Statistical testing Provide a way of determining whether hypothesis should be accepted or rejected. In psychology they tell us whether differences or relationships.

Slides:



Advertisements
Similar presentations
Statistics. Hypothesis Testing Hypothesis is a ‘testable statement’ Types = alternate, research, experimental (H1), null (H0) They are 1 or 2 tailed (directional.
Advertisements

1 Hypothesis Testing William P. Wattles, Ph.D. Psychology 302.
Chapter 16 Introduction to Nonparametric Statistics
Statistics Sample: Descriptive Statistics Population: Inferential Statistics.
Chapter 14 Conducting & Reading Research Baumgartner et al Chapter 14 Inferential Data Analysis.
Data measurement, probability and statistical tests
C82MCP Diploma Statistics School of Psychology University of Nottingham 1 Overview of Lecture Between Group & Within Subjects Designs Mann-Whitney Test.
Chapter 15 Nonparametric Statistics
STATISTICS. DESCRIPTIVE STATISTICS INFERENTIAL STATISTICS.
Nonparametric or Distribution-free Tests
Introduction to A2 research methods: We will look at the following concepts in a nut shell: Inferential tests & Significance Null hypothesis.
AM Recitation 2/10/11.
Overview of Statistical Hypothesis Testing: The z-Test
Jeopardy Hypothesis Testing T-test Basics T for Indep. Samples Z-scores Probability $100 $200$200 $300 $500 $400 $300 $400 $300 $400 $500 $400.
Hypothesis Testing Charity I. Mulig. Variable A variable is any property or quantity that can take on different values. Variables may take on discrete.
Inferential Stats, Discussions and Abstracts!! BATs Identify which inferential test to use for your experiment Use the inferential test to decide if your.
14 Elements of Nonparametric Statistics
Identify the I.V. and D.V. variables as you read the story: Two researchers were talking shop over coffee one morning. The topic was intensive early training.
Statistical Significance R.Raveendran. Heart rate (bpm) Mean ± SEM n In men ± In women ± The difference between means.
Statistical Analysis I have all this data. Now what does it mean?
Ordinally Scale Variables
Inference and Inferential Statistics Methods of Educational Research EDU 660.
Which Statistical Test to Select?. Choosing a statistical test Instructions You will need to click the mouse to progress through this presentation You.
INFERENTIAL STATISTICS 1.Level of data 2.Tests 3.Levels of significance 4.Type 1 & Type 2 Error.
Educational Research Chapter 13 Inferential Statistics Gay, Mills, and Airasian 10 th Edition.
Review Hints for Final. Descriptive Statistics: Describing a data set.
Experimental Design and Statistics. Scientific Method
Chapter Eight: Using Statistics to Answer Questions.
PSYCHOLOGY IA THE RESULTS. RATIONALE/PURPOSE The results section is where you report the results that you have found from your experiment. The results.
Research Methods Exam Qs & Mark Scheme Booklet FIND THE JUNE 2011 QS: READ THROUGH THEM HIGHLIGHT THE KEY PARTS OF THEM MARK SCHEME E.G. EXAMPLES ON EACH.
Statistical Inference Statistical inference is concerned with the use of sample data to make inferences about unknown population parameters. For example,
STATISTICS. DESCRIPTIVE STATISTICS Quick Re-Cap From Last Year What do they tell us? What are the ways you can describe your data? What are the ways you.
Statistics Statistics Data measurement, probability and statistical tests.
Chapter 13 Understanding research results: statistical inference.
Chapter 7: Hypothesis Testing. Learning Objectives Describe the process of hypothesis testing Correctly state hypotheses Distinguish between one-tailed.
Nonparametric statistics. Four levels of measurement Nominal Ordinal Interval Ratio  Nominal: the lowest level  Ordinal  Interval  Ratio: the highest.
Extension: How could researchers use a more powerful measure of analysis? Why do you think that researchers do not just rely on descriptive statistics.
1 Nonparametric Statistical Techniques Chapter 18.
Lesson 5 DATA ANALYSIS. Am I using and independent groups design or repeated measures? Independent groups Mann- Whitney U test Repeated measures Wilcoxon.
Exam question 15 minutes to look over plan. 30 minutes to answer question Describe and evaluate the gender schema theory of gender development (8 marks.
Research methods. Recap: last session 1.Outline the difference between descriptive statistics and inferential statistics? 2.The null hypothesis predicts.
Mann Whitney U Test - DV produces ordinal or interval type of data
Data measurement, probability and Spearman’s Rho
Learning Objectives: 1. Understand the use of significance levels. 2
Inferential Statistics
Data analysis Research methods.
Spearman’s Rank Correlation Test
Learning Aims By the end of this session you are going to totally ‘get’ levels of significance and why we do statistical tests!
Data measurement, probability and statistical tests
Which type of inferential test should be used?
Inferential Statistics
Spearman’s rho Chi-square (χ2)
Happy new year Welcome back.
Inferential Statistics
Inferential Statistics
Inferential statistics,
Inferential Statistics
Parametric and non parametric tests
Formation of relationships Matching Hypothesis
Spearman Rank Order Correlation Example
Starter: Descriptive Statistics
Research methods.
1.3 Data Recording, Analysis and Presentation
Data measurement, probability and statistical tests
6.1 Psychology Research methods.
Research Methods: Data analysis and reporting investigations.
Graphs and Chi Square.
Inferential Statistical Tests
Inferential testing.
PSYCHOLOGY AND STATISTICS
Presentation transcript:

Statistical testing Provide a way of determining whether hypothesis should be accepted or rejected. In psychology they tell us whether differences or relationships between variables are statistically significant or have occurred by chance.

Justify each test Fill in the gaps The Spearman’s Rho was used because the data can be treated as at least 1)_______________ and the researchers were studying a possible 2)_________________ between two co- variables 1 = Ordinal 2 = Correlation (or relationship)

Now you need to justify each test Fill in the gaps The Chi-Square test was used because the data can be treated as 1)_______________ and the researches had hypothesised that there will be 2)___________________ between conditions when using the 3) _________________________ design. 1 = Nominal 2 = a difference 3 = Independent groups (please note that the Chi-square is also used as a test of association)

Now you need to justify each test Fill in the gaps The Wilcoxon T test was used because the data can be treated as 1)_______________ and the researches had hypothesised that there will be 2)___________________ between conditions when using the 3) _________________________ design. 1 = ordinal 2 = a difference 3 = Repeated Measures (please note that the Wilcoxon T is also used for a matched-pairs design)

Now you need to justify each test Fill in the gaps The Mann-Whitney U test was used because the data can be treated as 1)_______________ and the researches had hypothesised that there will be 2)___________________ between conditions when using the 3) _________________________ design. 1 = ordinal 2 = a difference 3 = independent groups

Recap: probability and significance ExpressionInterpretationMeaning P<0.05 The probability that the difference occurred through chance is ________(1/20 or 5%) The result is________ P=0.05 The probability that the difference occurred through chance is ________(1/20 or 5%) The result is________ P>0.05 The probability that the difference occurred through chance is ________(1/20 or 5%) The result is________

Recap: probability and significance ExpressionInterpretationMeaning P<0.05 The probability that the difference occurred through chance is less than 0.05 (1/20 or 5%) The result is significant P=0.05 The probability that the difference occurred through chance is equal to 0.05 (1/20 or 5%) The result is significant P>0.05 The probability that the difference occurred through chance is greater than 0.05 (1/20 or 5%) The result is not significant

What would the Alternative and Null be? What would the conclusion be? Research has shown that the colour red improves task performance Findings support with p=0.06 Alternative The colour red will improve participants task performance Null There will be no significant difference in task performance when the colour red is used. Any difference will be due to chance Conclusion- There is no significant difference in task performance when the colour red is used to when it is not

What would the Alternative and Null be? What would the conclusion be? 2. A new type of hypnosis has been introduced to increase positive thinking patterns in those with depression. Findings support with p=0.007 Alternative: There will be a significant difference in the positive thinking patterns of participants undergoing hypnosis to those who have not. Null There will be no significant difference in the positive thinking patterns of those participants undergoing hypnosis to those who have not. Any difference will be due to chance Conclusion - There is a significant difference in the positive thinking patterns to those experiencing hypnosis to those who have not

Interpreting results of a statistical test Type 1 error: occurs when we reject the null hypothesis and accept the hypothesis even though findings are due to chance. Known as False positive (falsely accepting the hypothesis) This is likely to happen when a P value is too lenient such as P<0.1 Type 1 error can be reduced by making the significance level more stringent.

