Basic Experimental Design Larry V. Hedges Northwestern University Prepared for the IES Summer Research Training Institute July 26, 2010.

Basic Experimental Design Larry V. Hedges Northwestern University Prepared for the IES Summer Research Training Institute July 26, 2010

Institute Schedule MondayTuesdayWednesdayThursdayFriday 26-Jul27-Jul28-Jul29-Jul30-Jul 8:00-10:00 Basic Design ISample/power IGrowth ModelingPower Lab ISpecify models HedgesBloomHedgesSpybrookLipsey 10:30-12:30 Basic Design IISample/Power IIAnalysis Lab IPower Lab IIDescribe outcomes HedgesBloomHedgesSpybrookLipsy Konstantopoulos Lunch 12:30-1:30 1:30-3:30 Basic Design IIISampling/ExternalAnalysis Lab IIMediation ModelsModel Cause HedgesValidityHedgesBeretvasCordray BloomKonstantopoulos 4:00-5:30 IntroduceGroup Project Group ProjectsMeeting CordrayCordray + Others Others Dinner 6:00 Dinner at Carmen'sDinner 6:00Dinner at Stained Glass

Institute Schedule MondayTuesdayWednesdayThursday 2-Aug3-Aug4-Aug5-Aug 8:00-10:00 Missing Data IModerator AnalysisFinalize GroupGroup 3 Presents GrahamKonstantopoulosProjects(faculty feedback) 10:30-12:30 Missing Data IIAlternate Designs IFinalize GroupGroup 4 Presents GrahamLipseyProjects(faculty feedback) Lunch 12:30-1:30 1:30-3:30 Analyzing FidelityAlternate Designs IIGroup 1 PresentsGroup 5 presents CordrayLipsey(faculty feedback) 4:00-5:30 Group Project Group 2 PresentsCourse Evaluation Meeting Cordray + Others (faculty feedback)Debrief Dinner at Mt EverestDinner 6:00 Dinner & Graduation

What is Experimental Design? Experimental design includes both Strategies for organizing data collection Data analysis procedures matched to those data collection strategies Classical treatments of design stress analysis procedures based on the analysis of variance (ANOVA) Other analysis procedure such as those based on hierarchical linear models or analysis of aggregates (e.g., class or school means) are also appropriate

Why Do We Need Experimental Design? Because of variability We wouldn’t need a science of experimental design if If all units (students, teachers, & schools) were identical and If all units responded identically to treatments We need experimental design to control variability so that treatment effects can be identified

A Little History The idea of controlling variability through design has a long history In 1747 Sir James Lind’s studies of scurvy Their cases were as similar as I could have them. They all in general had putrid gums, spots and lassitude, with weakness of their knees. They lay together on one place … and had one diet common to all (Lind, 1753, p. 149) Lind then assigned six different treatments to groups of patients

A Little History The idea of random assignment was not obvious and took time to catch on In 1648 von Helmont carried out one randomization in a trial of bloodletting for fevers In 1904 Karl Pearson suggested matching and alternation in typhoid trials Amberson, et al. (1931) carried out a trial with one randomization In 1937 Sir Bradford Hill advocated alternation of patients in trials rather than randomization Diehl, et al. (1938) carried out a trial that is sometimes referred to as randomized, but it actually used alternation

A Little History The first modern randomized clinical trial in medicine is usually considered to be the trial of streptomycin for treating tuberculosis It was conducted by the British Medical Research Council in 1946 and reported in 1948

A Little History Experiments have been used longer in the behavioral sciences (e.g., psychophysics: Pierce and Jastrow, 1885) Experiments conducted in laboratory settings were widely used in educational psychology (e.g., McCall, 1923) Thorndike (early 1900’s) Lindquist (1953) Gage field experiments on teaching (1978 – 1984)

A Little History Studies in crop variation I – VI (1921 – 1929) In 1919 a statistician named Fisher was hired at Rothamsted agricultural station They had a lot of observational data on crop yields and hoped a statistician could analyze it to find effects of various treatments All he had to do was sort out the effects of confounding variables

Studies in Crop Variation I (1921) Fisher does regression analyses—lots of them—to study (and get rid of) the effects of confounders soil fertility gradients drainage differences effects of rainfall effects of temperature and weather, etc. Fisher does qualitative work to sort out anomalies Conclusion The effects of confounders are typically larger than those of the systematic effects we want to study

Studies in Crop Variation II (1923) Fisher invents Basic principles of experimental design Control of variation by randomization Analysis of variance

Studies in Crop Variation IV and VI Studies in Crop variation IV (1927) Fisher invents analysis of covariance to combine statistical control and control by randomization Studies in crop variation VI (1929) Fisher refines the theory of experimental design, introducing most other key concepts known today

Our Hero in 1929

Principles of Experimental Design Experimental design controls background variability so that systematic effects of treatments can be observed Three basic principles 1.Control by matching 2.Control by randomization 3.Control by statistical adjustment Their importance is in that order

Control by Matching Known sources of variation may be eliminated by matching Eliminating genetic variation Compare animals from the same litter of mice Eliminating district or school effects Compare students within districts or schools However matching is limited matching is only possible on observable characteristics perfect matching is not always possible matching inherently limits generalizability by removing (possibly desired) variation

Control by Matching Matching ensures that groups compared are alike on specific known and observable characteristics (in principle, everything we have thought of) Wouldn’t it be great if there were a method of making groups alike on not only everything we have thought of, but everything we didn’t think of too? There is such a method

Control by Randomization Matching controls for the effects of variation due to specific observable characteristics Randomization controls for the effects all (observable or non-observable, known or unknown) characteristics Randomization makes groups equivalent (on average) on all variables (known and unknown, observable or not) Randomization also gives us a way to assess whether differences after treatment are larger than would be expected due to chance.

Control by Randomization Random assignment is not assignment with no particular rule. It is a purposeful process Assignment is made at random. This does not mean that the experimenter writes down the names of the varieties in any order that occurs to him, but that he carries out a physical experimental process of randomization, using means which shall ensure that each variety will have an equal chance of being tested on any particular plot of ground (Fisher, 1935, p. 51)

Control by Randomization Random assignment of schools or classrooms is not assignment with no particular rule. It is a purposeful process Assignment of schools to treatments is made at random. This does not mean that the experimenter assigns schools to treatments in any order that occurs to her, but that she carries out a physical experimental process of randomization, using means which shall ensure that each treatment will have an equal chance of being tested in any particular school (Hedges, 2007)

Control by Statistical Adjustment Control by statistical adjustment is a form of pseudo- matching It uses statistical relations to simulate matching Statistical control is important for increasing precision but should not be relied upon to control biases that may exist prior to assignment Statistical control is the weakest of the three experimental design principles because its validity depends on knowing a statistical model for responses

