Statistical tests for replicated experiments Normal probability plots are a less formal diagnostic tool for detecting effects Normal probability plots.

Slides:



Advertisements
Similar presentations
BPS - 5th Ed. Chapter 181 Two-Sample Problems. BPS - 5th Ed. Chapter 182 Two-Sample Problems u The goal of inference is to compare the responses to two.
Advertisements

Lecture 2 ANALYSIS OF VARIANCE: AN INTRODUCTION
Multiple-choice question
1 Contact details Colin Gray Room S16 (occasionally) address: Telephone: (27) 2233 Dont hesitate to get in touch.
1 STA 536 – Experiments with More Than One Factor Experiments with More Than One Factor (Chapter 3) 3.1 Paired comparison design. 3.2 Randomized block.
Chapter 9 Introduction to the t-statistic
Chapter 15 ANOVA.
BPS - 5th Ed. Chapter 241 One-Way Analysis of Variance: Comparing Several Means.
1 Analysis of Variance This technique is designed to test the null hypothesis that three or more group means are equal.
ANOVA: ANalysis Of VAriance. In the general linear model x = μ + σ 2 (Age) + σ 2 (Genotype) + σ 2 (Measurement) + σ 2 (Condition) + σ 2 (ε) Each of the.
Experimental Design & Analysis
Statistics Are Fun! Analysis of Variance
Inferential Stats for Two-Group Designs. Inferential Statistics Used to infer conclusions about the population based on data collected from sample Do.
BHS Methods in Behavioral Sciences I
Analysis of Variance Chapter 3Design & Analysis of Experiments 7E 2009 Montgomery 1.
Chapter 2 Simple Comparative Experiments
Chapter 11: Inference for Distributions
Chapter 9 - Lecture 2 Computing the analysis of variance for simple experiments (single factor, unrelated groups experiments).
Statistical Analysis. Purpose of Statistical Analysis Determines whether the results found in an experiment are meaningful. Answers the question: –Does.
1 Formal Evaluation Techniques Chapter 7. 2 test set error rates, confusion matrices, lift charts Focusing on formal evaluation methods for supervised.
F-Test ( ANOVA ) & Two-Way ANOVA
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.
Linear Lack of Fit (LOF) Test An F test for checking whether a linear regression function is inadequate in describing the trend in the data.
Analysis of Variance or ANOVA. In ANOVA, we are interested in comparing the means of different populations (usually more than 2 populations). Since this.
CPE 619 Simple Linear Regression Models Aleksandar Milenković The LaCASA Laboratory Electrical and Computer Engineering Department The University of Alabama.
Simple Linear Regression Models
Today’s lesson Confidence intervals for the expected value of a random variable. Determining the sample size needed to have a specified probability of.
One-Way Analysis of Variance Comparing means of more than 2 independent samples 1.
© 1998, Geoff Kuenning General 2 k Factorial Designs Used to explain the effects of k factors, each with two alternatives or levels 2 2 factorial designs.
Measures of Variability Objective: Students should know what a variance and standard deviation are and for what type of data they typically used.
t(ea) for Two: Test between the Means of Different Groups When you want to know if there is a ‘difference’ between the two groups in the mean Use “t-test”.
DOX 6E Montgomery1 Unreplicated 2 k Factorial Designs These are 2 k factorial designs with one observation at each corner of the “cube” An unreplicated.
Chapter 10: Analyzing Experimental Data Inferential statistics are used to determine whether the independent variable had an effect on the dependent variance.
Inference for Regression Simple Linear Regression IPS Chapter 10.1 © 2009 W.H. Freeman and Company.
1 Dr. David McKirnan, Psychology 242 Introduction to Research Cranach, Tree of Knowledge [of Good and Evil] (1472) Click “slide show”
Comparing Three or More Means ANOVA (One-Way Analysis of Variance)
July, 2000Guang Jin Statistics in Applied Science and Technology Chapter 7 - Sampling Distribution of Means.
Essential Question:  How do scientists use statistical analyses to draw meaningful conclusions from experimental results?
1 The Two-Factor Mixed Model Two factors, factorial experiment, factor A fixed, factor B random (Section 13-3, pg. 495) The model parameters are NID random.
Statistics in IB Biology Error bars, standard deviation, t-test and more.
- We have samples for each of two conditions. We provide an answer for “Are the two sample means significantly different from each other, or could both.
Statistics for Political Science Levin and Fox Chapter Seven
© 2008 McGraw-Hill Higher Education The Statistical Imagination Chapter 5. Measuring Dispersion or Spread in a Distribution of Scores.
Introduction to ANOVA Research Designs for ANOVAs Type I Error and Multiple Hypothesis Tests The Logic of ANOVA ANOVA vocabulary, notation, and formulas.
Linear Regression Models Andy Wang CIS Computer Systems Performance Analysis.
Chapter 4 Exploring Chemical Analysis, Harris
ESTIMATION OF THE MEAN. 2 INTRO :: ESTIMATION Definition The assignment of plausible value(s) to a population parameter based on a value of a sample statistic.
Essential Statistics Chapter 171 Two-Sample Problems.
Class Six Turn In: Chapter 15: 30, 32, 38, 44, 48, 50 Chapter 17: 28, 38, 44 For Class Seven: Chapter 18: 32, 34, 36 Chapter 19: 26, 34, 44 Quiz 3 Read.
Lecture notes 13: ANOVA (a.k.a. Analysis of Variance)
Differences between t-distribution and z-distribution
Sample Size How many replications, n, do I need?
Analysis of Variance -ANOVA
Two way ANOVA with replication
i) Two way ANOVA without replication
Basic Practice of Statistics - 5th Edition
Chapter 2 Simple Comparative Experiments
Two way ANOVA with replication
Chapter 5 Introduction to Factorial Designs
Statistical Process Control
Measures of Dispersion (Spread)
Basic Practice of Statistics - 3rd Edition Two-Sample Problems
CHAPTER 12 More About Regression
Statistical tests for replicated experiments
Essential Statistics Two-Sample Problems - Two-sample t procedures -
Sample Size How many replications, n, do I need?
Essentials of Statistics for Business and Economics (8e)
ANOVA: Analysis of Variance
Statistical Inference for the Mean: t-test
F test for Lack of Fit The lack of fit test..
Presentation transcript:

