March 24 - o Add all scores and divide by the number of...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
March 24, 2008 Central Tendency and Dispersion Summary measures o In addition to graphs and tables, we need summary statistics o Central tendency tells us the most typical or common score: Mean, median, mode o Dispersion tells us about differences in groups of cases Range, inter-quartile range, variance, standard deviation Central tendency: the mode o Mode can be calculated for any type of variable o It is your only option for a nominal-level measure or a true ordinal-level measure o It is the most common value o We can read it from a graph, or a frequency table o If there are two categories with equal or near-equal quantities at the mode, we have a bimodal distribution Central tendency: the median o The median is the 50% percentile – the middle score in a ranked list of values measured at the interval or ratio level o Half of all scores are above it; half are below it o Median position = (n+1)/2; (when cases are ranked in order) Central tendency: the mean o The arithmetic average ; For a sample μ For a population
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: o Add all scores and divide by the number of cases o This is what we refer to most often, and what we use most often in statistics o The mean carries the most information, but is sensitive to outliers o Formula (x with line over it = sigma*x sub i / n) =Σx i /N Dispersion o Dispersion statistics tell us how spread out or scattered the scores in a distribution are o This is important, because the central tendency alone doesn’t tell us enough o Though book discusses the variation ratio for nominal or ordinal data, we will focus only on measure for interval or ratio date Dispersion: the range o The range is the distance from the lowest to highest value Dispersion: Interquartile range o Quartiles are the 25 th , 50 th , and 75 th percentile (they divide the distribution in 4 equal segments) o IQR = X Q3 – X Q1 ; the difference between the 3 rd quartile and the 1 st quartile o If a quartile value falls between 2 cases, take their midpoint....
View Full Document

This note was uploaded on 03/15/2009 for the course SOCI 301 taught by Professor Kupchick during the Spring '09 term at University of Delaware.

Ask a homework question - tutors are online