Using Principles of Experimental Design You have to know a lot (be smart) to use matching and statistical control effectively You do not have to be smart to use randomization effectively But Where all are possible, randomization is not as efficient (requires larger sample sizes for the same power) as matching or statistical control

Basic Ideas of Design: Independent Variables (Factors) The values of independent variables are called levels Some independent variables can be manipulated, others can’t Treatments are independent variables that can be manipulated Blocks and covariates are independent variables that cannot be manipulated These concepts are simple, but are often confused Remember: You can randomly assign treatment levels but not blocks

Basic Ideas of Design (Crossing) Relations between independent variables Factors (treatments or blocks) are crossed if every level of one factor occurs with every level of another factor Example The Tennessee class size experiment assigned students to one of three class size conditions. All three treatment conditions occurred within each of the participating schools Thus treatment was crossed with schools

Basic Ideas of Design (Nesting) Factor B is nested in factor A if every level of factor B occurs within only one level of factor A Example The Tennessee class size experiment actually assigned classrooms to one of three class size conditions. Each classroom occurred in only one treatment condition Thus classrooms were nested within treatments (But treatment was crossed with schools)

Where Do These Terms Come From? (Nesting) An agricultural experiment where blocks are literally blocks or plots of land Here each block is literally nested within a treatment condition Blocks 12…n T1T2…T1

Where Do These Terms Come From? (Crossing) An agricultural experiment Blocks were literally blocks of land and plots of land within blocks were assigned different treatments Blocks 12…n T1T2 … T1 T2T1T2

Where Do These Terms Come From? (Crossing) Blocks were literally blocks of land and plots of land within blocks were assigned different treatments. Here treatment literally crosses the blocks Blocks 12…n T1T2 … T1 T2T1T2

Where Do These Terms Come From? (Crossing) The experiment is often depicted like this. What is wrong with this as a field layout? Consider possible sources of bias Blocks 12…n Treatment 1 … Treatment 2

Blocking Variables We often exploit natural structure by adding blocking variables to the design Examples districts states regions This may be a good idea if they explain variation But it raises issues in analysis about how you think about the blocks (fixed or random effects) We will talk about that later

Think About These Designs A study was to assign schools to treatments, but you decide to block by districts before assignment to treatments A study was to have assigned individuals (students) to treatments within schools, but you decide to block by districts before assignment to treatments Both of these designs occur frequently Which design would you expect to be the most sensitive?

Districts As Blocks Added to a Hierarchical Design D 1 D 2 … T 1 T 2 T 1 T 2 … S 1 S 2 S 3 S 4 S 5 S 6 S 7 S 8 …

Districts As Blocks Added to a Randomized Blocks Design D 1 D 2 … T 1 T 2 T 1 T 2 … S 1 S 2 S 1 S 2 S 3 S 4 S 3 S 4 …

Think About These Designs 1. A study assigns T or C to 20 teachers. The teachers are in five schools, and each teacher teaches 4 science classes 2. A study assigns a reading treatment (or control) to children in 20 schools. Each child is classified into one of three groups with different risk of reading failure. 3. Two schools in each of 10 districts are picked to participate. Each school has two grade 4 teachers. One of them is assigned to T, the other to C

Three Basic Designs The completely randomized design Treatments are assigned to individuals The randomized block design Treatments are assigned to individuals within blocks (This is sometimes called the matched design, because individuals are matched within blocks) The hierarchical design Treatments are assigned to blocks, the same treatment is assigned to all individuals in the block

The Completely Randomized Design Individuals are randomly assigned to one of two treatments TreatmentControl Individual 1 Individual 2 …… Individual n T Individual n C

The Randomized Block Design Block 1…Block m Treatment 1 Individual 1 … …… … …… Individual n 1 Individual n m Treatment 2 Individual n 1 +1Individual n m + 1 …… Individual 2n 1 Individual 2n m

The Hierarchical Design TreatmentControl Block 1Block mBlock m+1Block 2m Individual 1 … … Individual 2 ………… Individual n 1 Individual n m Individual n m+1 Individual n 2m

Randomization Procedures Randomization has to be done as an explicit process devised by the experimenter Haphazard is not the same as random Unknown assignment is not the same as random “Essentially random” is technically meaningless Alternation is not random, even if you alternate from a random start This is why R.A. Fisher was so explicit about randomization processes

Randomization Procedures R.A. Fisher on how to randomize an experiment with small sample size and 5 treatments A satisfactory method is to use a pack of cards numbered from 1 to 100, and to arrange them in random order by repeated shuffling. The varieties [treatments] are numbered from 1 to 5, and any card such as the number 33, for example is deemed to correspond to variety [treatment] number 3, because on dividing by 5 this number is found as the remainder. (Fisher, 1935, p.51)

Randomization Procedures Think about Fisher’s description Does it worry you in any way?

Randomization Procedures You may want to use a table of random numbers, but be sure to pick an arbitrary start point! Beware random number generators—they typically depend on seed values, be sure to vary the seed value (if they do not do it automatically) Otherwise you can reliably generate the same sequence of random numbers every time It is no different that starting in the same place in a table of random numbers

Randomization Procedures Completely Randomized Design (2 treatments, 2n individuals) Make a list of all individuals For each individual, pick a random number from 1 to 2 (odd or even) Assign the individual to treatment 1 if even, 2 if odd When one treatment is assigned n individuals, stop assigning more individuals to that treatment

Randomization Procedures Completely Randomized Design (2pn individuals, p treatments) Make a list of all individuals For each individual, pick a random number from 1 to p One way to do this is to get a random number of any size, divide by p, the remainder R is between 0 and (p – 1), so add 1 to the remainder to get R + 1 Assign the individual to treatment R + 1 Stop assigning individuals to any treatment after it gets n individuals

Randomization Procedures Randomized Block Design with 2 Treatments (m blocks per treatment, 2n individuals per block) Make a list of all individuals in the first block For each individual, pick a random number from 1 to 2 (odd or even) Assign the individual to treatment 1 if even, 2 if odd Stop assigning a treatment it is assigned n individuals in the block Repeat the same process with every block

Randomization Procedures Randomized Block Design with p Treatments (m blocks per treatment, pn individuals per block) Make a list of all individuals in the first block For each individual, pick a random number from 1 to p Assign the individual to treatment p Stop assigning a treatment it is assigned n individuals in the block Repeat the same process with every block

Randomization Procedures Hierarchical Design with 2 Treatments (m blocks per treatment, n individuals per block) Make a list of all blocks For each block, pick a random number from 1 to 2 Assign the block to treatment 1 if even, treatment 2 if odd Stop assigning a treatment after it is assigned m blocks Every individual in a block is assigned to the same treatment

Randomization Procedures Hierarchical Design with p Treatments (m blocks per treatment, n individuals per block) Make a list of all blocks For each block, pick a random number from 1 to p Assign the block to treatment corresponding to the number Stop assigning a treatment after it is assigned m blocks Every individual in a block is assigned to the same treatment

