Experimental design, or design of experiments (DOE), is the design of any information-gathering exercises where variation is present. In statistics, controlled experiments are usually implied, which involve an "experimental group" and a "control group". In the design of experiments, the ...

learn more… | top users | synonyms (1)

0
votes
0answers
20 views

Regression discontinuity design with multiple cutoffs

When we have an RD with multiple cutoffs, and we pool all observations and estimate the treatment effect across cutoffs, what does the pooled estimate identify? I have found one paper using a RDD ...
1
vote
2answers
33 views

Can we use weights in lme as a covariable?

This question might be a duplicate, but a colleague and I have trouble understanding previous answers about the use of weights in lme. So in simple terms: We have an experimental design with 2 ...
0
votes
0answers
10 views

Terminology for comparing anwers to a set of reference questions

I´m conducting a questionnaire in order to examine the behavior of drivers of electric vehicles when providing information, such as parking time, to a charging station. For several reasons it is ...
1
vote
2answers
23 views

Using Kruskal Wallis vs One Way Anova with small sample size

I have an experiment with one factor and five levels. The response is proportion of conversion (ex: 1/11, 1/8...). Doing a power analysis: ...
0
votes
0answers
13 views

Pairwise Learning to Rank - detecting detrimental changes

The idea behind Pairwise Learning to Rank is that if you have a set of search results then a clicked on result can be used as training example to indicate that it should rank more highly that the ...
0
votes
0answers
18 views

Threshold for true experimental status?

This has been bugging me for a while now. I've read numerous sources but I can't really find a definitive answer. Most textbooks deal with generic designs but don't really address designs that ...
1
vote
0answers
25 views

User Study Setup: Correct selection of tasks

I'm struggling with the problem to design a formally correct user study. I have the following circumstances: I want users to assess the (subjective) usefulness of a -so called- trail result. That ...
0
votes
0answers
9 views

Finding redundant parts of a data set for training a nonlinear model

I like to train a nonlinear model based on a data set $D_1$,..$D_n$, where $D_i$ is collected by doing experiments $E_i$. It is possible that $D_i$ is redundant given $D_j$ and $D_k$. Since doing an ...
1
vote
0answers
64 views

Regression on unbalanced two-way with interaction

I am developing my own algorithm to calculate it for me. I am interested in type III SS and using the overparametrized design matrix to estimate my parameters vector and then proceed to the cubic ...
0
votes
0answers
20 views

Have I interpreted the effect of a confounding variable correctly?

I'm interested in whether feeding rate differ between two species of birds, Species A and Species B. However, tide also affects their feeding rate, and so tide is a confounding variable. In the plot ...
0
votes
0answers
8 views

Predicting individual treatment effects as the difference between predicted outcomes with and without treatment

To provide some context, I am trying to (a) identify the best ad to increase support for a particular issue among a large group of people, and (b) identify the people most likely to respond positively ...
1
vote
0answers
21 views

Assign the tree species most representitive of a specific size class

I am replicating another study in which trees were assigned to a class based on diameter. The most representative species of each class was identified for each plot sampled. The classes are sapling ...
0
votes
0answers
12 views

How to make Fractional Factorial designs with constraints?

I want to make a Fractional factorial plan of $2^{100}$ with the following additionnal constraint : $\sum_1^{500} I_{x_i=1} =5$ and $\sum_1^{500} I_{x_i=-1} =95$ ; where $x_i i=1,...,500$ are my two ...
2
votes
0answers
35 views

Are Latin hypercube samples uncorrelated

I understand the basics to Latin hypercube sampling, such as implemented by the algorithm LHSA mentioned in the book Design and Modeling for Computer Experiments. But I'd like to make sure: 1, n ...
0
votes
0answers
9 views

Need help setting up a model and running a test for significance

new poster here. I've taken very basic stats classes so I would like some help setting up a model testing the significance of an Act that was passed by the US gov't recently utilizing real data. ...
1
vote
0answers
14 views

How should you perform a manipulation check for multiple items that should belong to one of two groups?

