PSYC217 Chapter 12 - Descriptive Statistics Scales of Measurement - Nominal scale -> levels are different categories or groups that have no intrinsic numerical properties. · E.g., two different kinds of therapies for depression would be nominal categories. - Ordinal scale -> rank order the levels from lowest to highest (or least to most) · Intervals between each rank order are not equal. · A list of the top ten restaurants in Halifax would use an ordinal scale. - Interval scale -> distances between each level are equivalent in size. " E.g., difference between 90 and 95 on the scale should be the same as the difference between 115 and 120. · Scores on an intelligence test are an example of an interval scale. " No meaningful zero point that indicates a total "absence" of the construct. - Ratio scales -> equal intervals in addition to a true zero point. · Response time and age are examples of ratio scales. - Difficult to know precisely whether an ordinal or an interval scale is being used. · E.g., when participants rate their health on a 4-point scale (interval scale) -> points are labelled very good, good, fair, and poor · Difficult to claim difference between very good (4) and good (3), is it the same difference between fair (2) and poor (1)? " Common practice to treat variables measured as an interval scale · When ordinal scales are averaged across many instances (e.g., many items in a self- report scale), they take on properties similar to an interval scale. - Variables measured on interval and ratio scales are often referred to as continuous variables > values represent an underlying continuum " Variables using interval and ratio scales can be treated the same way statistically > will group them together and refer to them as continuous variables. Describing Each Variables Graphing Frequency Distributions - Frequency distribution: representation of how often each score was observed, arranged from lowest to highest score. · Indicates number of participants who receive or select each possible score on a variable. · Frequency distributions can be created for variables using any scale of measurement. - Graphical representations of frequency distributions allow us to see what data look like. See what scores are most common (or frequent), which are infrequent, and the shape of the distribution. Can also tell whether there are any outliers (scores that are unusual, unexpected, impossible, or very different from the scores of other participants) o Outlier: scores that are very different from the rest of the scores in a dataset (i.e., much smaller or much larger); also known as extreme scores. o An outlier might reflect a data-entry error that can be corrected (e.g., a person's age appearing as 333).
- There are several types of graphs used to depict frequency distributions: bar graph, pie chart, histogram, and frequency polygon. " Bar graphs and histograms are the most common. Bar Graphs - Bar graph: graph using bars to depict frequencies of responses, percentages, or