Randomization Procedures What if I get a big imbalance by chance? Classical answers If there are random assignments you wouldn’t like, include blocking variables OR Use statistical control More complicated alternatives Adaptive randomization methods (e.g., Efron’s)

Sampling Models

Sampling Models in Educational Research Sampling models are often ignored in educational research But Sampling is where the randomness comes from in social research Sampling therefore has profound consequences for statistical analysis and research designs

Sampling Models in Educational Research Which is a better simple random sample (which sample will provide a more precise estimate)? Sample A, with N = 1,000 Sample B, with N = 2,000

Sampling Models in Educational Research Why? Because if the population variance is σ T 2 We know that the variance of the sample mean from a sample of size N is σ T 2 /N But

Sampling Models in Educational Research Simple random samples are rare in field research Educational populations are hierarchically nested: Students in classrooms in schools Schools in districts in states We usually exploit the population structure to sample students by first sampling schools Even then, most samples are not probability samples, but they are intended to be representative (of some population)

Sampling Models in Educational Research Survey research calls this strategy multistage (multilevel) clustered sampling We often sample clusters (schools) first then individuals within clusters (students within schools) This is a two-stage (two-level) cluster sample We might sample schools, then classrooms, then students This is a three-stage (three-level) cluster sample

Sampling Models in Educational Research Which is a better two-stage sample (which sample will provide a more precise estimate)? Sample A, with N = 1,000 Sample B, with N = 2,000 Now we cannot tell unless we know the number of clusters ( m ) and number of units ( n ) in each cluster

Precision of Estimates Depends on the Sampling Model Suppose the total population variance is σ T 2 and ICC is ρ Consider two samples of size N = mn A simple random sample or stratified sample The variance of the mean is σ T 2 /mn A clustered sample of n students from each of m schools The variance of the mean is (σ T 2 /mn)[1 + (n – 1)ρ] The inflation factor [1 + (n – 1)ρ] is called the design effect

Precision of Estimates Depends on the Sampling Model Suppose the population variance is σ T 2 School level ICC is ρ S, class level ICC is ρ C Consider two samples of size N = mpn A simple random sample or stratified sample The variance of the mean is σ T 2 /mpn A clustered sample of n students from p classes in m schools The variance is (σ T 2 /mpn)[1 + (pn – 1)ρ S + (n – 1)ρ C ] The three level design effect is [1 + (pn – 1)ρ S + (n – 1)ρ C ]

Example For example, suppose ρ = 0.20 Sample A Suppose m = 100 and n = 10, so N = 1,000 then the variance of the mean is (σ T 2 /100 x 10)[1 + (10 – 1)0.20] = (σ T 2 /1000)(2.8) Sample B Suppose m = 20 and n = 100, so N = 2,000, then the variance of the mean is (σ T 2 /100 x 20)[1 + (100 – 1)0.20] = (σ T 2 /1000)(10.4)

Precision of Estimates Depends on the Sampling Model The total variance can be partitioned into between cluster ( σ B 2 ) and within cluster ( σ W 2 ) variance We define the intraclass correlation as the proportion of total variance that is between clusters There is typically much more variance within clusters ( σ W 2 ) than between clusters ( σ B 2 ) School level intraclass correlation values are 0.10 to 0.25 This means that ( σ W 2 ) is between 9 and 3 times as large as ( σ B 2 )

Precision of Estimates Depends on the Sampling Model So why does ( σ B 2 ) have such a big effect? Because averaging (independent things) reduces variance The variance of the mean of a sample of m clusters of size n can be written as The cluster effects are only averaged over the number of clusters

Precision of Estimates Depends on the Sampling Model Treatment effects in experiments and quasi- experiments are mean differences Therefore precision of treatment effects and statistical power will depend on the sampling model

Sampling Models in Educational Research The fact that the population is structured does not mean the sample is must be a clustered sample Whether it is a clustered sample depends on: How the sample is drawn (e.g., are schools sampled first then individuals randomly within schools) What the inferential population is (e.g., is the inference to these schools studied or a larger population of schools)

Sampling Models in Educational Research A necessary condition for a clustered sample is that it is drawn in stages using population subdivisions schools then students within schools schools then classrooms then students However, if all subdivisions in a population are present in the sample, the sample is not clustered, but stratified Stratification has different implications than clustering Whether there is stratification or clustering depends on the definition of the population to which we draw inferences (the inferential population)

Sampling Models in Educational Research The clustered/stratified distinction matters because it influences the precision of statistics estimated from the sample If all population subdivisions are included in the every sample, there is no sampling (or exhaustive sampling) of subdivisions therefore differences between subdivisions add no uncertainty to estimates If only some population subdivisions are included in the sample, it matters which ones you happen to sample thus differences between subdivisions add to uncertainty

Inferential Population and Inference Models The inferential population or inference model has implications for analysis and therefore for the design of experiments Do we make inferences to the schools in this sample or to a larger population of schools? Inferences to the schools or classes in the sample are called conditional inferences Inferences to a larger population of schools or classes are called unconditional inferences

Inferential Population and Inference Models Note that the inferences (what we are estimating) are different in conditional versus unconditional inference models In a conditional inference, we are estimating the mean (or treatment effect) in the observed schools In unconditional inference we are estimating the mean (or treatment effect) in the population of schools from which the observed schools are sampled We are still estimating a mean (or a treatment effect) but they are different parameters with different uncertainties

Fixed and Random Effects When the levels of a factor (e.g., particular blocks included) in a study are sampled and the inference model is unconditional, that factor is called random and its effects are called random effects When the levels of a factor (e.g., particular blocks included) in a study constitute the entire inference population and the inference model is conditional, that factor is called fixed and its effects are called fixed effects

Fixed and Random Effects Remember the idea of adding blocking variables Technically, if blocking variables (e.g., district) are fixed effects: generalizations are limited to the districts observed random effects: generalizations to a larger universe of districts These technicalities are often ignored The key point is that generalizations are not supported by sampling

Applications to Experimental Design We will look in detail at the two most widely used experimental designs in education Randomized blocks designs Hierarchical designs

Experimental Designs For each design we will look at Structural Model for data (and what it means) Two inference models –What does ‘treatment effect’ mean in principle –What is the estimate of treatment effect –How do we deal with context effects Two statistical analysis procedures –How do we estimate and test treatment effects –How do we estimate and test context effects –What is the sensitivity of the tests

The Randomized Block Design The population (the sampling frame) We wish to compare two treatments We assign treatments within schools Many schools with 2 n students in each Assign n students to each treatment in each school

The Randomized Block Design The experiment Compare two treatments in an experiment We assign treatments within schools With m schools with 2 n students in each Assign n students to each treatment in each school

