Edited Invalid date
Chapter 11: Statistics
Descriptive statistics describe a set of data.
If you were interested in learning how many students have dogs, cats, zebras, and so on, you could use a Frequency Distribution to tell you how many students have them.
It is helpful to graph your findings.
Frequency distributions can be turned into bar graphs known as histograms.
Pets are graphed along the x - axis, while the y - axis always represents Frequency.
Measures of central tendency are a group of statistical measures.
The center of a distribution is marked by measures of central tendency.
The mean, median, and mode are measures of central tendency.
The mean is the average of the scores in the distribution.
To calculate the mean, you add up all the scores in the distribution and divide by the number of scores.
The distribution has a median score.
If there is an odd number of scores, you can find the middle one by writing the scores down in descending order.
The average of the middle two scores is the median of the distribution.
The mode is the score that shows up the most.
A distribution may have more than one mode.
A distribution is bimodal if two scores show up the same amount of times.
The mean is the most widely used measure of central tendency, but it can be distorted by extreme scores or outliers.
19 of your friends drive cars worth $12,000 but your other friend has a $120,000 car.
The value of your car is $17,400.
Since that value is in excess of everyone's car, it is not the best measure of central tendency.
The median is a better measure of central tendency when a distribution includes outliers.
The distribution is skewed if it is symmetrical.
Outliers skew distributions.
The distribution is said to be positively skewed when it includes a group of scores that are very high.
The distribution is negatively skewed when the skew is caused by a particularly low score.
A distribution with more low scores than high scores is called a skew.
A negatively skewed distribution has more high scores than low scores.
The mean is higher than the median because the outliers have a more dramatic effect on the mean than on the median.
Descriptive statistical measures include measures of variability.
You may be familiar with the range, variance, and standard deviation.
The diversity of the distribution is depicted by measures of variability.
The range is the distance between the highest and lowest scores.
The square root of the standard deviation is related to the variance.
The average distance of any score in the distribution from the mean is related to both measures.
Being able to compare scores is important.
You can convert scores from different distributions into measures called Z scores.
The distance from the mean to the Z scores is measured in units of standard deviation.
Scores below the mean have negative Z scores, while scores above the mean have positive Z scores.
If Clarence scored a 72 on a test with a mean of 80 and a standard deviation of 8, his Z score would be -1.
Maria's Z score would be +0.5 if she scored an 84 on that test.
You will often see references to the normal curve in psychology.
The area under the curve lying between the two scores has been set.
Almost 99 percent of scores fall within three standard deviations of the mean in a normal distribution, as well as 95 percent of scores falling within two standard deviations of the mean.
Knowing that the normal curve is symmetrical and knowing the three numbers will allow you to calculate the percentage of scores falling between any given scores.
The percentiles indicate the distance of a score from 0 to the mean.
A person who scores in the 90th percentile on a test is more likely to score better than other people.
Only 38 percent of the people who took the test scored better than someone who scored at the 38th percentile.
The normal curve has a relationship between percentiles and Z scores.
Someone who scores at the 50th percentile has a Z score of 0, and someone who scores at the 98th percentile has an approximate Z score of +2.
A correlation is a measure of the relationship between two variables.
Positive or negative correlations can be found.
The presence of one thing predicts the presence of the other.
A negative correlation means that the presence of one thing predicts the absence of the other.
There is no correlation when there is no relationship between two things.
It is possible that a correlation exists between studying and earning good grades.
It is possible that a negative correlation could occur between cutting classes and earning good grades.
It is likely that there is no correlation between the number of stuffed animals you own and your grades.
Correlations can be strong or weak.
The correlation coefficients can be used to determine the strength of a correlation.
Correlation coefficients range from a negative correlation to a positive correlation.
Both -1, and -1, show strong correlations.
No correlation means that knowing something about one variable doesn't tell you anything about the other.
A correlation can be graphed using a scatter plot.
The number of hours a group of people study per week can be plotted on the x - axis while their grade point average can be plotted on the y - axis.
A scatter plot is a series of points.
The closer the points fall on a straight line, the stronger the correlation.
The line of best fit is the line drawn through the scatter plot that is closest to the line.
Positive correlation can be seen when the line slopes upward from left to right.
A negative correlation is shown by a downward slope.
Students believe correlations are related to positive numbers.
It's as strong a correlation as +.
A correlation, no matter how strong, does not indicate a relationship.
The plot shows the correlation between hours studied.