Suppose I have 8 creatures that participants rate on my YuckFactor scale. I chose 4 cute animals to be part of a LowYuck group and 4 ugly bugs to be part of the HighYuck group. How can I test that ...
1
vote
0answers
38 views

Required sample size with unequal variances

I have a setup with equal sample sizes ($N_1=N_2$) from two groups (sample means $\mu_1$, $\mu_2$), but different variances $\sigma_1^2$, $\sigma_2^2$ in both groups. If the variances were equal, ...
0
votes
1answer
25 views

Residual vs fits for 2-level factorial design

So I'm analysing a 2-level factorial design, and get the residual vs fits plot below. I don't understand why it's symmetrical around 0. In any form of linear regression I've learned that the plot in ...
1
vote
1answer
23 views

Multiple pairwise comparison DOE

I'm going to conduct experiment with 7 products. One subject can evaluate no more than 3 products. The ultimate goal is to compare all 7 products to each other (let say, on means) and rank them. So, ...
0
votes
0answers
12 views

Interpretion of ANOVA with Nested Design

The following scenario is a basic nested design. I am trying to wrap my head around the interpretation of the ANOVA Table. Scenario: A school administrator is looking to investigate 5th grade ...
0
votes
0answers
14 views

Design of experiment - coding, method to analyze data

We have data from an experiment where there are two groups. They are both measured at time 0, before training and one of the group is trained the other is not. We measure some outcome variables ...
2
votes
1answer
22 views

Random Effect Model and Response Surface Methodology

In Design and analysis of experiment , Random effect is defined as : An experimenter is frequently interested in a factor that has a large number of possible levels. If the experimenters randomly ...
3
votes
1answer
39 views

Number of trials necessary to demonstrate Bernoulli process doesn't have mean p

I have a Bernoulli process that purportedly has mean $x$ but I hypothesize that the process actually has mean $q$. How many trials are necessary to demonstrate (to some confidence $p$) that the actual ...
0
votes
1answer
41 views

What kind of research design is this, is it even possible? If so, how to go about analyzing it?

This is for a psychology design. I have 2 groups, all members of both groups are to be administered all tests. I think that I want to do a 3x2 factorial ANOVA on the DIFFERENCES in the means of my ...
0
votes
0answers
34 views

Statistical Significance , which approach?

[editing original post to clarify my question] I have looked at some of the other posts on this but still can't grasp if these 2 are different approaches to determining somethings stat sig, or if ...
1
vote
0answers
23 views

Other options for a 2x2x2 RCT design that would require less participants

Alright, imagine the following: I would like to assess (the main effect & interplay of) three independent variables (i.e. A, B, and C) on a dependent variable Y. In addition, each independent ...
0
votes
0answers
22 views

Research Design Question

We have collected data from one group of students (post-only) where students went through two versions of online discussions (large group vs. small group) and then rated their overall experience in ...
3
votes
1answer
38 views

How to deal with subjects who cannot receive the treatment in an experiment?

Imagine an experiment where you are trying to establish that cell phone users who receive a a local offer tend to spend more. How do you deal with those in the test group that cannot receive the ...
0
votes
0answers
26 views

Different groups, same intervention. What design is this?

I'm trying to figure out the best way to analyse the following clinical trial: Group1: Healthy individuals Group2: Diseased individuals Both groups follow the same intervention and are tested pre- ...
0
votes
0answers
5 views

Matching two populations that have different disease status that have undergone the same intervention?

If there are two populations, D+ and D-, where D is disease state, and both populations have undergone an intervention I, what would be the best way to design that study? Given that this is ...
2
votes
1answer
40 views

Help with analyzing/planning a physical experiment — regression

This is a real experiment about to be performed Batches of samples will be prepared. A Striker will be used to see if a reaction will occur. For example: 20 drops might be performed, and number of ...
9
votes
1answer
130 views

Mixed-effect model design with a sampling variable

I am trying to specify a formula for a linear mixed effect model (with lme4) for my experimental design, but I'm not sure I'm doing it right. The design: basically ...
1
vote
0answers
54 views

Comparing distributions from a factorial design

I have the following experimental design: I have six animals, where three received treatment and the other three were used as control (so treatment and control animals are not paired). From each of ...
2
votes
1answer
65 views

Size of Tukey's 1 Degree of Freedom Test

In Oehlert (p. 218) the following algorithm for computing Tukey's one degree of freedom test for non-additivity is suggested: Fit a preliminary model; this will usually be an additive model. ...
0
votes
2answers
41 views

How to test for a synergistic effect of A & B with proportions of treatment effects, if I don't have the full 2x2 table?