The Randomized Block Design Diagram of the design Schools Treatment12… m 1 … 2 …

The Randomized Block Design School 1 Schools Treatment12… m 1 … 2 …

The Conceptual Model The statistical model for the observation on the k th person in the j th school in the i th treatment is Y ijk = μ +α i + β j + αβ ij + ε ijk where μ is the grand mean, α i is the average effect of being in treatment i, β j is the average effect of being in school j, αβ ij is the difference between the average effect of treatment i and the effect of that treatment in school j, ε ijk is a residual

Effect of Context Context Effect

Two-level Randomized Block Design With No Covariates (HLM Notation) Level 1 (individual level) Y ijk = β 0j + β 1j T ijk + ε ijk ε ~ N(0, σ W 2 ) Level 2 (school level) β 0j = π 00 + ξ 0j ξ 0j ~ N(0, σ S 2 ) β 1j = π 10 + ξ 1j ξ 1j ~ N(0, σ T x S 2 ) If we code the treatment T ijk = ½ or - ½, then the parameters are identical to those in standard ANOVA

Effects and Estimates The population mean of treatment 1 in school j is α 1 + αβ 1j The population mean of treatment 2 in school j is α 2 + αβ 2j The estimate of the mean of treatment 1 in school j is α 1 + αβ 1j + ε 1j ● The estimate of the mean of treatment 2 in school j is α 2 + αβ 2j + ε 2j ●

Effects and Estimates The comparative treatment effect in any given school j is ( α 1 – α 2 ) + ( αβ 1j – αβ 2j ) The estimate of comparative treatment effect in school j is (α 1 – α 2 ) + ( αβ 1j – αβ 2j ) + ( ε 1j ● – ε 2j ● ) The mean treatment effect in the experiment is (α 1 – α 2 ) + ( αβ 1 ● – αβ 2 ● ) The estimate of the mean treatment effect in the experiment is (α 1 – α 2 ) + ( αβ 1 ● – αβ 2 ● ) + ( ε 1 ●● – ε 2 ●● )

Inference Models Two different kinds of inferences about effects Unconditional Inference (Schools Random) Inference to the whole universe of schools (requires a representative sample of schools) Conditional Inference (Schools Fixed) Inference to the schools in the experiment (no sampling requirement on schools)

Statistical Analysis Procedures Two kinds of statistical analysis procedures Mixed Effects Procedures (Schools Random) Treat schools in the experiment as a sample from a population of schools (only strictly correct if schools are a sample) Fixed Effects Procedures (Schools Fixed) Treat schools in the experiment as a population

Unconditional Inference (Schools Random) The estimate of the mean treatment effect in the experiment is (α 1 – α 2 ) + ( αβ 1 ● – αβ 2 ● ) + ( ε 1 ●● – ε 2 ●● ) The average treatment effect we want to estimate is (α 1 – α 2 ) The term ( ε 1 ●● – ε 2 ●● ) depends on the students in the schools in the sample The term ( αβ 1 ● – αβ 2 ● ) depends on the schools in sample Both ( ε 1 ●● – ε 2 ●● ) and ( αβ 1 ● – αβ 2 ● ) are random and average to 0 across students and schools, respectively

Conditional Inference (Schools Fixed) The estimate of the mean treatment effect in the experiment is still (α 1 – α 2 ) + ( αβ 1 ● – αβ 2 ● ) + ( ε 1 ●● – ε 2 ●● ) Now the average treatment effect we want to estimate is (α 1 + αβ 1● ) – (α 2 + αβ 2● ) = (α 1 – α 2 ) + (αβ 1● – αβ 2● ) The term ( ε 1 ●● – ε 2 ●● ) depends on the students in the schools in the sample The term ( αβ 1 ● – αβ 2 ● ) depends on the schools in sample, but the treatment effect in the sample of schools is the effect we want to estimate

Expected Mean Squares Randomized Block Design (Two Levels, Schools Random) Source df E{MS} Treatment (T) 1σ W 2 + nσ T x S 2 + nmΣα i 2 Schools (S) m – 1 σ W 2 + 2nσ S 2 T x S m – 1 σ W 2 + nσ T x S 2 Within Cells 2m ( n – 1 ) σW2σW2

Mixed Effects Procedures (Schools Random) The test for treatment effects has H 0 : (α 1 – α 2 ) = 0 Estimated mean treatment effect in the experiment is (α 1 – α 2 ) + ( αβ 1 ● – αβ 2 ● ) + ( ε 1 ●● – ε 2 ●● ) The variance of the estimated treatment effect is 2[σ W 2 + nσ T x S 2 ] /mn = 2[1 + (n ω S – 1)ρ]σ 2 /mn Here ω S = σ T x S 2 /σ S 2 and ρ = σ S 2 /(σ S 2 + σ W 2 ) = σ S 2 /σ 2

Mixed Effects Procedures The test for treatment effects: F T = MS T /MS T x S with (m – 1) df The test for context effects (treatment by schools interaction) is F TxS = MS T x S /MS WS with 2m(n – 1) df Power is determined by the operational effect size where ω S = σ T x S 2 /σ S 2 and ρ = σ S 2 /(σ S 2 + σ W 2 ) = σ S 2 /σ 2

Expected Mean Squares Randomized Block Design (Two Levels, Schools Fixed) Source Df E{MS} Treatment (T) 1σ W 2 + nmΣα i 2 Schools (S) m – 1 σ W 2 + 2nΣβ i 2 /(m – 1) S x T m – 1 σ W 2 + nΣΣαβ ij 2 /(m – 1) Within Cells 2m ( n – 1 ) σW2σW2

Fixed Effects Procedures The test for treatment effects has H 0 : (α 1 – α 2 ) + (αβ 1● – αβ 2● ) = 0 Estimated mean treatment effect in the experiment is (α 1 – α 2 ) + (αβ 1 ● – αβ 2 ● ) + ( ε 1 ●● – ε 2 ●● ) The variance of the estimated treatment effect is 2σ W 2 /mn

Fixed Effects Procedures The test for treatment effects: F T = MS T /MS WS with m(n – 1) df The test for context effects (treatment by schools interaction) is F C = MS T x S /MS WS with 2 m(n – 1) df Power is determined by the operational effect size with m(n – 1) df

Comparing Fixed and Mixed Effects Statistical Procedures (Randomized Block Design) FixedMixed Inference ModelConditionalUnconditional Estimand (α 1 – α 2 ) + (αβ 1● – αβ 2● )(α 1 – α 2 ) Contaminating Factors (ε 1●● – ε 2●● )(αβ 1● – αβ 2● ) + (ε 1●● – ε 2●● ) Operational Effect Size df 2m(n – 1)(m – 1) Powerhigherlower

Comparing Fixed and Mixed Effects Procedures (Randomized Block Design) Conditional and unconditional inference models estimate different treatment effects have different contaminating factors that add uncertainty Mixed procedures are good for unconditional inference The fixed procedures are good for conditional inference The fixed procedures have higher power

The Hierarchical Design The universe (the sampling frame) We wish to compare two treatments We assign treatments to whole schools Many schools with n students in each Assign all students in each school to the same treatment

