New answers tagged

2 votes

Within subject experiments done by (some) Psychologists

Talking about the definition of the term "experiment", I think it is fulfilled if they first have a research hypothesis, and then what they run is planned in such a way that they can control ...
Christian Hennig's user avatar
1 vote

Relative importance of equal sample size vs equal sample density

To determine what's optimum, a good way is to first identify a few key research questions. Then, do a power analysis to design a study that can answer those questions. The key takeaway is, what you're ...
Alex J's user avatar
  • 2,206
1 vote

Which statistical approach is best for diverse conversion rates in an A/B test?

Our goal is to introduce changes that maximize conversion rate as a whole across all types of stores. If this is your goal, then you do not need statistics like computation of significance. You just ...
Sextus Empiricus's user avatar
0 votes

Randomised Block Design

But in my particular example, there are multiple observations per cell. It makes me doubt if I am adopting the correct experimental design. Is it possible to have more than one observation per cell in ...
kjetil b halvorsen's user avatar
0 votes

Block-treatment interaction for Randomized Block Design (RCBD) and Generalized Random Block Design (GRBD)

I am surprised this is not answered on site so far (at least I cannot find it by search). We suppose balanced designs. First the unreplicated case, then the analysis is by a two-way anova. Let the ...
kjetil b halvorsen's user avatar
1 vote

2^3 Factorial design in Yates' notation

Since this is old now, we can do a full answer. A design matrix for the full $2^3$-design is below $$ \begin{pmatrix} 1 & 1 & 1 & abc \\ 1 & 1 & -1 &...
kjetil b halvorsen's user avatar
2 votes

Understanding "Multiplication/ Group Operation" in Fractional Experiments

It is true that there is a group structure underlying factorial and fractal factorial designs. It is explained in great detail in the Box, Hunter and Hunter book referenced at Do you have ...
kjetil b halvorsen's user avatar
0 votes

Does 'As Good As Random' Have a rigorous definition in identification strategies?

As good as random is a way to state that - although it did not occur as an actual lottery and cannot be described as a result of an actual random draw (such as can be conducted in randomized ...
Sara's user avatar
  • 1
2 votes

Double Blind Studies & Confounders

Adding to PBulls excellent answer: You can still add covariates/confounders to the analysis in a double blind RCT. It's true that, with random assignment to treatment/control (or more) the confounders ...
Peter Flom's user avatar
  • 120k
7 votes

Double Blind Studies & Confounders

You seem to be mixing a few things here. Unknown confounders are addressed thought randomization, because doing so properly guarantees (in the limit) that any characteristic that may be prognostic for ...
PBulls's user avatar
  • 4,513
-2 votes

Experimental design: What gives you more statistical power: Increasing number of sub samples or replicates?

Your real sample is the group. It is good to have a sufficient number of individuals in each group so that your proportion does actually represent something of course, but better increase Z. Edit ...
CaroZ's user avatar
  • 770

Top 50 recent answers are included