Share
Embed
Transcript
29 slides
-
Quantitative Data Information that is systematically collected and communicated in
numerical form; Data that can be analyzed with mathematical (usually statistical) techniques -
Levels of Measurement Nominal (aka Categorical) Ordinal Interval Ratio Descriptive
labels/ categories; no meaningful order to values Depict the order of a measurement, but not the difference between integers Depict the order and difference between integers (“interval” = distance between entities); No “true” zero Depict the order and difference between integers; “True” zero ✓ Genders ✓ Countries ✓ Cities ✓ Occupations ✓ Likert-scale survey responses ✓ “Star” ratings ✓ Interval/ratio data expressed as categories ✓ IQ Scores ✓ Temperature ✓ Age ✓ Income ✓ Budgets -
Descriptive Statistics Analysis of data that helps describe, show or
summarize data in a meaningful way such that, for example, patterns might emerge from the data. -
Counts Percentages Rates Ratios Measures of central tendency Measures of
dispersion Commonly Used Descriptive Statistics -
Mean: Average value (sum/n) Median: Midpoint of a distribution (middle
number) Mode: Most frequent value Measures of Central Tendency Figures (numbers) that represent the “center” of the data -
Levels of Measurement Nominal (aka Categorical) Ordinal Interval Ratio Descriptive
labels/ categories; no meaningful order to values Depict the order of a measurement, but not the difference between integers Depict the order and difference between integers (“interval” = distance between entities); No “true” zero Depict the order and difference between integers; “True” zero ✓ Mode ✓ Mode ✓ Median ✓ Mode ✓ Median ✓ Mean ✓ Mode ✓ Median ✓ Mean -
Measures of Central Tendency $75k $65k $50k $50k $30k $30k
$30k Mode = $30k -
Measures of Central Tendency $75k $65k $50k $50k $30k $30k
$30k Median = $50k Mode = $30k -
Measures of Central Tendency $75k $65k $50k $50k $30k $30k
$30k Mean = $47k Median = $50k Mode = $30k -
Measures of Central Tendency $75k $65k $50k $50k $30k $30k
$30k Mean = $47k Median = $50k Mode = $30k $500k $75k $65k $50k $50k $30k $30k $30k Mean = $104k Median = $50k Mode = $30k -
Range: Difference between lowest and highest values Standard Deviation: Calculated
spread from the mean Interquartile Range: Spread from the median (Q3-Q1) Measures of Dispersion “Spread” of data; how far the data diverge from the data “center” -
Levels of Measurement Nominal (aka Categorical) Ordinal Interval Ratio Descriptive
labels/ categories; no meaningful order to values Depict the order of a measurement, but not the difference between integers Depict the order and difference between integers (“interval” = distance between entities); No “true” zero Depict the order and difference between integers; “True” zero ✓ Mode ✓ Mode ✓ Median ✓ Interquartile range ✓ Mode ✓ Median ✓ Mean ✓ Interquartile range ✓ Standard deviation ✓ Mode ✓ Median ✓ Mean ✓ Interquartile range ✓ Standard deviation -
Visualizing Data Strongly agree = 5 Agree = 4 Neither
agree nor disagree = 3 Disagree = 2 Strongly disagree = 1 Mean = 3.13 Mode = 5 Mean = 3.16 Mode = 3 Indicate your level of agreement that this is an overall effective course... -
$75k $65k $50k $50k $30k $30k $30k Mean = $47k
Median = $50k Mode = $30k $500k $75k $65k $50k $50k $30k $30k $30k Mean = $104k Median = $50k Mode = $30k -
Differences in satisfaction with city services based on race Using
frequencies Satisfied Neither Dissatisfied Total White 113 30 8 151 Nonwhite 37 15 22 74 Using percentages Satisfied Neither Dissatisfied Total White 75 20 5 100 Nonwhite 50 20 30 100 -
Examining Relationships Differences in measures of central tendency (means, medians,
modes) Crosstabs • Controlling for a third variable in crosstabs -
Differences in satisfaction with city services based on race (percentages)
Satisfied Neither Dissatisfied Total White 75 20 5 100 Nonwhite 50 20 30 100 -
Differences in satisfaction with city services based on race (percentages)
Less- affluent neighborhoods Satisfied Neither Dissatisfied Total White 28 22 50 100 Nonwhite 31 18 51 100 More-affluent neighborhoods Satisfied Neither Dissatisfied Total White 77 18 5 100 Nonwhite 74 20 6 100 -
Examining Relationships Differences in measures of central tendency (means, medians,
modes) Crosstabs • Controlling for a third variable in crosstabs Measures of association • Appropriate correlation analysis for level of measurement (i.e. nominal, ordinal, interval); Johnson, pg. 208 • Direction of relationship • Strength of relationship (correlation coefficient = r); Johnson, pg. 206