The Hierarchical Design The experiment We wish to compare two treatments We assign treatments to whole schools Assign 2 m schools with n students in each Assign all students in each school to the same treatment

The Hierarchical Design Diagram of the experiment Schools Treatment12… m m +1m +2… 2m2m 1 2

The Hierarchical Design Treatment 1 schools Schools Treatment12… m m +1m + 2…2 m 1 2

The Hierarchical Design Treatment 2 schools Schools Treatment12… m m + 1m + 2…2 m 1 2

The Conceptual Model The statistical model for the observation on the k th person in the j th school in the i th treatment is Y ijk = μ + α i + β i + αβ ij + ε jk(i) = μ + α i + β j(i) + ε jk(i) μ is the grand mean, α i is the average effect of being in treatment i, β j is the average effect if being in school j, αβ ij is the difference between the average effect of treatment i and the effect of that treatment in school j, ε ijk is a residual Or β j(i) = β i + αβ ij is a term for the combined effect of schools within treatments

The Conceptual Model The statistical model for the observation on the k th person in the j th school in the i th treatment is Y ijk = μ + α i + β i + αβ ij + ε jk(i) = μ + α i + β j(i) + ε jk(i) μ is the grand mean, α i is the average effect of being in treatment i, β j is the average effect if being in school j, αβ ij is the difference between the average effect of treatment i and the effect of that treatment in school j, ε ijk is a residual or β j(i) = β i + αβ ij is a term for the combined effect of schools within treatments Context Effects

Two-level Hierarchical Design With No Covariates (HLM Notation) Level 1 (individual level) Y ijk = β 0j + ε ijk ε ~ N(0, σ W 2 ) Level 2 (school Level) β 0j = π 00 + π 01 T j + ξ 0j ξ ~ N(0, σ S 2 ) If we code the treatment T j = ½ or - ½, then π 00 = μ, π 01 = α 1, ξ 0j = β j(i) The intraclass correlation is ρ = σ S 2 /(σ S 2 + σ W 2 ) = σ S 2 /σ 2

Effects and Estimates The comparative treatment effect in any given school j is still (α 1 – α 2 ) + ( αβ 1j – αβ 2j ) But we cannot estimate the treatment effect in a single school because each school gets only one treatment The mean treatment effect in the experiment is (α 1 – α 2 ) + (β ● (1) – β ● (2) ) = (α 1 – α 2 ) +(β 1 ● – β 2 ● )+ ( αβ 1 ● – αβ 2 ● ) The estimate of the mean treatment effect in the experiment is (α 1 – α 2 ) + (β ● (1) – β ● (2) ) + ( ε 1 ●● – ε 2 ●● )

Inference Models Two different kinds of inferences about effects (as in the randomized block design) Unconditional Inference (schools random) Inference to the whole universe of schools (requires a representative sample of schools) Conditional Inference (schools fixed) Inference to the schools in the experiment (no sampling requirement on schools)

Unconditional Inference (Schools Random) The average treatment effect we want to estimate is (α 1 – α 2 ) The term ( ε 1 ●● – ε 2 ●● ) depends on the students in the schools in the sample The term (β ● (1) – β ● (2) ) depends on the schools in sample Both ( ε 1 ●● – ε 2 ●● ) and (β ● (1) – β ● (2) ) are random and average to 0 across students and schools, respectively

Conditional Inference (Schools Fixed) The average treatment effect we want to (can) estimate is (α 1 + β ●(1) ) – (α 2 + β ●(2) ) = (α 1 – α 2 ) + (β ●(1) – β ●(2) ) = (α 1 – α 2 ) + (β 1 ● – β 2 ● )+ (αβ 1 ● – αβ 2 ● ) The term (β ● (1) – β ● (2) ) depends on the schools in sample, but we want to estimate the effect of treatment in the schools in the sample Note that this treatment effect is not quite the same as in the randomized block design, where we estimate (α 1 – α 2 ) + (αβ 1 ● – αβ 2 ● )

Statistical Analysis Procedures Two kinds of statistical analysis procedures (as in the randomized block design) Mixed Effects Procedures Treat schools in the experiment as a sample from a universe Fixed Effects Procedures Treat schools in the experiment as a universe

Expected Mean Squares Hierarchical Design (Two Levels, Schools Random) Source df E{MS} Treatment (T) 1σ W 2 + nσ S 2 + nmΣα i 2 Schools (S) 2 ( m – 1 ) σ W 2 + nσ S 2 Within Schools 2m ( n – 1 ) σW2σW2

Mixed Effects Procedures (Schools Random) The test for treatment effects has H 0 : (α 1 – α 2 ) = 0 Estimated mean treatment effect in the experiment is (α 1 – α 2 ) + (β ● (1) – β ● (2) ) + ( ε 1 ●● – ε 2 ●● ) The variance of the estimated treatment effect is 2[σ W 2 + nσ S 2 ] /mn = 2[1 + (n – 1)ρ]σ 2 /mn where ρ = σ S 2 /(σ S 2 + σ W 2 ) = σ S 2 /σ 2

Mixed Effects Procedures (Schools Random) The test for treatment effects: F T = MS T /MS BS with (m – 2) df There is no omnibus test for context effects Power is determined by the operational effect size where ρ = σ S 2 /(σ S 2 + σ W 2 ) = σ S 2 /σ 2

Expected Mean Squares Hierarchical Design (Two Levels, Schools Fixed) Source df E{MS} Treatment (T) 1σ W 2 + nmΣ(α i + β ● (i) ) 2 Schools (S) m – 1 σ W 2 + nΣΣβ j (i) 2 /2(m – 1) Within Schools 2m ( n – 1 ) σW2σW2

Mixed Effects Procedures (Schools Fixed) The test for treatment effects has H 0 : (α 1 – α 2 ) + (β ●(1) – β ●(2) ) = 0 Note that the school effects are confounded with treatment effects Estimated mean treatment effect in the experiment is (α 1 – α 2 ) + (β ● (1) – β ● (2) ) + ( ε 1 ●● – ε 2 ●● ) The variance of the estimated treatment effect is 2σ W 2 /mn

Mixed Effects Procedures (Schools Fixed) The test for treatment effects: F T = MS T /MS WS with m(n – 1) df There is no omnibus test for context effects, because each school gets only one treatment Power is determined by the operational effect size and m(n – 1) df

Comparing Fixed and Mixed Effects Procedures (Hierarchical Design) FixedMixed Inference Model ConditionalUnconditional Estimand (α 1 – α 2 ) + (β ●(1) – β ●(2) )(α 1 – α 2 ) Contaminating Factors (ε 1●● – ε 2●● )(β ●(1) – β ●(2) ) + (ε 1●● – ε 2●● ) Effect Size df m(n – 1)(m – 2) Powerhigherlower

