A Data Science Central Community
Hi guys,
I'm trying to validate a hypothesis (Younger people are more techsavy than older people). So what I understand is that we're essentially trying to examine the correlation between two variables:
 techsavy: which is a clustered categorical variable (5 categories)
 age: which is a categorical variable (5 categories)
Can you please suggest which statistical technique would be appropriate to validate the above hypothesis?
Simple Correlation/Chisquare/ANOVA/Multinomial Logistic Regression?
Many Thanks.
Tags:
Since you are dealing with categorical variables, and also since you have only two, chisquare test of independence would be an automatic choice for simplicity of application and interpretation.
If you want more details, you can find some here http://www.simafore.com/blog/?Tag=chi+square+test
In a previous work tech savy has more to do with the qualification than with age.
Old people with good qualifications are equally techsavy.
In my country the issue is that many older people have fewer qualifications than younger people.
But Chi Square is a good test.
Contingency Tables are good visualization method, with counts, percentiles in your case a 5 x 5 mosaic plot and table of counts, etc. Chi Sq tests use likelihood ratio and Pearson tests for example, but there are numerous options in stat software for analysis of those mosaic plots and their contingency table data.
Measures of Association, for example, several measure types).
And of course the Nominal Logistic Regression Modeling tools have effects tests (Wald, Likelihood Ratio) for the main effects and interactions of your model.
JMP.com or most other stat software tools support this type of data.
Pasted below are list of OPTIONS for the Mosaic Plot and its Contingency Table from JMP help file (no detail, just names or tests and analysis options for your consideration). This list is property of JMP.com
A graphical representation of the data in the Contingency Table. See "Mosaic Plot".


A twoway frequency table. There is a row for each factor level and a column for each response level. See "Contingency Table".


Analogous to the Analysis of Variance table for continuous data. The tests show that the response level rates are the same across X levels. See "Tests".


Only appears if the response has exactly two levels. Compares response proportions for the X levels to the overall response proportion. See "Analysis of Means for Proportions".


Shows which rows or columns of a frequency table have similar patterns of counts. In the correspondence analysis plot, there is a point for each row and for each column of the contingency table. See "Correspondence Analysis".


Tests if there is a relationship between two categorical variables after blocking across a third classification. See "CochranMantelHaenszel Test".


Only appears when both the X and Y variables have the same levels. Displays the Kappa statistic (Agresti 1990), its standard error, confidence interval, hypothesis test, and Bowker’s test of symmetry, also know as McNemar's test. See "Agreement Statistic".


Calculates risk ratios. Appears only when both the X and Y variables have only two levels. See "Relative Risk".


Performs a twosample test for proportions. This test compares the proportions of the Y variable between the two levels of the X variable. Appears only when both the X and Y variables have only two levels. See "Two Sample Test for Proportions".


Describes the association between the variables in the contingency table. See "Measures of Association".


Tests for trends in binomial proportions across levels of a single variable. This test is appropriate only when one variable has two levels and the other variable is ordinal. See "Cochran Armitage Trend Test".


See "Exact Test".

What is the measure of techsavvy and can you tell us the five categories?