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
3 views

Clustering and power: increasing the n but not the number of clusters

I am designing an experimental study with N observations from M sampled clusters, where M << N. Half of the clusters will be assigned to treatment. I can spend more money to increase the number ...
0
votes
1answer
19 views

How do I control for changes in rating methods in this study?

I'm performing a study where subjects rate their perceived, subjective intensity of a stimulus presented to them at different magnitudes. To submit a rating, they click on on a logarithmic scale ...
3
votes
1answer
38 views

How do I know if my result is statistically significant?

I wanted to test the effectiveness of 3 different messages I sent to users(respondents) to take a survey. In total, I sent out 6000 messages (3 sets of 2000 users). For message A, I received a ...
0
votes
0answers
4 views

fractional desing and interpolation

Factorial design is an experimental design which help in determining the effects of the factors on the response. I would wonder whether there is a relation between factorial design (used for some ...
0
votes
0answers
6 views

How do I determine true preferences vs random?

Let's say I'm running a dating service. I want to determine if you can decide if you like someone from a profile description. I set up the experiment as follows: A user is presented with 4 ...
3
votes
0answers
27 views

Between-subject comparison contains paired data

This is a difficult question to search for, so I apologize if it's been addressed elsewhere. If I am interested in the effect that weather (sunny/rainy) has on dog running speed, and I have running ...
0
votes
0answers
26 views

How to use Taguchi method when doing online multivariate A/B testing?

I want to run a multivariate test on my website landing page. I have a click on subscribe KPI, and I want to test many different color / calls to action / positions on that button. I heard of ...
3
votes
1answer
39 views

Is it possible to determine how many effects I can estimate in a least squares problem just by looking at the correlation matrix?

I currently have a model matrix $X$ with $6$ columns, which is being used for a factorial design problem, with each column associated with an effect. The ultimate goal is to be able to estimate as ...
3
votes
1answer
19 views

Experimental design vs factorial design

During my study about experimental design, I detect from some examples that factorial design is a sub-step in an experimental design. However till now the idea seems not fully clear for me. What is ...
0
votes
0answers
24 views
+50

Main effects in Minitab

I have a multilevel factorial design. I use Minitab to study and analyze this design. One of the outcome of such study is the main effect plot. I get the following : As I am new to design of ...
0
votes
0answers
5 views

What is the two alternative forced choice paradigm

Can someone please help me, Is a two alternative forced choice paradigm (2AFC) an experimental design?
0
votes
0answers
10 views

Matching vs Stratifying

I have read that both methods are used, in absence of a pretest on the units of study, in order to get a treatment and control group as similar as possible. My book (Shadish, Cook, Campbell, ...
1
vote
0answers
13 views

Experimental desing when having continuous factors

I am studying about experimentla design. I understand some of its geenral steps. I still have a small question: Can we apply experimental design when having continuous factors ? What I mean by a ...
0
votes
0answers
23 views

Experimental designs

I am having trouble understanding factorial designs and whether mine falls into it. If I have two independent variables and one has 3 levels and the other has 7 levels, what kind of design is this? ...
1
vote
1answer
27 views

Experimental design definition

I am doing some research on how to analyse experimental data. During the last three weeks, I face the expression "experimental design", I try to google to understand this notion, and how it works. ...
0
votes
0answers
18 views

Multiple t-tests on group averages vs multi-level model

I did an experiment with N participants, each tested with 10 stimuli with type 1 and 2 variants. 10 instances of each stimulus. I want to see if response to item type 1 was significantly different ...
1
vote
1answer
21 views

Design matrix with intersec 0 or 1

I am constructing a model matrix for a repeated meassurments experiment with three individuals per group and three treatments per individual. ...
0
votes
0answers
10 views

Active independent variable

In a study, there are two independent variables - A and B. We only manipulate variable B. Do we count A as an independent variable in our analysis, even though it has not been manipulated?
1
vote
1answer
30 views

Difference Between ANOVA and factorial Design

I was wondering about the difference between ANOVA and factorial design ? I have applied the factorial design method for studying some models(in fact in is a model with three factors). I used ...
0
votes
0answers
6 views

Stratified sampling And ANOVA with blocking

Thank you for your reading and maybe your help. I am new in Experiment Design and ANOVA and I do apologize, I am pretty sur this is a stupid question just due to my ANOVA misunderstood. Study ...
0
votes
0answers
22 views

Why do needed sample sizes for ANCOVA versus OLS differ so much?