Comparing Fixed and Mixed Effects Statistical Procedures (Hierarchical Design) Conditional and unconditional inference models estimate different treatment effects have different contaminating factors that add uncertainty Mixed procedures are good for unconditional inference The fixed procedures are not generally recommended The fixed procedures have higher power

Comparing Hierarchical Designs to Randomized Block Designs Randomized block designs usually have higher power, but assignment of different treatments within schools or classes may be practically difficult politically infeasible theoretically impossible It may be methodologically unwise because of potential for Contamination or diffusion of treatments compensatory rivalry or demoralization

Comparing Hierarchical Designs to Randomized Block Designs But even when there is substantial contamination Chris Rhoads has shown that : even though randomized block designs underestimate the treatment effect randomized block designs can have higher power than hierarchical designs This is not widely known yet, but is important to remember

Applications to Experimental Design We will address the two most widely used experimental designs in education Randomized blocks designs with 2 levels Randomized blocks designs with 3 levels Hierarchical designs with 2 levels Hierarchical designs with 3 levels We also examine the effect of covariates Hereafter, we generally take schools to be random

Complications Which matchings do we have to take into account in design (e.g., schools, districts, regions, states, regions of the country, country)? Ignore some, control for effects of others as fixed blocking factors Justify this as part of the population definition For example, we define the inference population as these five districts within these two states But, doing so obviously constrains generalizability

Precision of the Estimated Treatment Effect Precision is the standard error of the estimated treatment effect Precision in simple (simple random sample) designs depends on: Standard deviation in the population σ Total sample size N The precision is

Precision of the Estimated Treatment Effect Precision in complex (clustered sample) designs depends on: The (total) standard deviation σ T Sample size at each level of sampling (e.g., m clusters, n individuals per cluster) Intraclass correlation structure It is a little harder to compute than in simple designs, but important because it helps you see what matters in design

Intraclass Correlations in Two-level Designs In two-level designs the intraclass correlation structure is determined by a single intraclass correlation This intraclass correlation is the proportion of the total variance that is between schools (clusters) Typical values of ρ are 0.1 to 0.25, so σ S 2 is typically 1/9 to 1/3 of σ W 2 but it has a big impact

Precision in Two-level Hierarchical Design With No Covariates The standard error of the treatment effect is SE decreases as m (number of schools) increases SE deceases as n increases, but only up to point SE increases as ρ increases

How Does Between-Cluster Variance Impact Precision? Think about the standard error again So even though σ S 2 is smaller than σ W 2, it has a bigger impact on the uncertainty of the treatment effect Suppose σ S 2 is 1/10 of σ S 2 (a pretty small value of ρ) if n = 30, σ S 2 will have 3 times as big an effect on the standard error as will σ W 2

Statistical Power Power in simple (simple random sample) designs depends on: Significance level Effect size Sample size Look power up in a table for sample size and effect size

Fragment of Cohen’s Table 2.3.5 d n0.100.20…0.801.001.201.40 80507…31466073 90607…35516579 100607…39567184 110607…43637687

Computing Statistical Power Power in complex (clustered sample) designs depends on: Significance level Effect size δ Sample size at each level of sampling (e.g., m clusters, n individuals per cluster) Intraclass correlation structure This makes it seem a lot harder to compute

Computing Statistical Power Computing statistical power in complex designs is only a little harder than computing it for simple designs Compute operational effect size (incorporates sample design information) Δ T Look power up in a table for operational sample size and operational effect size This is the same table that you use for simple designs

Power in Two-level Hierarchical Design With No Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the two-level hierarchical design with no covariates Operational sample size is number of schools (clusters)

Power in Two-level Hierarchical Design With No Covariates As m (number of schools) increases, power increases As effect size increases, power increases Other influences occur through the design effect As ρ increases the design effect (and power) decreases No matter how large n gets the maximum design effect is Thus power only increases up to some limit as n increases

Optimal Allocation in the Two-level Hierarchical Design Many different combinations of m and n give the same power or precision How should we choose? Optimal allocation gives some guidance Suppose cost per individual is c 1 and cost per school is c 2, so total cost is 2mc 2 + 2mnc 1 gives the optimal n (most precision with smallest cost)

Optimal Allocation in the Two-level Hierarchical Design The optimal sample size n is often much smaller than you might think For example, if ρ = 0.20 n O = 14 if c 2 = 50c 1 n O = 6 if c 2 = 10c 1 n O = 2 if c 2 = c 1 But remember that optimality is only one factor in choosing sample sizes Practicality and robustness of the sample (e.g., to attrition) are also important considerations

Two-level Hierarchical Design With Covariates (HLM Notation) Level 1 (individual level) Y ijk = β 0j + β 1j X ijk + ε ijk ε ~ N(0, σ AW 2 ) Level 2 (school Level) β 0j = π 00 + π 01 T j + π 02 W j + ξ 0j ξ ~ N(0, σ AS 2 ) β 1j = π 10 Note that the covariate effect β 1j = π 10 is a fixed effect If we code the treatment T j = ½ or - ½, then the parameters are identical to those in standard ANCOVA

Precision in Two-level Hierarchical Design With Covariates The standard error of the treatment effect SE decreases as m increases SE deceases as n increases, but only up to point SE increases as ρ increases SE decreases as R W 2 and R S 2 increase

Power in Two-level Hierarchical Design With Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the two-level hierarchical design with covariates The covariates increase the design effect

Power in Two-level Hierarchical Design With Covariates As m and effect size increase, power increases Other influences occur through the design effect As ρ increases the design effect (and power) decrease Now the maximum design effect as large n gets big is As the covariate-outcome correlations R W 2 and R S 2 increase, the design effect (and power) increases

Optimal Allocation in the Two-level Hierarchical Design With Covariates Optimal allocation can also be computed when there are covariates to give some guidance on cluster size ( n ) Suppose cost per individual is c 1 and cost per school is c 2, so total cost is 2mc 2 + 2mnc 1 Then the optimal cluster size gives the optimal n (most precision with smallest cost)

Three-level Hierarchical Design Here there are three factors Treatment Schools (clusters) nested in treatments Classes (subclusters) nested in schools Suppose there are m schools (clusters) per treatment p classes (subclusters) per school (cluster) n students (individuals) per class (subcluster)

Three-level Hierarchical Design With No Covariates The statistical model for the observation on the l th person in the k th class in the j th school in the i th treatment is Y ijkl = μ + α i + β j(i) + γ k(ij) + ε ijkl where μ is the grand mean, α i is the average effect of being in treatment i, β j(i) is the average effect of being in school j, in treatment i γ k(ij) is the average effect of being in class k in treatment i, in school j, ε ijkl is a residual

Three-level Hierarchical Design With No Covariates (HLM Notation) Level 1 (individual level) Y ijkl = β 0jk + ε ijkl ε ~ N(0, σ W 2 ) Level 2 (classroom level) β 0jk = γ 0j + η 0jk η ~ N(0, σ C 2 ) Level 3 (school Level) γ 0j = π 00 + π 01 T j + ξ 0j ξ ~ N(0, σ S 2 ) If we code the treatment T j = ½ or - ½, then π 00 = μ, π 01 = α 1, ξ 0j = γ k(ij), η 0jk = β j(i)

