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)

1
vote
1answer
27 views

Downsides of having a model with too many independent variables (factors)?

It is often tempting in experimental design to make distinctions of all sorts in the manipulated variables, and thus to end up with a lot of factors in one's model (e.g. a 3x2x2x2x2 ANOVA). The same ...
4
votes
3answers
81 views

Nonrandomized better performance

On the footnote of page 497 in Jaynes' "Probability Theory: The Logic of Science" he writes Of course, Fisher’s randomized planting methods – which we think to be not actually wrong, but ...
2
votes
1answer
33 views

Can we estimate a missing Y value from a three factor experiment?

In preparation for an examination I'm looking at some old questions, and I could use a little help with figuring out what to do here: In a three-factor experiment the researchers lost the results ...
0
votes
0answers
16 views

archive of statistical studies/ experiments [closed]

Where can I find a compilation of free pdf files that talks about different remarkable experiments? such as the marshmallow test, Russian Sleep experiment, anything that I can share to my students so ...
0
votes
0answers
16 views

Biased coin randomization with adjustments over time

Assume an experiment that was going to consider different randomization strategies to address different challenges. The experiment involves an experimental (active treatment) and control group (usual ...
0
votes
2answers
43 views

Response Surface Methodology (RSM) for A Mathematical Model

I would like to create a second order polynomial model using Response Surface Methodology (RSM) for a non-polynomial mathematical model. For example, I would like to represent $f(x)=x_1 + \sin(x_1x_2) ...
0
votes
0answers
15 views

A/B, C/D test (fractional factorial design/anova?)

WE are conducting a test on a website and tracking number of form fills + the number of calls (by using a unique number of each variation). We basically have two base designs with two variation on ...
0
votes
0answers
11 views

Splitting a Two Way Anova for detecting effects

My question regards a specific case, which is the following. Hope someone can provide me with a clear, not too elaborated/statistical explanation if possible. Thanks in advance. Given 2 independent ...
0
votes
0answers
20 views

Two Way ANOVA not meeting the assumptions, moving to One Way Anova

I have the following ANOVA problem. Hope someone can help, thanks in advance. I have a sample of 120 respondents, split in 4 equal groups (4 groups originating from the combination of gender: ...
2
votes
2answers
31 views

Identifying method by equation (Related to Factorial Fractional Design)

I'd like to know the name of the method in the picture below. It's the same category as full - and factorial fractional design. It's quite difficult to search the net for this equation - I've tried ...
1
vote
1answer
13 views

Should I measure and analyze two highly correlative dependent variables?

In a study, I have measured two dependent variables. They are closely correlated, both theoretically and mathematically (r = 0.9). As an example, think of body height and foot size as dependent ...
0
votes
0answers
9 views

2k factorial effect interpretation

Say if I run a 2k factorial experiment with 3 variables: A, B, & C. For variable A it is varied parametrically, e.g. "-" = old parts, "+" = new parts. If my main effect of A is negligible and ...
0
votes
0answers
20 views

Details on counterbalancing: crossover on two variables, unbalanced allocation participants/ sequences

I am looking at an experiment design, two-way factorial, counterbalancing aims at three nuisance variables: (i) subject (it is a within-subject design) (ii) period (order of treatments) (iii) test ...
1
vote
2answers
199 views

How to account for participants in a study design?

I have a conceptual problem. I want to find out if stress during the day leads to (stronger) teeth grinding (bruxism) at night. I have a number of participants. They will fill in a self-report ...
1
vote
0answers
36 views

Rule of thumb for exploratory data

I frequently perform 2k factorial design of experiments and fit the data to a linear regression to control/optimize processes in a manufacturing environment. I have noticed recently that a large ...
0
votes
0answers
11 views

Sampling based on the DV [duplicate]

Say someone runs an experiment where there is one treatment group and one control group, and the DV is binary. The full experiment leads to over a million observations (it's an online experiment). ...
1
vote
0answers
13 views

Would using the md5 for treatment assignment introduce any biases?