The purpose of inferential statistics is to determine if the findings can be applied to the larger population from which the sample was selected.
One of the primary goals in selecting a sample is to represent the population from which it was picked.
One cannot infer anything from a sample that does not represent the larger population.
It is impossible to guarantee that a sample is representative of the population.
Sampling error is the extent to which the sample is different from the population.
Say that you tested the effects of sugar consumption on short-term memory.
You assigned your subjects to either a control group that was given a sugarfree lollipop or to the experimental group that was given a seemingly identical lollipop.
The participants were tested on their recall of 15 one-syllable nouns.
The 0.1 difference in the example is too small to allow us to make a conclusion.
You would be reluctant to draw any conclusions given the huge difference in the number of words recalled.
You would be correct to be skeptical.
Sampling error and chance are likely to be the reasons for the differences between the groups.
Inferential statistics are used to help psychologists decide when to apply their findings to the larger population.
There are many different inferential statistical tests.
They take into account the size of the sample and the magnitude of the difference found.
The most important thing for you to know is that the tests yield a p value.
The probability of the difference being due to chance is given by the p value.
The cutoff for statistically significant results is a p value of.05.
5 percent is the chance that the results occurred by chance.
We can never be certain that the results did not happen due to chance.
Scientists try to duplicate their results in order to gather more evidence that their initial findings were not due to chance.
The correlation coefficients can be computed with a p value.
The bigger the sample, the more likely the relationship will be significant.
Research design involves ethical considerations.
The ethical guidelines established by the APA for human and animal research should be understood and applied to specific research designs.
Any type of academic research must be submitted to the ethics board or IRB at the institution.
The IRB reviews research proposals for ethical violations.
Researchers can either go ahead with the research or have to revise their procedures.
Groups advocating the ethical treatment of animals are more focused on how animals are treated in laboratory experiments.
The guidelines for using animals in psychological research were developed by the APA.
They need a clear scientific purpose.
The research needs to answer an important scientific question.
The best-suited animals to answer the question must be chosen.
They need to care for and house animals in a humane way.
They need to acquire animal subjects legally.
The animals must be purchased from accredited companies.
Wild animals need to be trapped in a humane way.
They need to design procedures that use the least amount of suffering.
Participation should be voluntary.
Participants must know that they are involved in research and give their consent.
If the participants are deceived in any way about the nature of the study, the deception must not be so extreme as to invalidate the informed consent.
To give informed consent meaning, the research the participants thought they were consenting to must be similar to the actual study.
The trauma deception may cause researchers to be very careful.
Privacy must be protected.
The researcher cannot reveal their identities or actions.
When the researchers don't collect any data that will allow them to match a person's responses with his or her name, participants have anonymity.
In some cases, such as interview studies, a researcher can't promise anonymity, but they can guarantee confidentiality, which means they won't identify the source of the data.
Participants can't be placed at significant mental or physical risk.
It is permissible for participants to experience temporary stress but they should avoid activities that could cause long-term mental or physical harm.
The Review Board has to interpret this clause.
Some boards might not allow a certain level of risk.
In the 1970s, Stanley Milgram's studies in which participants thought they were causing significant harm or death to other participants highlighted this consideration.
After the study, participants should be told the purpose of the study and how to contact the researchers.
It is important to conduct a thorough debriefing when research involves deception.
Five suggested answers or completions are followed by each of the questions or incomplete statements.
Pick the one that is the best.
lab partners assigned to research who is friendlier, girls or boys After talking to their first 10 participants, they found that their ratings for politeness differed a lot.
Professor Ma wants to study the emotional response to date rape.
He advertises for participants in the school newspaper, informs them about the nature of the study, gets their consent, conducts an interview, and debriefs them after the experiment is over.
A mean of 100 and a standard deviation of 15 were the values of the IQ test scored by Lily.
Everyone else fails the test, but Emma scores a perfect 100.
Jose thinks that a new drug he has invented will improve mice's memories.
He gives a placebo to the experimental group.
The mice are learning to run through a maze.
The three classes were assigned to an experimental condition.
A computer creates a random list of high school students.
Approaching any students during lunch.
Vincenzo wants to see if fear makes mice run faster.
He divided the 60 mice into two groups, the control group and the experimental group.
According to a nursery school student, boys have fights with the finger paints more than girls do.
She looked at the finger-painting table for three days at nursery school.
Survey data shows that students who spend more time preparing for the AP test score better on the test.
View flashcards and assignments made for the note
Getting your flashcards
Privacy & Terms