Ch 8. Quantitative Data Analysis Flashcards
(31 cards)
The biggest mistake in quantitative research is to think that data analysis decisions can…
…wait until after the data have been collected.
How do we handle it when a respondent does not complete an answer? Is it missing because…(3)
- they accidentally skip it?
- they do not want to answer it?
- it does not apply to them?
Three types of variables (levels of measurement)
- Nominal
- Ordinal
- Interval/Ratio
Nominal Variable
The only difference that exists between participants is being in one category or another. Categories cannot be ordered by rank. Examples: Male/Female, Employed/Unemployed, Homeless/Housed
Ordinal Variable
The categories of the variable can be rank ordered (ex. high enthusiasm, moderate enthusiasm, low enthusiasm). Distance between categories may not be equal.
Interval/Ratio
Distance or amount of difference between categories is uniform (e.g., 0 siblings, 1 sibling, 2 siblings, etc.) Ratio variables have a real “0” start position. Can do arithmetic and mathematical operations with the categories (e.g., 1 sibling + 3 siblings = 4 siblings)
Univariate Analysis
Analysis of one variable at a time. Often the first step is to create frequency tables.
score that shows up the most in a particular category
Mode
middle score when all scores have been arrayed in order
Median
sum of all scores, divided by the number of scores
Mean
Highest score minus lowest score
Range
Measures the amount of variation around the mean
Standard Deviation
Determines whether there is a relationship between two variables
Bivariate Analysis
- Allow simultaneous analysis of two variables
- Identify patterns of association
- Can be used for any variable type
- Normally used for nominal or ordinal data
Contingency tables (cross-tabulations)
Has values of 0 (no relationship) +1 (perfect positive relationship) -1 (perfect negative relationship)
Pearson’s r
To be able to label a finding as “significant” means you need to:
- set up a null hypothesis
- establish an acceptable level of significance (p-value)
- if the null is correct there is no relationship
- if the null is rejected and the statistical significance (p) of the findings is at less than 0.05 level.
show the number of times a particular variable shows up in the distribution, expressed as an actual number and as a percentage of the whole
Frequency Table
Diagrams can be used to illustrate frequency distributions. What can be used for displaying nominal, ordinal, or interval/ratio variables?
bar charts/pie charts: nominal or ordinal variables
histograms: interval/ratio variable
nominal-nominal, nominal-ordinal, and nominal-interval/ratio bivariate analysis uses:
contingency table + chi-squre (x2) + cramer’s V
ordinal-ordinal and ordinal-interval/ratio bivariate analysis can be measured by:
kendall’s tau-b
interval/ratio - interval/ratio bivariate analysis can be measured by
Pearson’s R
Shows correlation between pairs of ordinal variables (ex., 2 Likert Scale responses) or with one ordinal and one interval/ratio variable (ex., frequency of activity/BP)
Like Pearson’s r, values range from 0 to +1
Kendall’s tau-b
Shows correlation between pairs of ordinal variables
Like Pearson’s r, values range from 0 to +1
Will predict a rank position from one variable to another
Spearman’s Rho
Shows the strength of the relationship between two nominal variables (ex., gender/homelessness)
Values range from 0 to 1
(Nominal categories cannot be rank ordered)
Usually reported with a contingency table and a chi-square test
Cramer’s V
