This preview shows page 1. Sign up to view the full content.
Unformatted text preview: Steps for Hypothesis Testing
1. Hypothesis Testing 2. 3. 4. 5. 6. 7. 8. 9. H1 and H0 Determining the nature of the dependent variable Choosing the appropriate test statistic Setting Type I & Type II error rates Determining sample size Collecting data Conducting appropriate statistical tests Calculate observed effect sizes Decision Making Step #3: Choosing the Appropriate Test Statistic
This determines the null hypothesis distribution. For example:
Correlation (r) = interval/ratio data (no "true" IV) true" ChiSquare = nominal data ChiANOVA = interval/ratio data (2+ means)
Nominal Data One IV 2 Groups Ratio/Interval Data What Type of Test? Depends on # of IVs & Measurement Scale One IV > 2 groups > Two IV Nominal Data Interval/Ratio Data Nominal Data Interval/Ratio Data ChiSquare Test of Association Independent ttest ChiSquare Test of Association Oneway ANOVA ChiSquare Test of Association Twoway ANOVA Dependent ttest Oneway ANOVA 1 Example of different null hypothesis distributions Degrees of Freedom
The number of scores in a data set that are free to vary
Using a sample mean as an estimate of the population An unbiased estimator The shape of the ttest, X2, and Ftest will change WRT degrees of freedom. Putting a restriction on (Xi M)2
S# 1 2 3 4 5 6 7 8 9 X 30 29 12 18 16 24 19 20 (XM) (X10 9 8 2 4 4 1 0 8 (XM) (X10 19 11 9 5 9 8 8 0 M = 20 n=9 df = (n1) (ndf = 8 S# 1 2 3 4 5 6 7 8 9 X 30 29 12 18 16 24 19 20 12 (XM) (X10 9 8 2 4 4 1 0 8 (XM) (X10 19 11 9 5 9 8 8 0 ? Cannot be anything but... 2 Degrees of Freedom
The number of scores in a data set that are free to vary
Using a sample mean as an estimate of the population An unbiased estimator Increase sample size (n) increase relation to population
But, only to a point... point... Steps for Hypothesis Testing
1. 2. 3. 4. 5. 6. 7. 8. 9. Step 4: Set Type I & Type II Errors
Type I Error:
saying there is an effect when there is not an effect
(P (rejecting H0 / H0 is true) H1 and H0 Determining the nature of the dependent variable Choosing the appropriate test statistic Setting Type I & Type II error rates Determining sample size Collecting data Conducting appropriate statistical tests Calculate observed effect sizes Decision Making This is referred to as (alpha)
In psychology, = 0.05
Less than a 5% chance that you have committed a Type I error 3 Step 4: Set Type I & Type II Errors
Related to statistical significance Different types of Type I Errors:
Per Comparison () ( Per Experiment: (#tests) Experimentwise
[1(1)#tests] [1 (1 What is a "true" difference? = 0.05 95% (0.95) 2.5% (0.025) 2.5% (0.025) Difference! critical value Null is true critical value Difference! p = proportion under the curve Directionality Step 4: Set Type I & Type II Errors
Type II Error () (
Failing to reject the null hypothesis when it is in fact false and your research hypothesis is true Not as strictly enforced in psychology compared to Type I error
Times are changing... changing... Are researchers making a specific prediction with respect to directionality or just saying there will be a difference? 4 Step 4: Set Type I & Type II Errors
Usually set to 0.20
e.g., you have an 20% chance of NOT detecting something that IS actually there Step 4: Set Type I & Type II Errors
"True State" of the Null Hypothesis H0 TRUE H0 FALSE Related to practical significance
Involved with the design of your study
Decision ACCEPT H0 Correct! Type II Error Correct!
(power) REJECT H0 Type I Error 5 ...
View
Full
Document
This note was uploaded on 04/07/2008 for the course PSY 031 taught by Professor Dicorcia during the Spring '08 term at Tufts.
 Spring '08
 Dicorcia

Click to edit the document details