Interpreting results of a statistical test Type 2 error: occurs when we retain the null hypothesis even thought the hypothesis is correct Known as False negative (falsely accepting the null hypothesis) Type 1 error occurs when the significance level is too stringent. (1% significance level is harder to achieve so we are more likely to say our findings are due to chance)

Interpreting results of a statistical test Type 1 error: Example: if a pregnancy test revealed a women to be pregnant and she wasn’t. Type 2 error: Example: if a pregnancy test revealed a women NOT to be pregnant when she was.

Interpreting results of a statistical test 5% significance level Minimises the chances of making both Type 1 and Type 2 error. 10% Type 1 error 1% Type 2 error 5% significance level

Which error (type 1 or type 2) would occur if we use the following P values… P= 0.01 P= 0.1 Type 2 Type 1 Complete assessment 9 on page 12 in your research methods pack

Process of analysing scientific data 1. conduct a study 2. select correct statistical test to analyse 3. calculate an observed value 4. Compare observed value with critical value from existing table. 5. State which hypothesis is retained

Observed and critical values Observed values: Critical values: When referring to the critical value tables you need to consider: –Whether hypothesis is directional/non-directional –Number of participants –Level of significance

Observed and critical values Mann-Whitney and Wilcoxon: –observed values to be equal to or less than the critical value to be accepted as significant. Chi-squared and Spearman’s Rho: –observed value to be equal to or greater than the critical value to be accepted as significant

Class experiment

Cinderella questions 1.What type of creatures appeared in the bottom left? 2.From these creatures, what was the main item the one on the right was wearing? 3.What mode of transport appeared in the bottom right? 4.What were the exact words that were written along the bottom? 5.What colour was Cinderella’s dress? 6.What colour was the main background of the image? 7.What did Cinderella have around her neck? 8.What is special about this product? (2 possible answers) 9.What is on the horses’ heads? 10. Did the castle appear on the image?

Cinderella answers 1.What type of creatures appeared in the bottom left? Mice 2.From these creatures, what was the main item the one on the right was wearing? T shirt 3.What mode of transport appeared in the bottom right? Horse and carriage 4.What were the exact words that were written along the bottom? Limited time only 5.What colour was Cinderella’s dress? blue 6.What colour was the main background of the image? blue 7.What did Cinderella have around her neck? Black ribbon 8.What is special about this product? (2 possible answers) ist time on disc, 2 discs 9.What is on the horses’ heads? plumes 10.Did the castle appear on the image? yes

5 minutes On a scrap piece of paper….draw the flow diagram to show which statistical test to use

Rescuers questions 1.What was the boat made out of? 2.What was standing on the back of the boat? 3.What colour was the mouse on the right wearing? 4.What were the exact words that were written along the bottom? 5.What colour was the mouse on the left wearing? 6.What vegetation appeared in the water? 7.What did the mouse on the left have around its neck? 8.What word appeared between “Walt Disney” and “The Rescuers”? 9.What appeared in the sky? 10.Which mouse had visible teeth? (left or right mouse)

Rescuers answers 1.What was the boat made out of? leaf 2.What was standing on the back of the boat? Dragon fly 3.What colour was the mouse on the right wearing? red 4.What were the exact words that were written along the bottom? Two brave mice one great adventure 5.What colour was the mouse on the left wearing? purple 6.What vegetation appeared in the water? reeds 7.What did the mouse on the left have around its neck? bow 8.What word appeared between “Walt Disney” and “The Rescuers”? classics 9.What appeared in the sky? Sparkles 10.Which mouse had visible teeth? (left or right mouse) right

Results C1- Cinderella C2- Rescuers 17

Page 17 of your pack What is the IV? What is the DV? Write the research and null hypothesis Which statistical test would you use and why? Which level of significance would you use and why?

anks/

Observed value 1.find the difference between each pair of scores (it makes things easier to subtract in the direction the differences are expected to go which should be larger – smaller but it must be the same way for every pair. 2.Rank the differences; ignoring their sign. Omit any zero differences from the analysis.

3. Find the sum of ranks of positive differences and the sum of ranks of negative differences; the smaller of these is T 4. Consult appendix table on page 18 to find the critical value required; use N (number of participants) 5. Using two-tailed values, for significance T must be less than or equal to the table value (p<0.05) Is our obtained T less than or equal to the critical value? If so then we can reject the HO.

Fill in the spaces The observed value is ___________ N is ______ So the critical value at _____% level of significance is_____ So which hypothesis is retained and which is rejected?

Pages 14/15 Complete pages 14 and 15 from your research methods booklet.