{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Lecture 15 Chi-Square

# Lecture 15 Chi-Square - ChiSquare Lecture 15 Today...

This preview shows pages 1–12. Sign up to view the full content.

Chi-Square Lecture 15

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Today • Introduction to non-parametric tests • Chi square  – Test of independence – Test of goodness of fit • (Not covered in this course)
Non-Parametric Statistics • Up to this point, we have used  parametric  statistics . – Normal distribution (Z scores), t tests, F test • An alternative:  non-parametric statistics – You don’t know the population variance ( σ ) – You don’t meet the assumptions for F and t tests  (not normally distributed) – Data are frequency counts or ranks

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Comparing Parametric & Non- parametric Tests • Similarities: – Both use null hypothesis testing logic – Both require random assignment to groups • Differences: – Assumptions – Interpretation
Some non-parametric tests • Chi Square – Test of independence – Test of goodness of fit • Mann-Whitney U, Wilcoxon matched-pairs sign  ranks T, Wilcoxon-Wilcox comparisons Spearman r s • Randomization Tests • AND many others (logistic regression, survival  analysis, growth curve analyses…)

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Chi Square • Used with  frequency counts  in categories • Comparing  observed  frequencies to  expected   frequencies • Uses a  chi square distribution  of values • Two types – Test of  independence – Test of  Goodness of Fit
Frequency Counts Favorite Food Pizza Chocolate Gender Males 18 6 Females 4 20 In cells: Frequency (# of people), rather than means

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Observed frequencies (O) – Actual count of events in a category Expected frequencies (E) – Theoretical frequency based on the null hypothesis – These are the values we’d expect to see if the null  hypothesis is true
Chi Square Test • We compare the observed and expected frequencies  using a chi square test χ ² = (O – E) ² E O = Observed Frequency E = Expected Frequency

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Chi Square Distribution • Theoretical  distribution • Changes as df  changes • Positively skewed  (no negative values)
Chi Square Distribution • For critical values, use

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 36

Lecture 15 Chi-Square - ChiSquare Lecture 15 Today...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online