MAT Conference May, 2012 Resampling with TinkerPlots Jane Watson University of Tasmania 1.

Slides:



Advertisements
Similar presentations
Probability models- the Normal especially.
Advertisements

Chapter 16 Inferential Statistics
Statistics.  Statistically significant– When the P-value falls below the alpha level, we say that the tests is “statistically significant” at the alpha.
Hypothesis Testing A hypothesis is a claim or statement about a property of a population (in our case, about the mean or a proportion of the population)
Statistics: Purpose, Approach, Method. The Basic Approach The basic principle behind the use of statistical tests of significance can be stated as: Compare.
Sampling Distributions (§ )
HYPOTHESIS TESTING Four Steps Statistical Significance Outcomes Sampling Distributions.
EPIDEMIOLOGY AND BIOSTATISTICS DEPT Esimating Population Value with Hypothesis Testing.
10-1 Introduction 10-2 Inference for a Difference in Means of Two Normal Distributions, Variances Known Figure 10-1 Two independent populations.
Probability (cont.). Assigning Probabilities A probability is a value between 0 and 1 and is written either as a fraction or as a proportion. For the.
INFERENTIAL STATISTICS – Samples are only estimates of the population – Sample statistics will be slightly off from the true values of its population’s.
Chapter 8 Introduction to Hypothesis Testing
Tests of significance & hypothesis testing Dr. Omar Al Jadaan Assistant Professor – Computer Science & Mathematics.
Informal statistical inference: Years 10 to 12 Maxine Pfannkuch and Chris Wild The University of Auckland.
6.1 What is Statistics? Definition: Statistics – science of collecting, analyzing, and interpreting data in such a way that the conclusions can be objectively.
Week 9 Testing Hypotheses. Philosophy of Hypothesis Testing Model Data Null hypothesis, H 0 (and alternative, H A ) Test statistic, T p-value = prob(T.
Introduction to Statistical Inference Probability & Statistics April 2014.
Comparing Two Proportions
Population All members of a set which have a given characteristic. Population Data Data associated with a certain population. Population Parameter A measure.
Estimation Bias, Standard Error and Sampling Distribution Estimation Bias, Standard Error and Sampling Distribution Topic 9.
STA Statistical Inference
Individual values of X Frequency How many individuals   Distribution of a population.
Significance Tests: THE BASICS Could it happen by chance alone?
90288 – Select a Sample and Make Inferences from Data The Mayor’s Claim.
90288 – Select a Sample and Make Inferences from Data The Mayor’s Claim.
1 rules of engagement no computer or no power → no lesson no SPSS → no lesson no homework done → no lesson GE 5 Tutorial 5.
CHAPTER 17: Tests of Significance: The Basics
Chapter 9 Fundamentals of Hypothesis Testing: One-Sample Tests.
Sampling And Resampling Risk Analysis for Water Resources Planning and Management Institute for Water Resources May 2007.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 10 Comparing Two Populations or Groups 10.1.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 10 Comparing Two Populations or Groups 10.1.
Medical Statistics as a science
Statistics: Unlocking the Power of Data Lock 5 Exam 2 Review STAT 101 Dr. Kari Lock Morgan 11/13/12 Review of Chapters 5-9.
Confidence Interval Estimation For statistical inference in decision making:
Copyright © 2011 Pearson Education, Inc. Putting Statistics to Work.
: An alternative representation of level of significance. - normal distribution applies. - α level of significance (e.g. 5% in two tails) determines the.
Revision of basic statistics Hypothesis testing Principles Testing a proportion Testing a mean Testing the difference between two means Estimation.
AP Statistics Section 11.1 B More on Significance Tests.
26134 Business Statistics Tutorial 12: REVISION THRESHOLD CONCEPT 5 (TH5): Theoretical foundation of statistical inference:
Synthesis and Review 2/20/12 Hypothesis Tests: the big picture Randomization distributions Connecting intervals and tests Review of major topics Open Q+A.
Sampling Design and Analysis MTH 494 Ossam Chohan Assistant Professor CIIT Abbottabad.
AP Test Practice. A student organization at a university is interested in estimating the proportion of students in favor of showing movies biweekly instead.
Dr.Theingi Community Medicine
Assessing Statistical Significance ROSS 2016 Lane-Getaz.
Improving Teaching and Learning of Probability in VCE
Chapter 25: Paired t-Test
CHAPTER 10 Comparing Two Populations or Groups
One-Sample Inference for Proportions
What Is a Test of Significance?
Inference for Proportions
Goals of Statistics 8/27.
Review Measure testosterone level in rats; test whether it predicts aggressive behavior. What would make this an experiment? Randomly choose which rats.
Goals of Statistics.
Statistical Data Analysis
CHAPTER 10 Comparing Two Populations or Groups
Quantitative Data Analysis P6 M4
Essential Statistics (a.k.a: The statistical bare minimum I should take along from STAT 101)
Writing the executive summary section of your report
Statistical Inference
What’s next Quiz.
CHAPTER 10 Comparing Two Populations or Groups
Statistical Data Analysis
CHAPTER 10 Comparing Two Populations or Groups
Sampling Distributions (§ )
CHAPTER 10 Comparing Two Populations or Groups
CHAPTER 10 Comparing Two Populations or Groups
CHAPTER 10 Comparing Two Populations or Groups
CHAPTER 10 Comparing Two Populations or Groups
CHAPTER 10 Comparing Two Populations or Groups
Some Key Ingredients for Inferential Statistics
Presentation transcript:

MAT Conference May, 2012 Resampling with TinkerPlots Jane Watson University of Tasmania 1

What is Resampling? It is a process that can lead to decision- making with data that does not depend on theoretical statistics. It is currently controversial in the world of statistics education and curriculum development. Personally I would like to see it in the Year 11/12 Australian Mathematics Curriculum. 2© Jane Watson, 2012

Decision Making in Statistics Statistics is about carrying out investigations with data from samples to answer questions about populations or with data from experiments to draw causal inferences. At some point in the development of understanding of the inferential process, probabilistic reasoning becomes involved because the decisions about the questions cannot be made with certainty. The question is: what processes are used? 3© Jane Watson, 2012

Inference: Formal and Informal Formal inference is what statisticians do based on the assumptions underlying the normal distribution to carry out hypothesis tests, etc. Informal inference is what school students do when evidence is used to make a generalisation beyond the data with an acknowledgement of uncertainty. ─Evidence: height data from my Grade 5 class ─Generalisation: what can I say about all Grade 5 students in Australia? ─Uncertainty: How confident am I about this? 4© Jane Watson, 2012

Informal Inference via Resampling Resampling methods offer a way of gathering evidence to support a generalisation that can be reported with an associated frequency-based probability. Resampling refers to the use of the observed data or of a data generating mechanism (such as a die) to produce new hypothetical samples, the results of which can then be analysed (Simon, 1997). 5© Jane Watson, 2012

Informal Inference via Resampling The process then recalculates the value of the statistic of interest for the resampled data, perhaps the difference in the group means or medians. This is done many times to estimate the relative frequency (probability) with which the original difference (or more extreme) would be expected to occur compared to the differences with random reallocation. 6© Jane Watson, 2012

Resampling Contexts –Compare proportions from 2-way tables –Compare means/medians for 2 groups –Estimate a population mean –Estimate a correlation coefficient –Estimate a confidence interval Programs –Minitab –Excel –R–R –Fathom –Applets (Rossman & Chance) –TinkerPlots 7© Jane Watson, 2012

Example using TinkerPlots (Shaughnessy et al., 2009) Is it easier for people to memorise meaningful words than nonsense words? Two lists of 3-letter words: one a list of meaningful words and the other nonsense words. The lists are randomly distributed face-down to members of the class, one to a student. Students are told to turn the sheet over and spend 30 seconds memorising the words. They then turn the sheet over and write as many words as they can remember on the back of the sheet. 8© Jane Watson, 2012

Compare performances on the two lists Class data: Is it easier to remember meaningful or nonsense words? How unusual is the difference? 9© Jane Watson, 2012

Using box plots from Year 10 Using Chris Wild’s criteria, no overlap of the boxes means 3/4 of “Nonsense” are to the left of 3/4 “Meaningful.” There appears to be evidence for a difference. 10© Jane Watson, 2012

Resampling with TinkerPlots Data from class in Data Cards and Table. Set up Sampler to reassign the data randomly (No_words_remembered) without replacement to the two conditions. Use the Ruler to measure the “new” difference in medians. Use the History button to record this and repeat “many” times. See how many times the difference is at least as large as the class difference of 4. 11© Jane Watson, 2012

12© Jane Watson, 2012

13© Jane Watson, 2012

14© Jane Watson, 2012

A Second Example: Swimming with Dolphins 30 patients diagnosed with mild to moderate depression were randomly allocated to two treatment groups where they engaged in the same amount of time swimming and snorkelling each day for four weeks. One group participated in the presence of bottlenose dolphins and the other did not. The patients had no other treatment. 15© Jane Watson, 2012

A Second Example: Swimming with Dolphins 16© Jane Watson, 2012

17© Jane Watson, 2012

18© Jane Watson, 2012

Benefits of Resampling Concrete – can be done “by hand first.” Students can “see” how unlikely (or otherwise) an outcome is. There is no theoretical baggage beyond random sampling. Put it in the Year 11/12 curriculum. 19© Jane Watson, 2012