Now that you have familiarity with the new key terms of this chapter, it is time to begin using the terms in the context of the chapter material. See if you can fill-in-the-blanks in the following discussions. To get the correct answer, click on the blank.
Statistical procedures are a powerful tool for __________ and understanding large sets of data. For statistical analyses to be most helpful, it is important to plan them as part of the overall __________-__________.
We make the distinction between two categories of statistical procedures. __________ statistics simplify and help us to organize the data. __________ statistics go beyond description of the data and help us to interpret the meaning of the data.
Statistical procedures depend on __________ or differences in responses among participants. We make the distinction between two types of variability. Variability __________ groups focuses on the difference in average performance between two or more groups. Variability __________ groups focuses on the differences among the scores within each group. The variability within groups is usually a function of __________-__________ --the normal variation among individuals on whatever variable is being measured. In psychology, the differences created by manipulating variables are usually __________ than the differences that already exist between people. Our task in psychological research is to show that any observed differences on the dependent measure are due to the __________-__________ and not to already existing __________-__________. __________ statistics are used to help us determine which of these factors are responsible for the observed differences in the dependent measure.
Your textbook discusses three groups of descriptive statistics. Frequency __________ provide the first level of organization of the data from a study. Here the number of people with each possible score are counted and organized for the researcher. __________- __________ present the material from frequency distributions in a pictorial format. This pictorial approach often allows the researcher to literally see the data more clearly and understand it more fully. Finally, __________-__________ simplify the data by reducing them to just one or two numbers, such as an index indicating an average and another index indicating the amount of variability.
For most nominal and ordinal data, statistical simplification involves computing the __________ of participants in each category. At times, we may want to count the number of people who fall into categories, where the categories are defined by the simultaneous classification on two variables (such as sex and political affiliation). This process is known as __________-__________, and it can often help us to see relationships between variables that are measured on a nominal scale. With score data, we usually organize the frequency counts into a __________-__________ by ordering the scores from lowest to highest and listing the number of people with each possible score. If there is a large number of possible scores, we often set up intervals of more than one score and list the number of people whose score is within each interval. This is known as a __________ frequency distribution. This type of frequency distribution must be used whenever we have a __________ variable; because there are theoretically an infinite number of scores with a continuous variable, we are required to define score intervals in order to construct a distribution.
Two commonly used graphical procedures for representing frequency distributions are the __________ (or bar graph) and the __________-__________. The __________-__________ is one of the most commonly used graphical representation techniques. It can be used to illustrate either frequency or grouped frequency distributions. It is a two-dimensional graph in which the horizontal axis (known as the X axis or the __________) represents the range of scores, and the vertical axis (known as the Y axis or the __________) represents the frequency of scores. With small sample sizes, the frequency polygon often appears jagged. As the sample size increases, the frequency polygon often begins to resemble a smooth curve. We make the distinction between different shapes of the curve of the frequency polygon. If the right side of the curve is the mirror image of the left side of the curve, we say the curve is __________. A special symmetric curve that has a distinct bell shape and is defined by a mathematical equation is the __________ curve. Not all curves are symmetric. If scores tend to bunch up near one end of the distribution, we say the distribution is __________.The distribution is __________-__________ if the scores tend to bunch up near the top of the distribution and is __________-__________ if the scores tend to bunch at the bottom of the distribution.
__________-__________ serve two purposes: to describe data in just one or two numbers, and to provide a basis for later analyses. Your textbook describes three types of summary statistics: measures of __________-__________ ; measures of __________ ; and measures of __________. Measures of __________-__________ describe the typical or average score. Measures of __________ describe how variable the scores are. Measures of __________ describe the degree of association or relationship one variable has with another.
Three measures of central tendency are typically used. The __________ is the most commonly used measure of central tendency. It is the arithmetic average of the scores. The __________ is the middle score or the score at the fiftieth percentile. The __________ is the most frequent score.
Your book describes four measures of variability. The __________ is the distance from the lowest to the highest score. The __________-__________ is the average distance each score is from the mean. The __________ is essentially a measure of the average squared deviation of scores from the mean. The __________-__________ is equal to the square root of the variance. The __________- __________ and the __________ are the measures of variability that are used most frequently in the computation of inferential statistics.
Your book describes three commonly used measures of relationship. The __________-__________- __________ correlation is a measure of relationship that should be used when quantifying the relationship between two variables, both of which are measured on either an interval or a ratio scale. The __________ __________- __________ correlation quantifies the relationship between two variables when at least one of the variables is measured on an ordinal scale and the other is measured on at least an ordinal scale. Both of the correlation coefficients index the degree of __________ relationship. If the relationship is not linear, these correlations are inappropriate to use. The best way to see the shape of the relationship between variables is to graph the data in a __________-__________. Phi should be used to measure the relationship between nominal measures.
Inferential statistics are used to draw inferences about a larger group, the __________, on the basis of the performance of a subset of the larger group, the __________. With inferential statistics, we actually test the null hypothesis. If we were testing two groups of participants and want to compare the mean scores of the groups, the __________-__________ would state that the population means from the groups were equal.
We never actually test the null hypothesis in an absolute sense. Instead, we test it probabilistically. We usually set an arbitrary probability level (that we call __________) to serve as a decision criterion. For example, if we were interested in evaluating population means, the inferential statistic would evaluate the size of the observed mean differences. If the __________ means are so different that it is unlikely that the samples could have come from __________ with equal means, we reject the __________-__________ that the population means are equal. The criterion for making this decision to reject is the __________ level. Since the decision is probabilistic, there is always some chance that we will make the wrong decision. There are two types of decision errors. A __________- __________ error occurs when we decide to reject the null hypothesis, but the null hypothesis is actually true. The probability of making this error is equal to the __________ level. A __________-__________ error occurs when we decide not to reject the null hypothesis when the null hypothesis is actually false.
There are several inferential statistical procedures for evaluating mean differences in two or more groups. An __________- __________-__________ (ANOVA) can be used to evaluate mean differences when we have two or more groups. The advantage of an ANOVA is that the technique can be used in many different situations. The power of a statistical test refers to its __________. Power is the ability to __________ Type II errors. The traditional way to increase power is to increase __________ __________. Computing the effect size gives us an estimate of the size of the __________ between group means expressed in standard deviation units.