Chapter 2 - Section 3 Statistical Methods in Psychology, and 4 Flashcards
What are descriptive statistics?
They include all numerical methods to summarize sets of data.
There are a number of relatively simple statistics that are commonly used to describe a set of data. These include the mean, median, and a measure of variability. (p. 41)
What do inferential statistics do?
They help us assess the likelihood that relationships observed are real and repeatable or due merely to chance. (They help researchers decide how confident they can be in judging that the results observed are not due to chance.) (p. 41)
What is a mean?
The mean is simply the arithmetic average, determined by adding the scores and dividing the sum by the number of scores. (p. 41)
What is a median?
The median is the center score, determined by ranking the scores from highest to lowest and finding the score that has the same number of scores above it as below it, that is, the score representing the 50th percentile. (p. 41)
What is variability?
Variability refers to the degree to which the numbers in the set differ from one another and from their mean. (p. 42)
What is the standard deviation?
A common measure of variability. (It is calculated by a formula described in the Statistical Appendix.) The further most individual scores are from the mean, the greater is the standard deviation.
What is a correlation coefficient?
Correlational studies examine two or more variables to determine whether or not a nonrandom relationship exists between them.
When both variables are measured numerically, the strength and direction of the relationship can be assessed by a statistic called the correlation coefficient.
The number ranges from -1.00 to 1.00.
To the degree that a correlation is strong (close to +1.00 or -1.00), you can predict the value of one variable by knowing the other.
Which question do inferential statistics answer and how?
What are inferential statistical methods?
How confident can a researcher be in inferring a general conclusion from the study’s data? Laws of probability are used.
Inferential statistical methods, applied to either an experiment or a correlational study, are procedures for calculating the probability that the observed results could derive from chance alone.
(p. 43)
What is a p (for probability) value, or the level of significance?
When two means are being compared, p is the probability that a difference as great as or greater than that observed would occur by chance, if in the larger population, there were no difference between the two means. (“Larger population” here means the entire set of scores that would be obtained if the experiment were repeated an infinite number of times with all possible subjects.)
In other words, in the case of comparing two means in an experiment, p is the probability that a difference as large as or larger than that observed would occur if the independent variable had no real effect on the scores.
In the case of a correlational study, p is the probability that a correlation coefficient as large as or larger than that observed (in absolute value) would occur by chance if, in the larger population, the two variables were truly uncorrelated. (p. 44)
When are results usually labeled as statistically significant?
If the value of p is less than .05 (5 percent).
To say that results are statistically significant is to say that the probability is acceptably small (generally less than 5 percent) that they could be caused by chance alone. (p. 44)
How is statistical significance affected by the size of the observed effect?
Other things being equal, a large effect is more likely to be significant than a small one.
How is statistical significance affected by the number of individual subjects or observations in the study?
Other things being equal, results are more likely to be significant the more subjects or observations included in a research study.
How is statistical significance affected by the variability of the data within each group?
This element applies to cases in which group means are compared to one another and an index of variability, such as the standard deviation, can be calculated for each group.
Variability can be thought of as an index of the degree to which uncontrolled, chance factors influence the scores in a set of data. (For example, in the experiment assessing treatments for depression, greater variability in the depression scores within each treatment group would indicate greater randomness attributable to chance.)
Other things being equal, the less the variability within each group, the more likely the results are to be significant. If all of the scores within each group are close to the group mean, then even a small difference between the means of different groups may be significant.