Disclaimer: I'm not sure if there's a better stackexchange for this, but since I consider experimental design an integral part of causal/statistical inference, I'm hoping this is an appropriate ...
0
votes
1answer
16 views

Coding factors with non-numeric settings

For my role as a TA I am assisting the instructor in developing curriculum based on DOE and statistics. We have a set of failure strengths (the output/dependent variable) for several glass rods. The ...
1
vote
1answer
25 views

R lsmeans in a model with two residuals (split-plot) [closed]

Let's assume the model: lm(VAR ~ A * B + (A : R), data) which produces this ANOVA: ...
0
votes
0answers
29 views

Standard Error of estimate of variance

I am not understanding how is the standard error of estimates of two-factor factorial random effect model calculated ? For example , In the book Design and Analysis of Experiments , by Douglas C. ...
0
votes
0answers
17 views

One corner point duplicate and two level full factorial design main effects calculation

I conducted a series of experiments corresponding to a full factorial design with 3 factors and two levels per factor. I entered the data in a software (minitab, not sure if relevant) the calculation ...
1
vote
0answers
55 views

Robust parameter design - modern methods?

I would really appreciate help regarding a project I've been given. First off, I'm an undergrad engineering student with no experience or training in statistics. I've been given a task to improve the ...
1
vote
0answers
17 views

Feedback on Experiment: bosses and meetings

As my context is rather specific, I'll try to write an analogy that sounds more natural and preserves all characteristics of the original problem. It goes like this: A certain company has around 2k ...
0
votes
0answers
9 views

Calculate mean and std dev from experiment - no formal params

I am a little lost on how to calculate mean and std dev from an experiment (simulation). I have run the simulation (10000 times) and it output a set of numbers (10000). Plotting a histogram, it gives ...
0
votes
0answers
25 views

Experimental design for high dimensional model

I am running a computer model with a lot of inputs ( > thousands). I am not familiar with this area, so may I ask for any instructions/directions on how to make design on such high dimensional space? ...
0
votes
0answers
26 views

How to find this conditional probability in sampling without replacement in this experiment?

My problem is the following: I have an urn with 10 different names. Consider a particular name (ex. John). I want to estimate: 1) the probability to extract John 2) the probability to extract John ...
0
votes
0answers
16 views

Measuring training effectiveness

I am measuring training effectiveness using a control and experiment group design. However, as it is a live project in an organization having an 'interest based' approach for training subscriptions, I ...
0
votes
0answers
24 views

Advantage of a pooled Repeated Measures ANOVA?

Study Design: 2 (time) x 2 (condition) repeated measures design DV: Physical activity (i.e. walking/cycling/running; all measured in units of seconds, meters, and amount of steps) IV's: Time, ...
0
votes
1answer
28 views

Can we make mediation analysis with ANOVA?

I conducted mixed ANCOVA for my research. However, I need to make a mediation analysis as well. I have no idea of converting a mixed ANCOVA with many control variables into a regression. Can't I do ...
0
votes
1answer
22 views

Two-way ANOVA doesn't detect differences between conditions in a specific group?

OK, so let's say we have independent variables Condition (A or B) and Race (1 or 2 or 3). Then say we have a dependent variable X. We can run a two-way ANOVA to find out if there's an effect due to ...
0
votes
1answer
44 views

Why do we ignore the main effects when the interactions are not significant in a three-way ANOVA?

I'm following an SPSS guide online, and the procedure is to first test for a three-way interaction. In my case there was no sig. three-way interaction. Then the procedure asks me to consider two-way ...
3
votes
2answers
125 views

Adjustable sample size in clinical trial

Most clinical trials I see have a fixed sample size. In some cases they have prior data that allows estimating the effect size and the variance or distribution of values, and calculate the sample ...
0
votes
1answer
68 views

How to analyze data once broken down into gender, race, etc

I have two conditions, Treatment A, and Treatment B. Participants are randomly assigned to a treatment at the outset. Then I run unpaired t-tests on the data to find any differences. BUT I am also ...
1
vote
1answer
59 views

1 and 2 sample t-tests for plants and soils question!