I am planning a study of the effect of an intervention on two groups. While computing the appropriate sample size (using GPower) for the study, I noticed that ANCOVA requires about 4x the sample as an ...
0
votes
0answers
14 views

Which statistical test (2 x 2 x 2 three way factorial design, splitted dependent variable)?

I have data collected via a survey and the study is a 2 x 2 x 2 between subject design. For the dependent variable I asked two questions so that it is a split DV = DV_1 + DV_2. My question is, which ...
4
votes
0answers
27 views

Learning Design of Experiments

I work helping analyze large amounts of sequence data and I am trying to learn more design of experiments. However, something that I have observed is that, even though design of experiments is very ...
0
votes
0answers
17 views

Research Design Strategy

The total number of participants in a study is 70. This sample is divided into two groups. Group A (35 participants) and Group B (35 participants). The purpose of the study is to investigate the ...
0
votes
0answers
16 views

number of questionnaires and sample size

Is there any correlation between number of questionnaires used in a study and the sample size in order to obtain accurate measurement?
3
votes
1answer
31 views

Maximize variance of a distribution subject to constraints

Suppose a random variable $X$ has a distribution with support on $[0,1]$, ${\rm Prob}\{ X\in[0,1]\}=1$. I want to maximize its variance subject to the contraint that $\mathbb{E}[X]=\mu\in[0,1]$. My ...
0
votes
0answers
14 views

How to determine the proper sample size and testing criteria range for an experiment design?

I am currently trying to design an experiment that will be testing how fast a conveyor is able to convey different size cases. The case sizes are based on 4 dimensions (LxWxH and Weight) and the case ...
2
votes
1answer
81 views

Error in the design of an experiment

Suppose that we have a population with a subpopulation that exhibits a certain characteristic. We are interested in the performance of a group of people from the population on a group test. The ...
0
votes
0answers
20 views

Determining hold out group size for purposes of verifying lift

I have the following scenario: We want to send out an email blast to existing members to promote an upsell. We are quite positive the email blast will increase the number of upsells, but we are ...
0
votes
2answers
48 views

If A/B test results are not significant, how does increasing sample size affect things?

If I run an A/B with the recommended sample size (using this for example), and at the end my results are not significant, what can be done at this point? If someone requests to continue running the ...
0
votes
0answers
9 views

Hypothesis test design taking into account follow-up segmentation studies

Suppose I want to have a simple test with one treatment group and one control group. Let's assume the treatment for the treatment group is increasing a quantity $X$ by $10\%$. I have two questions: ...
0
votes
1answer
30 views

Power calculation using simulation — should I use empirical distribution?

In most tutorials on power calculation using simulation (e.g. this example in R), the analyst simulates the outcome variable using some convenient distribution such as the normal distribution. It ...
0
votes
1answer
18 views

Should I use a Mixed ANOVA?

I am struggling on which type of ANOVA to use for my work, I will provide as many details below about the study design, at the moment I am thinking mixed ANOVA but im encountering some problems which ...
0
votes
0answers
14 views

Summary statistics for mean of proportions

I have data from 30 subjects, each subject performing 50 trials and making a binary choice (category A or category B). I want to know if overall the preference is for category A or category B. I ...
0
votes
0answers
16 views

evaluating an intervention against a predictive model

I have the following situation: a large sample of the population, based on which I build a predictive classification model, about a likelihood of a certain event to happen to certain persons in a ...
0
votes
1answer
33 views

Can fixed effects be “post-treament”?