I currently have a 2x2 table of proportions for treatment effects that looks like: \begin{array}{lll} & \text{Treatment } A & \text{Without Treatment } A \\ ...
0
votes
0answers
26 views

Cyclic Block Design with multivariate adaptive regression splines

I came upon a question of a linear block design for reviewing an article. The experimental design looked as follows: Material of different compostion (9 different combinations) was incubated in a ...
1
vote
0answers
30 views

Why would one not stratify random assignments in a controlled trial?

With some frequency I read reports of randomized controlled trials where, despite the randomization, a baseline survey found significant between-group differences in important covariates. It seems to ...
1
vote
0answers
19 views

How to determine number of replicate in DOE mathematically?

Actually, almost all of agriculturist define the number of replicate in their design of experimentally is based on subjective approach like experience, field condition, and so on. Even we know that ...
1
vote
1answer
33 views

Strange two sample z test result in experiment

I performed an experiment on a virtual population wanting to see whether Vitamin C can positively affect performance on an IQ test. I gathered 80 people and grouped them into two groups of 40. ...
0
votes
0answers
4 views

Biology IRP Design Help

So for my biology final I need to design and test an experiment. The idea was to test for a significant difference in the cleanliness of my library's 2 computer stations (8 computers each) and quick ...
2
votes
6answers
141 views

How to prevent collinearity?

Ieno & Zuur 2015 describe a number of causes of collinearity among explanatory variables entered into a linear regression. One of these causes is what they call a 'data collection' cause. They ...
1
vote
1answer
78 views

Identification problems with a structural equation model of experimental data

I have performed an experiment in which I manipulated three factors and I would like to model latent variables that those factors affect and then estimate the effects of the latents on response ...
2
votes
1answer
30 views

Augmenting experiment design matrices

Consider a set of users (rows) where we are already testing several treatments (columns): $$\begin{pmatrix} E & U & E \\ U & E &E \\ \vdots & \vdots &\vdots \\ E & E ...
1
vote
0answers
18 views

Within Subjects Design question

I have 75 participants and each participant has an exam on 15 questions. These questions are words. Their answers are 0 and 1 (knownn-unknown). Then I have another variable, their fixation on those ...
2
votes
0answers
11 views

Can I use experimental data from one experiment in another?

I ran an experiment with a simple 2 x 2 factorial design. Subjects were high school students. Factor 1 = school (school 1, school 2). Factor 2 = group (treatment/control). N = 322, split quite ...
1
vote
1answer
51 views

When would you use an I-optimal design over a D-optimal design?

We were discussing in DOE designs that it was best for model development to us d-optimal designs to identify your design space. The common alternative would be an i-optimal design. When would it be ...
2
votes
1answer
81 views

How can I measure difference between non-parametric data with many zeros?

I'm comparing two groups of students by their course activity and I'm struggling a little to determine the best way to test for significant difference. The data is non-normal, and very prevalent with ...
0
votes
0answers
19 views

How do I calculate the sample size required for a crossover AB|BA study?

I would like to know whether it is feasible to conduct this study. We have a subset of people in facility A (n=1300 per year), of which a proportion of these present a condition (n=18). Similarly, we ...
0
votes
1answer
118 views

Misfitting of drift rate in Wiener model

In a binary-decision experiment, the accuracy and response time of some subjects were recorded. My goal is to fit a Wiener model to response time and accuracy data. The binary experiment has three ...
2
votes
1answer
92 views

Advantages of counterbalancing vs. randomizing stimuli

I'm designing an experiment, in which 40 participants answer 10 questions, 5 in condition $A$ and 5 in condition $B$, and I'm interested in the difference between the two conditions. It's not clear ...