I have a good friend who has an experiment where he grows different kind of plants on various soils and measures the protein content and weight each week for 5 weeks. His goal is to determine which ...
0
votes
0answers
33 views

Post-hoc multi-level design analysis

I am developing a model to predict a dichotomous satisfaction measure on festival event participants. Events can last 1 to n days; and participants are grouped in parties of 1 to k party members who ...
1
vote
0answers
34 views

Why am I finding greater power with a coarser level of randomization?

I am working on a Monte Carlo power analysis for an experiment about the hiring of teachers in schools. We can randomize the treatment at the school level or at the applicant-school level. I was ...
4
votes
1answer
29 views

Why does randomising the order of measurements remove time as a confounding variable?

Say we're interested in the difference in x between Group1 and Group2. We might measure 50 samples from Group1 then 50 samples from Group2. If the accuracy or precision of our measurements change over ...
0
votes
0answers
6 views

Searching for a term for systematic, universal non-reporting in survey data

I am searching for a technical term to describe a situation I have run into my survey research and analyzing survey datasets. In experimental survey research, systematic under-reporting and ...
0
votes
0answers
31 views

Choosing the correct experimental design

So lets just say I conducted a chi-squared contingency analysis test (I did btw) on 40 separate fish. Each individual fish only went through one treatment trial, where they were subjected to ...
1
vote
0answers
17 views

Paired studies: possible drawbacks

I have a question regarding paired studies. We are doing a medical study, we have a whole lot of data on a few hundred people and our aim is to study if a different level in one substance is linked to ...
0
votes
0answers
33 views

BIBD or IBD or PBIBD

I use block design for discrete choice experiment. While Balanced incomplete block design(BIBD) is considered as gold standard for blocking in choice experiments. However this is not always possible ...
0
votes
0answers
25 views

Do two-way ANOVA data need to be strictly balanced?

I conducted an experiment of 2x2 between-subjects design. So there is four conditions with the two factors. However, after deleting the data that failed to pass manipulation check, the four conditions ...
0
votes
0answers
11 views

Ask about measure pretest posttest in different groups

My team members are going to have a blood donation campaign and we would like to see whether the campaign has significant social impact. A group of people will be randomly asked to answer a ...
1
vote
0answers
21 views

Help with repeated measures analysis in a complex design

I'm looking at a study measuring blood flow in the brain, there are 8 subjects in this study, with 18 measurements each. The measurements are done 6 at a time in three different time points ...
1
vote
0answers
55 views

Combinatorial Block Designs in Statistics

I am interested in description and references for how combinatorial designs (such as BIBD, Steiner triple systems etc.) are used in statistics (especially in designs of experiments and hypothesis ...
-1
votes
1answer
29 views

ANOVA table for 4-factor split-plot

Hopefully I can explain this clearly. Reference diagram below if needed. I'm planning a large field experiment that I think will have to be a split plot design. There are six sites (outlined in ...
0
votes
0answers
24 views

How to Analyze Categorical Data in a Repeated Measures Design?

First post. I've read through similar posts and no one's quite answered it already, so I thought I'd throw my hat in the ring. Here goes: I have a repeated-measures design planned proposes to ask a ...
2
votes
4answers
236 views

When does correlation matter when there is no theoretical relationship?

Summary: Correlations does not imply causation has became mainstream. I am interested in understanding what is required for the implication to actually take place. Detailed question: When I have a ...
0
votes
0answers
12 views

Quasi-experiment with naturally assembled collectives (classrooms): Propensity score matching or not?

I am planning on running a quasi-experiment (pre-test post-test non-equivalent groups design) that involves two treatment groups that are subjected to different treatments (X+ & X-) and one ...
0
votes
0answers
17 views

Why does a blocking design require balancing across blocking levels

Why does a blocking design require balancing across blocking levels, say the following design is valid: ...