Statistical tests for replicated experiments Normal probability plots are a less formal diagnostic tool for detecting effects Normal probability plots are a less formal diagnostic tool for detecting effects F-tests and t-tests provide a statistical test of factor effects F-tests and t-tests provide a statistical test of factor effects

Statistical tests for replicated experiments Statistical tests are possible for unreplicated designs (unreplicated pilot studies are essential tools in sample size calculations) Statistical tests are possible for unreplicated designs (unreplicated pilot studies are essential tools in sample size calculations) We will first focus on statistical tests for replicated designs We will first focus on statistical tests for replicated designs

Statistical tests for replicated experiments--Example Response--Pulse rate of subject Response--Pulse rate of subject Factors Factors –Treatment (Energy Drink, Placebo) –Setting (Moderate, Difficult) –Machine (Stair climber, Recumbent bike)

Statistical tests for replicated experiments--Example

Statistical tests for replicated experiments Effect sizes depend on the measurement scale Effect sizes depend on the measurement scale Statistical tests are based on standardized effects Statistical tests are based on standardized effects To compute standardized effects, start with an estimate of experimental error To compute standardized effects, start with an estimate of experimental error

Statistical tests for replicated experiments Experimental error can be summarized by the square root of the variance of the background noise (the standard deviation) Experimental error can be summarized by the square root of the variance of the background noise (the standard deviation) The experimental error measures variation in a single observation The experimental error measures variation in a single observation

Statistical tests for replicated experiments The variance is best estimated by the Mean Square for Pure Error (MSPE) The variance is best estimated by the Mean Square for Pure Error (MSPE)

Statistical tests for replicated experiments--Example The standard deviation for each run is ~3 beats per minute The standard deviation for each run is ~3 beats per minute

Statistical tests for replicated experiments While the standard deviation for a single response is the square root of MSPE, the standard deviation of an effect (its standard error) is: While the standard deviation for a single response is the square root of MSPE, the standard deviation of an effect (its standard error) is:

Statistical tests for replicated experiments We divide an effect in a k-factor experiment with n replications (e.g., A) by its standard error to compute a t-test statistic : We divide an effect in a k-factor experiment with n replications (e.g., A) by its standard error to compute a t-test statistic :

Statistical tests for replicated experiments Test statistics for other effects are computed similarly Test statistics for other effects are computed similarly U-do-it: Calculate the T-statistics of all effects for the Exercise data U-do-it: Calculate the T-statistics of all effects for the Exercise data

Statistical tests for replicated experiments When an effect is negligible, T has a t- distribution When an effect is negligible, T has a t- distribution The shape of the t-distribution curve depends on the number of replicates (degrees of freedom=2 k (n-1)) The shape of the t-distribution curve depends on the number of replicates (degrees of freedom=2 k (n-1)) The t-distribution curves have slightly more spread than the bell-shaped (normal) curve The t-distribution curves have slightly more spread than the bell-shaped (normal) curve

Statistical tests for replicated experiments--t curve for 3- factor design

Statistics tests for replicated experiments If |T| is larger than the 99.5 th or 97.5 th percentile of the t distribution, an effect is significant If |T| is larger than the 99.5 th or 97.5 th percentile of the t distribution, an effect is significant These percentiles are commonly found in textbooks (but please use a computer package instead) These percentiles are commonly found in textbooks (but please use a computer package instead)

Statistical tests for replicated experiments--t critical value for 3-factor design (n=4)

Statistical tests for replicated experiments Sometimes, twice the area to the right of |T| is reported as a p-value. Small p- values suggest that a standardized effect is distinguishable from background noise Sometimes, twice the area to the right of |T| is reported as a p-value. Small p- values suggest that a standardized effect is distinguishable from background noise You definitely need a computer to compute p-values--in the following example, the p-value for the M effect is 2*.122=.244 You definitely need a computer to compute p-values--in the following example, the p-value for the M effect is 2*.122=.244

Statistical test for replicated experiments--Example

Statistical tests for replicated experiments--Example U-do-it: Compute p-values for the remaining effects. Which effects are significant? Are these the same effects that the probability plot detected? U-do-it: Compute p-values for the remaining effects. Which effects are significant? Are these the same effects that the probability plot detected?

Statistical tests for replicated experiments F tests for individual effects are equivalent to t-tests F tests for individual effects are equivalent to t-tests F tests allow several comparisons to be tested simultaneously F tests allow several comparisons to be tested simultaneously The t-test can be used to help in computing the number of replications needed in a factorial experiment The t-test can be used to help in computing the number of replications needed in a factorial experiment

Statistical tests for replicated experiments Hypothesis testing can be extended to combine estimates of error from both pure error and negligible effects Hypothesis testing can be extended to combine estimates of error from both pure error and negligible effects –Negligible effects can be selected a priori or from effects plots –Degrees of freedom for t-tests and F-tests should be adjusted accordingly

Statistical tests for replicated experiments Error estimated from negiglible terms (Lack of Fit) is similar to MSPE Error estimated from negiglible terms (Lack of Fit) is similar to MSPE Source DF SS MS Residual Error Lack of Fit Lack of Fit Pure Error Pure Error