Session2_HMA278_2010

# Session2_HMA278_2010 - HMA278/HAYG421 DesignandMeasurement2

This preview shows pages 1–17. Sign up to view the full content.

Click to edit Master subtitle style HMA278/HAYG421  Design and Measurement 2 Session 2 Diane Mainwaring

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

View Full Document
Brief Review of Last Session Limitations of hypothesis testing. Power analysis  Comparing the relationship between two metric  variables for subgroups Describing the Relationship Between two  Categorical Variables Testing Significance using Chi-Square Session 2
Describing the distribution of a single metric  variable Describing the relationship between two metric  variables Introduction to power analysis Review last Session

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

View Full Document
l S u m 0 a 4 5 .0 0 M o d e 1 R S td . E o f th e E s t im a P re d a . Regression Note that R is always reported as a positive  value, even when the relationship is  negative.
A N O V A b 1 6 9 0 .8 6 0 .0 0 0 a 2 5 2 9 3 R e g re s s R e s id u a T o ta l M o 1 S u m q u a d M e a S q u F S ig P d ic to rs a . D e p e n d b . o e f ic ie n ts a 2 3 5 2 .7 2 0 .0 0 0 . 0 4 6 .2 9 0 -3 .7 2 3 (C o n s ta A G E 1 B S td . e f S ta n d a rd C o e f ic ie n ts t S ig D e p e n a .

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

View Full Document
There was a weak, linear relationship between age  and hours spent watching television per week, with  older individuals tending to watch less television.  The relationship between age and time spent  watching TV was significant (r=-0.29, n=200,  p<.001).  Example
Effect Size:  Proportion of variation in scores  (dependent variable) that can be explained by the  differences in level of the independent variable. Significance versus Importance Power Analysis  Issues related to Hypothesis

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

View Full Document
Effect Size Obj1 8 r = –0.82
r  =   0.23

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

View Full Document
Correlation between age and enthusiasm   r = 0.64, n = 10, p = 0.046  Correlation between age and self esteem   r = 0.12, n = 1000, p < .001 Correlation between age and experience   r = 0.78, n = 1000, p < .001 Significance versus Importance
Samples of size 10 POP CORR SAMP 1 SAMP 2 SAMP3 SAMP 4 SAMP5 A 0.80 0.87 ** 0.97 ** 0.57 0.69 ** 0.80 ** B 0.64 0.71 * 0.91 ** 0.43 0.75 * 0.68 * C 0.26 0.09 0.66 ** 0.34 0.52 0.63 D 0.10 0.13 0.55 –0.06 –0.42 0.42

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

View Full Document
Samples of size 50 POP CORR SAMP 1 SAMP 2 SAMP 3 SAMP 4 SAMP 5 A 0.80 0.82 ** 0.79 ** 0.91 ** 0.83 ** 0.64 ** B 0.64 0.72 ** 0.67 ** 0.63 ** 0.78 ** 0.50 ** C 0.26 0.27 0.60 ** –0.11 0.42 ** 0.37 ** D 0.10 0.12 0.10 0.01 0.13 –0.11
Samples of size 100 POP CORR SAMP 1 SAMP 2 SAMP 3 SAMP 4 SAMP 5 A 0.80 0.80 ** 0.81 ** 0.84 ** 0.81 ** 0.75 ** B 0.64 0.70 ** 0.71 ** 0.76 ** 0.64 ** 0.66 ** C 0.26 0.27 ** 0.28 ** 0.26 ** 0.15 0.22 * D 0.10 0.19 ** –0.01 0.25 * 0.23 * 0.05

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

View Full Document
Samples of size 1000 Obj123
Question How closely do the sample  correlations reflect the correlations in  the population?

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

View Full Document
Consider Sample 5, population D (r=0.42) and Sample  3 population B ( r=0.43). In population D, population correlation = 0.10 In population B, population correlation = 0.64 What do we do if the  correlation is not significant?
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 10/27/2010 for the course ENGINEERIN CIC taught by Professor Loren during the Three '10 term at Swinburne.

### Page1 / 74

Session2_HMA278_2010 - HMA278/HAYG421 DesignandMeasurement2

This preview shows document pages 1 - 17. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online