Three-level Hierarchical Design Intraclass Correlations In three-level designs there are two levels of clustering and two intraclass correlations At the school (cluster) level At the classroom (subcluster) level

Precision in Three-level Hierarchical Design With No Covariates The standard error of the treatment effect SE decreases as m increases SE deceases as p and n increase, but only up to point SE increases as ρ S and ρ C increase

Power in Three-level Hierarchical Design With No Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the three-level hierarchical design with no covariates The operational sample size is the number of schools

Power in Three-level Hierarchical Design With No Covariates As m and the effect size increase, power increases Other influences occur through the design effect As ρ S or ρ C increases the design effect decreases No matter how large n gets the maximum design effect is Thus power only increases up to some limit as n increases

Optimal Allocation in the Three-level Hierarchical Design With No Covariates Optimal allocation can also be computed in three level designs to give guidance on ( p and n ) Suppose cost per individual is c 1, the cost per class is c 2, and the cost per school is c 3, so total cost is 2mc 3 + 2mpc 2 + 2mpnc 1 Then the optimal sample sizes size (most precision with smallest cost) are And

Three-level Hierarchical Design With Covariates (HLM Notation) Level 1 (individual level) Y ijkl = β 0jk + β 1jk X ijkl + ε ijkl ε ~ N(0, σ AW 2 ) Level 2 (classroom level) β 0jk = γ 00j + γ 01j Z jk + η 0jk η ~ N(0, σ AC 2 ) β 1jk = γ 10j Level 3 (school Level) γ 00j = π 00 + π 01 T j + π 02 W j + ξ 0j ξ ~ N(0, σ AS 2 ) γ 01j = π 01 γ 10j = π 10 The covariate effects β 1jk = γ 10j = π 10 and γ 01j = π 01 are fixed

Precision in Three-level Hierarchical Design With Covariates SE decreases as m increases SE deceases as p and n increase, but only up to point SE increases as ρ S and ρ C increase SE decreases as R W 2, R C 2, and R S 2 increase

Power in Three-level Hierarchical Design With Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the three-level hierarchical design with covariates The operational sample size is the number of schools

Power in Three-level Hierarchical Design With Covariates As m and the effect size increase, power increases Other influences occur through the design effect As ρ S or ρ C increase the design effect decreases No matter how large n gets the maximum design effect is Thus power only increases up to some limit as n increases

Optimal Allocation in the Three-level Hierarchical Design With Covariates Optimal allocation can also be computed in three level designs to give guidance on ( p and n ) Suppose cost per individual is c 1, the cost per class is c 2, and the cost per school is c 3, so total cost is 2mc 3 + 2mpc 2 + 2mpnc 1 Then the optimal sample sizes size (most precision with smallest cost) are and.

Randomized Block Designs

Two-level Randomized Block Design With No Covariates (HLM Notation) Level 1 (individual level) Y ijk = β 0j + β 1j T ijk + ε ijk ε ~ N(0, σ W 2 ) Level 2 (school Level) β 0j = π 00 + ξ 0j ξ 0j ~ N(0, σ S 2 ) β 1j = π 10 + ξ 1j ξ 1j ~ N(0, σ T x S 2 ) If we code the treatment T ijk = ½ or - ½, then the parameters are identical to those in standard ANOVA

Randomized Block Designs In randomized block designs, as in hierarchical designs, the intraclass correlation has an impact on precision and power However, in randomized block designs designs there is also a parameter reflecting the degree of heterogeneity of treatment effects across schools We define this heterogeneity parameter ω S in terms of the amount of heterogeneity of treatment effects relative to the heterogeneity of school means Thus ω S = σ T x S 2 /σ S 2

Randomized Block Designs There are other ways to express this heterogeneity of treatment effect parameter For example, (random effects) meta-analyses may give you direct access to an estimate of the variance of effect sizes ( τ 2 ) A direct argument shows that which gives ω S in terms of τ 2

Precision in Two-level Randomized Block Design With No Covariates The standard error of the treatment effect SE decreases as m (number of schools) increases SE deceases as n and p increase, but only up to point SE increases as ρ increases SE increases as ω S = σ T x S 2 /σ S 2 increases

How Does Between-Cluster Variance Impact Precision? Think about the standard error again So even though σ T x S 2 is smaller than σ W 2, it has a bigger impact on the uncertainty of the treatment effect Suppose σ T x S 2 is 1/10 of σ W 2 (a pretty small value ) if n = 30, σ T x S 2 will have 3 times as big an effect on the standard error as will σ W 2

Power in Two-level Randomized Block Design With No Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the two-level randomized block design with no covariates Operational sample size is number of schools (clusters)

Precision in Two-level Randomized Block Design With Covariates The standard error of the treatment effect SE decreases as m increases SE deceases as n increases, but only up to point SE increases as ρ increases SE increases as ω S = σ T x S 2 /σ S 2 increases SE (generally) decreases as R W 2 and R TS 2 increase

Power in Two-level Randomized Block Design With Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the two-level randomized block design with covariates The covariates increase the design effect

Optimal Allocation in the Two-level Randomized Block Design Optimal allocation can also provide guidance on sample size allocation in randomized block designs Suppose cost per individual is c 1 and cost per school is c 2, so total cost is mc 2 + 2mnc 1 gives the optimal n (most precision with smallest cost)

Three-level Randomized Block Designs (Assigning Classes to Treatments)

We will only discuss the randomized block design that assigns classrooms to treatments within schools You could also assign individuals within classes to treatments That yields another randomized block design We will not discuss that design here

Three-level Randomized Block Design With No Covariates Here there are three factors Treatment Schools (clusters) crossed with treatments Classes (subclusters) nested in schools and treatments Suppose there are m schools (clusters) per treatment 2p classes (subclusters) per school (cluster) n students (individuals) per class (subcluster)

Three-level Randomized Block Design With No Covariates The statistical model for the observation on the l th person in the k th class in the i th treatment in the j th school is Y ijkl = μ +α i + β j + γ k(ij) + αβ ij + ε ijkl where μ is the grand mean, α i is the average effect of being in treatment i, β j is the average effect of being in school j, γ k(ij) is the effect of being in the k th class, αβ ij is the difference between the average effect of treatment i and the effect of that treatment in school j, ε ijkl is a residual

