question 59

Note that is not the same as “confidence.” ____ refers to the ability to reject a false null hypothesis and, as noted above, is affected by the size of ____: Power ____ as alpha ____ and vice versa. Statistical power is something a researcher is concerned about ____ a decision about the null hypothesis is made. In contrast, ____ refers to the certainty a researcher has about the decision he or she has already made about the null hypothesis. An experimenter has more confidence that his or her decision to reject the null hypothesis was correct when alpha is ____ (e.g., .01 rather than .05).

Answer 59

Power; Alpha; Increases; Increases; Before; Confidence; Small

Question 60

When a researcher makes the decision to retain or reject the (1) ____ hypothesis, there is no way to know with certainty if the decision is correct or in error. There are two kinds of decision errors: A Type I error is made when a true null hypothesis is (2) ____. This occurs when a researcher concludes that an independent variable has had an effect on the dependent variable, but the observed effect was actually due to (3) ____. The probability of making a Type I error is equal to (4) ____. For example, when (5) ____ is set at .05 and the researcher has rejected the null hypothesis, there is a (6) ____% chance that a Type I error has been made.

Answer 60

(1) null; (2) rejected; (3) sampling error; (4) alpha (level of significance); (5) alpha; (6) 5

Question 61

A Type Il error is made when a false null hypothesis is (7) ____ This occurs when the researcher decides that an independent variable has had no effect on the dependent variable when it actually did. A Type Il error might occur when the (8) ____ variable was not administered in sufficient intensity or for a long enough period of time. when the sample size was too (9) ____, or when alpha is too (10) ____.

Answer 61

(7) retained; (8) independent; (9) small; (10) small

Question 62

A researcher can, of course, make a correct decision. One kind of correct decision Is to (11) ____ a true null hypothesis. In this situation, the researcher correctly concludes that any observed effect of an IV is actually due to (12) ____. The other correct decision is to (13) ____ a false null hypothesis.

Answer 62

(11) retain; (12) sampling error; (13) reject

Question 63

In this situation, the researcher correctly decides that the (14) ____ had an effect on the DV. When a statistical test enables a researcher to make this kind of correct decision, the test is said to have statistical power. Power is increased as alpha (15) ____, as the sample size (16) ____ and as the magnitude of the effect of the independent variable increases, Power is also maximized when a one-tailed test is used (when appropriate) and when the data are analyzed using a t-test, ANOVA, or other (17) ____ statistical test.

Answer 63

(14) IV; (15) increases; (16) increases; (17) parametric