Scribd
Upload
29 views2 pages

Stats

This document provides an overview of key concepts in descriptive statistics, including: 1) Scales of measurement such as nominal, ordinal, interval, and ratio scales. 2) The distinction between populations and samples, and measures of central tendency like the mode, median, and mean. 3) Measures of variability such as range, interquartile range, variance, standard deviation, coefficient of variation, and standard error of the mean. 4) Common graphic summaries for presenting data, including bar charts, histograms, box-and-whisker plots, and dot plots.

Uploaded by

Emmy2013
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
29 views2 pages

Stats

This document provides an overview of key concepts in descriptive statistics, including: 1) Scales of measurement such as nominal, ordinal, interval, and ratio scales. 2) The distinction between populations and samples, and measures of central tendency like the mode, median, and mean. 3) Measures of variability such as range, interquartile range, variance, standard deviation, coefficient of variation, and standard error of the mean. 4) Common graphic summaries for presenting data, including bar charts, histograms, box-and-whisker plots, and dot plots.

Uploaded by

Emmy2013
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

01.14.

11 F
Monday, January 17, 2011
8:59 AM

Description of Data
Diff methods
Scales of measurement
1) Nominal scale
a) Based on classification of an observation according to the group - a process of categorization
Group ie with placebo another group w/o
2) Ordinal scale
a) Measurement the diff base on the relationship of observations
i) i.e. poor fair good rating scale: student to instructor's evaluation
ii) unequal intervals, ranking on a scale =/ "true #" although using real number i.e. 1-5
iii) i.e. education level
iv) Test purpose, if 3 # or more, could be ordinal scale
3) Continuous (don't m the diff btwn the 2 in this class)
a) Interval: distance btwn 2 numbers is known, zero pt is arbitrary, i.e. temp scales
b) Ratio: true zero pt, i.e. mass, time, mean age

Variables
1) Populations: parameters, don't change, Greek symbols
2) Samples: variables, change, Roman Characters
3) Measurement of Central tendency
a) Mode: most frequent measurement, often used in nominal scale, can be use in others, can be more than 1 mode
b) Median: 50% pt when the measurement are arranged in order of magnitude, not for nominal scale
a) insensitive to the extreme #
b) Can be a calculation of 2 numbers
c) Mean: avg, for continuous

Variability
Diff btwn the largest and smallest numbers
1) Range i.e. pulse rate
2) Interquartile range: use percentile i.e. 25th percentile to 75th percentile, give the middle 50% of the info
3) Variance:
a) most difficult, avg of square of the deviations about the mean, considered in terms of distance
b) How much scatters around the means we have
4) Standard deviation
a) Should be continues variable
b) Square root of variance
5) Coefficient of variation
a) Measures the % of spread
b) Unitless, allow for comparisons
6) Standard error of the mean
a) Error variability, derive from SD, give us a sense of how certain our mean is

Graphic Summaries
1) Bar charts
a) Categorical data (nominal, ordinal)
b) Like bins
2) Histograms
a) Represent a range of variable
3) Box-Whiskers
a) Mid 50% of data
b) Allow to observe unusual data
4) Dot plots
a) Cont data
b) x-axis represents groups

01.14.11 F Page 1
b) x-axis represents groups
c) Dot superimpose
d) Show relative location and spread of each group

01.14.11 F Page 2

You might also like