Three-level Randomized Block Design With No Covariates (HLM Notation) Level 1 (individual level) Y ijkl = β 0jk + ε ijkl ε ~ N(0, σ W 2 ) Level 2 (classroom level) β 0jk = γ 00j + γ 01j T j + η 0jk η ~ N(0, σ C 2 ) Level 3 (school Level) γ 00j = π 00 + ξ 0j ξ oj ~ N(0, σ S 2 ) γ 01j = π 10 + ξ 1j ξ 1j ~ N(0, σ T x S 2 ) If we code the treatment T j = ½ or - ½, then π 00 = μ, π 10 = α 1, ξ 0j = β j, ξ 1j = αβ ij, η 0jk = γ k(ij)

Three-level Randomized Block Design Intraclass Correlations In three-level designs there are two levels of clustering and two intraclass correlations At the school (cluster) level At the classroom (subcluster) level

Three-level Randomized Block Design Heterogeneity Parameters In three-level designs, as in two-level randomized block designs, there is also a parameter reflecting the degree of heterogeneity of treatment effects across schools We define this parameter ω S in terms of the amount of heterogeneity of treatment effects relative to the heterogeneity of school means (just like in two-level designs) Thus ω S = σ T x S 2 /σ S 2

Three-level Randomized Block Design Heterogeneity Parameters There are other ways to express this heterogeneity of treatment effect parameter For example, (random effects) meta-analyses of studies that assign classes to treatments may give you direct access to an estimate of the variance of effect sizes ( τ 2 ) A direct argument shows that in this design which gives ω S in terms of τ 2

Precision in Three-level Randomized Block Design With No Covariates The standard error of the treatment effect SE decreases as m increases SE deceases as p and n increase, but only up to point SE increases as ω S increases SE increases as ρ S and ρ C increase

Power in Three-level Randomized Block Design With No Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the three-level randomized block design with no covariates The operational sample size is the number of schools

Power in Three-level Randomized Block Design With No Covariates As m and the effect size increase, power increases Other influences occur through the design effect As ρ S or ρ C increases the design effect decreases No matter how large n gets the maximum design effect is Thus power only increases up to some limit as n increases

Power in Three-level Randomized Block Design With Covariates SE decreases as m increases SE deceases as p and n increases, but only up to point SE increases as ρ S, ρ C, and ω S increase SE decreases as R W 2, R C 2, and R TS 2 increase

Power in Three-level Randomized Block Design With Covariates Basic Idea: Operational Effect Size = (Effect Size) x (Design Effect) Δ T = δ x (Design Effect) For the three-level randomized block design with covariates The operational sample size is the number of schools

Power in Three-level Randomized Block Design With Covariates As m and the effect size increase, power increases Other influences occur through the design effect As ρ S or ρ C increases the design effect decreases No matter how large n gets the maximum design effect is Thus power only increases up to some limit as n increases

Optimal Allocation in the Three-level Randomized Block Designs With Covariates Optimal allocation can also be computed in three level randomized block designs to give guidance on ( p and n ) Suppose cost per individual is c 1, the cost per class is c 2, and the cost per school is c 3, so total cost is mc 3 + 2mpc 2 + 2mpnc 1 Then the optimal sample sizes size (most precision with smallest cost) are and.

What Unit Should Be Randomized? (Schools, Classrooms, or Students) Experiments cannot estimate the causal effect on any individual Experiments estimate average causal effects on the units that have been randomized If you randomize schools the (average) causal effects are effects on schools If you randomize classes, the (average) causal effects are on classes If you randomize individuals, the (average) causal effects estimated are on individuals

What Unit Should Be Randomized? (Schools, Classrooms, or Students) Theoretical Considerations Decide what level you care about, then randomize at that level Randomization at lower levels may impact generalizability of the causal inference (and it is generally a lot more trouble) Suppose you randomize classrooms, should you also randomly assign students to classes? It depends: Are you interested in the average causal effect of treatment on naturally occurring classes or on randomly assembled ones?

What Unit Should Be Randomized? (Schools, Classrooms, or Students) Relative power/precision of treatment effect Assign Schools (Hierarchical Design) Assign Classrooms (Randomized Block) Assign Students (Randomized Block)

What Unit Should Be Randomized? (Schools, Classrooms, or Students) Precision of estimates or statistical power dictate assigning the lowest level possible But the individual (or even classroom) level will not always be feasible or even theoretically desirable

Questions and Answers About Design

1.Is it ok to match my schools (or classes) before I randomize to decrease variation? 2.I assigned treatments to schools and am not using classes in the analysis. Do I have to take them into account in the design? 3.I am assigning schools, and using every class in the school. Do I have to include classes as a nested factor? 4.My schools all come from two districts, but I am randomly assigning the schools. Do I have to take district into account some way?

Questions and Answers About Design 1.I didn’t really sample the schools in my experiment (who does?). Do I still have to treat schools as random effects? 2.I didn’t really sample my schools, so what population can I generalize to anyway? 3. I am using a randomized block design with fixed effects. Do you really mean I can’t say anything about effects in schools that are not in the sample?

Questions and Answers About Design 1.We randomly assigned, but our assignment was corrupted by treatment switchers. What do we do? 2.We randomly assigned, but our assignment was corrupted by attrition. What do we do? 3.We randomly assigned but got a big imbalance on characteristics we care about (gender, race, language, SES). What do we do? 4.We randomly assigned but when we looked at the pretest scores, we see that we got a big imbalance (a “bad randomization”). What do we do?

Questions and Answers About Design 1.We care about treatment effects, but we really want to know about mechanism. How do we find out if implementation impacts treatment effects? 2.We want to know where (under what conditions) the treatment works. Can we analyze the relation between conditions and treatment effect to find this out? 3.We have a randomized block design and find heterogeneous treatment effects. What can we say about the main effect of treatment in the presence of interactions?

Questions and Answers About Design 1.I prefer to use regression and I know that regression and ANOVA are equivalent. Why do I need all this ANOVA stuff to design and analyze experiments? 2.Don’t robust standard errors in regression solve all these problems? 3.I have heard of using “school fixed effects” to analyze a randomized block design. Is the a good alternative to ANOVA or HLM? 4.Can I use school fixed effects in a hierarchical design?

Questions and Answers About Design 1.We want to use covariates to improve precision, but we find that they act somewhat differently in different groups (have different slopes). What do we do? 2.We get somewhat different variances in different groups. Should we use robust standard errors? 3.We get somewhat different answers with different analyses. What do we do?

Thank You !

Basic Experimental Design Larry V. Hedges Northwestern University Prepared for the IES Summer Research Training Institute July 26, 2010.

Similar presentations

Presentation on theme: "Basic Experimental Design Larry V. Hedges Northwestern University Prepared for the IES Summer Research Training Institute July 26, 2010."— Presentation transcript:

Similar presentations

About project

Feedback

Log in

Auth with social network:

Basic Experimental Design Larry V. Hedges Northwestern University Prepared for the IES Summer Research Training Institute July 26, 2010.

Similar presentations

Presentation on theme: "Basic Experimental Design Larry V. Hedges Northwestern University Prepared for the IES Summer Research Training Institute July 26, 2010."— Presentation transcript:

Similar presentations

About project

Feedback