Appendix B: Statistics in Psychology Flashcards
Descriptive Statistics
descriptive statistics - statistics used to describe and summarize data
data can be interpreted using:
- frequence distributions
- measures of central tendency
- measures of variability
- frequency distributions - again
- measures of association
Frequency Distributions (ungrouped/grouped distributions, histograms, frequence polygons)
2 major types of frequency distributions:
1) Ungrouped frequency distributions - a count of the number of times each specific data point or score appears in a data set.
2) Grouped frequency distributions - a count of the number of time specific data points fall into a range of values in a data set.
- frequency distributions can be presented either in tabular format or in some type of graphic form such as a histogram or a frequency polygon.
Histograms - a bar chart showing a number of times specific data points fall into a range of values in a data set.
Frequency polygons - a line graph depicting a grouped frequency distributoin, which is created by connecting the midpoints of each class of data.
Measures of Central Tendency (mean, median, mode)
measures of central tendency - numbers used to summarize data sets.
mean - the average value in a data set; the sum of all numbers in the set divided by the total number of items in the set.
median - the data set value that represents the midpoint of an ordered set of numbers.
mode - the most frequent or most common value in a data set.
- if a distribution has comparatively few small or high scores, the mean mat NOT be the best measure of central tendency since it is only the measure of central tendency that is influenced by these types of extreme scores. In such cases, the median or mode may be a better, more representative measure of central tendency.
Measures of Variability (range, variance, standard deviation)
measures of variability - indicators that tell how different the values are within a data set.
range - the difference between the smallest and the largest value in a data set.
variance - a calculated indicator of the degree to which values in a data set differ from the mean value of that data set; the average of squared deviations about the mean.
standard deviation - a deviation value that is the square root of the variance; it is a statistical index of how much scores vary within a group.
Frequency Distributions - Again (normal distribution, positively skewed distribution, negatively skewed distribution)
normal distribution or bell curve - a symmetrical, bell-shaoed distribution in which most scores are in the middle with smaller groups of equal size at either end.
positively skewed distribution - a distribution where most values occur at the lower end of the scale. Distribution skewed to the right. The average (mean) for the distribution is considerably larger than the median value. The mode also tends to be less than the median.
negatively skewed distribution - a distribution where most values occur at the upper end of the scale. distibution skewed to the left. The mean is less than the median, which is also less than the mode.
Measures of Association (scatterplot, person product-moment correlation, positive/direct relationship, negative/inverse relationship, coefficient of determination)
measures of association - descrpitive statistics that quantify and summarize the degree of relationship or association between variables.
scatterplot - it is possible to represent the relationship between the two variables using a scatterplot. a graph or plot of the values of one variable or measure associated with the values on another variable or measure.
pearson product-moment correlation - a statistic indicating the degree of association or relationship between two variables or measures, ranging from -1.00 to +1.00. The most commonly used measure of association between 2 variables.
positive or diret relationship - a relationship where as the value of one variable increases, so do values in another associated variable.
negative or inverse relationship - a relationship where as the value of one variable increases, values in another associated variable decreases.
coefficient of determination - the degree to which values on one variable can be predicted by knowing the values of the other variable.
Inferential Statistics
inferential statistis - statistics used to draw conclusion about research data
data can be interpreted using:
- populations and samples
- hypothesis testing
- effect size
Populations and Samples (random sample)
sample - a group or set of people or items drawn from a larger population.
population - the entire group od individuals about whom we hope to learn (e.g., the Canadian population consists of all Canadians).
random sample - a group or set made by randomly.
Hypothesis Testing - (null hypothesis, alternative hypothesis, sampling distribution, significan or rejection level)
hypothesis testing - testing a statement or claim about a population using a sample and, in its simplest form, looking at experimental and control groups differences.
null hypothesis - as assertion in the underlying population from which the sample was obtained, there is no difference between the average performance of individuals in one group compared to another.
alternative hypothesis - an assertion that in the underlying population from which the sample was obtained, there is a difference between the average performance of individuals in one group compaired to another.
sampling distribution - the theoretical distribution of a sample statistic; for example, the difference between two sample means taken from a populaion.
significance level or rejection level - the level of risk researchers would be willing to take in terms of making an incorrect conclusion.
Effect size
a standardized measure that reflects the degree of relationship or size of the difference between two or more variables.