I have located a natural experiment in a time series cross-sectional dataset, but I am unsure of whether or not to include unit-level fixed effects in my models. I have produced a toy example that ...
0
votes
0answers
9 views

Should I look at mean performance to choose the best mean performance?

I've tested $C$ configurations for a computing platform's performance, each with $M$ runtime measures $t_{c}^{(m)}$ for re-runs. There is a spread for each configuration, due to random reasons (e.g. ...
1
vote
0answers
17 views

Multiple regression model from factorial experiment

Given the following factorial experiment, how does one construct an 'equivalent' multiple regression model? This appeared in an exam and left me almost clueless. \begin{align*} \mu_{11} &= \mu + ...
2
votes
1answer
26 views

What tradeoffs are there between internal and external validity?

I was reading through an article about research design. The authors gave an example on the relation between internal and external validity which I thought might be an important area of consideration ...
4
votes
0answers
36 views

Handedness — Observational study vs. Experiment

Let's say your goal is to determine whether left handed people are more coordinated with their right hands than right handed people are with their left. You gather up 20 left-handed people and 20 ...
3
votes
1answer
45 views

Sampling and design problem

Suppose there are quite many (hundreds/thousands) variables, $X_1$,...,$X_m$, in a computer model, following some multivariate distribution. How can we get a sample of these variables that has good ...
0
votes
1answer
19 views

Automated calculation of a fractional factorial design with 9 factors

In my research I want to employ a choice experiment using factorial design. However, I struggle to derive a fractional design from the full factorial design. There are 9 factors on 2 levels, which ...
1
vote
0answers
43 views

Textbooks on Deriving Linear Randomization Theory Models (e.g., $Y_{ij} = \mu + \beta_i + \tau_j + \epsilon_{ij}$)

In the M.S.-level Statistics Methods class I am taking, I've learned about various linear models for experimental design. Take, for example, $$Y_{ij} = \mu + \beta_i + \tau_j + \epsilon_{ij}$$ for ...
0
votes
0answers
10 views

Blocked experiments where the treatment is on links of a network

Imagine you have $N$ subjects of which 2/3 men and 1/3 women. Your want to assign each agent $i$ to a partner $j$, then each formed pair $(i,j)$ should be assigned to a treatment and a control group. ...
0
votes
0answers
22 views

Full Factorial Experiment to figure out what drives website traffic, sanity check

So for my intro to statistics class assignment, I'm supposed to perform a full factorial experiment on a dataset that correlates Traffic, Keywords and a few other factors using multi-way anova and ...
1
vote
0answers
20 views

Optimize Number of Possible Choices in Survey Question

I'm interested in asking a survey question ("How did you hear about us?") to people that visit a website. I'd like to have it be multiple choice, but since there are many different sources (referral, ...
1
vote
1answer
24 views

Pseudoreplication

I am growing coral on two different structures. I want to compare whether one structure (a table) grows coral more quickly than the other one (a tree). Both structures hold 60 pieces of coral, so a ...
0
votes
0answers
13 views

Information (c) matrix of a randomised block design

For a randomised block design, the block size is equal to a number of treatments (say v). Taking the number of blocks to be equal to b, I got the values of c matrix as b(v-1)/v along the diagonals and ...
2
votes
2answers
135 views

mixed effects and lme4: Do I need nesting?

I am analyzing data from a field experiment, and I am interested in the effects of fauna and altitude (fixed). Altitude has two levels, and at each site I have 5 blocks for the three levels of fauna ...
0
votes
0answers
7 views

Comparing 2 treatment groups in a randomized experiment

Good morning, I am drafting a randomized experiment testing the effects of A. an increase in quantity of kcal assumed in meals B. an increase in the quality of meals (quality defined both in terms ...