r - 如何在R中实施条件（嵌套和嵌套）实验设计？(How to implement conditional (nest and corss) experimental design in R?)

Question

I am preparing a questionnaire to ask which transport mode do the respondents use in different conditions in terms of travel time, cost and other factors.

(我正在准备一份调查表，以询问受访者在旅行时间，成本和其他因素方面，在不同条件下使用哪种运输方式。)

There are three transport modes, two levels of travel time, three levels of travel cost and two levels of walk time as below:

(共有以下三种运输方式，两个旅行时间级别，三个旅行成本级别和两个旅行时间级别，如下所示：)

mode <- c(1:3)
time <- c(1:2)
cost <- c(1:3)
walk <- c(1:2)

I am now trying to reduce total number of conditions by experimental design, however, there are two issues for the implementation.

(我现在正在尝试通过实验设计来减少条件总数，但是，实现有两个问题。)

Design of questionnaire looks like this:

(问卷设计如下：)

Question:
Which transport mode do you use in the following conditions?
Please select one of transport from each combination.

Q1.1: which mode do you select?
mode time cost walk
1    1    1    -
2    1    1    -
3    1    1    1

Q1.2: which mode do you select?
mode time cost walk 
1    1    1    -
2    2    1    -
3    2    1    2

Q1.3: which mode do you select?
mode time cost walk 
1    2    1    -
2    1    2    -
3    1    1    2

Q1.4: which mode do you select?
mode time cost walk
1    1    3    -
2    2    3    -
3    1    1    1

I used oa.design() function from DoE.base package.

(我使用了DoE.base包中的oa.design()函数。)

It brings the result as below:

(结果如下：)

> oa.design(
+   factor.names=list(
+     mode=mode,time=time,cost=cost,walk=walk),
+     seed=1)
creating full factorial with 36 runs ...

   mode time cost walk
1     1    2    1    1
2     1    1    1    1
3     1    2    3    2
4     2    2    1    2
5     2    2    2    1
6     2    1    3    1
7     3    2    3    1
8     3    1    2    2
9     1    1    1    2
10    2    2    3    2
11    3    1    1    2
12    2    1    2    2
13    1    2    2    1
14    1    2    1    2
15    1    1    3    2
16    3    2    1    2
17    1    1    2    1
18    3    1    2    1
19    3    1    3    1
20    2    2    1    1
21    1    2    2    2
22    1    2    3    1
23    3    1    3    2
24    2    2    3    1
25    1    1    3    1
26    2    1    1    1
27    1    1    2    2
28    3    2    2    2
29    3    2    3    2
30    2    1    1    2
31    2    2    2    2
32    2    1    2    1
33    3    1    1    1
34    2    1    3    2
35    3    2    2    1
36    3    2    1    1
class=design, type= full factorial 

Firstly, though the questionnaire should contain all three transport modes for each combination (Q1.1, Q1.2 ... Q1.4), the result reduces transport mode as one of the factor.

(首先，尽管问卷应包含每种组合的所有三种运输方式（Q1.1，Q1.2 ... Q1.4），但结果减少了运输方式作为因素之一。)

Secondary, though a variable walk is only available for mode=2 , it cannot be taken into account by the package.

(次要的，尽管变量walk仅适用于mode=2 ，但软件包无法将其考虑在内。)

It is quite new for me to deal with experimental design and I am searching for appropriate information for my issue for one day, however I could not find it yet.

(对于我来说，处理实验设计是一个相当新的事物，并且我正在为一天的问题寻找适当的信息，但是我找不到它。)

It is highly appreciated if you could have any idea for appropriate implementation.

(如果您对适当的实现有任何想法，我们将不胜感激。)

  ask by Hideo.S translate from so

Answer 1

等待大神答复