# measure of association

#### carlajosef

##### New Member
I want to explain more my problematic. I have a robot and i am clapping in order that the robot goes forward, back, left and right. The problem is that i am composing different patterns of clapping and the robot cannot know what i mean by a pattern but it knows at least that it should make a choice from 4 possibilities. Sometimes the robot is not moving and thus did not take the decision. So, I tried to calculate the number of times, the user makes a new pattern different from the previously composed one (exemple of patterns: 1 clap, 2 claps, 3 claps, 4 claps, multiple claps). I calculated meanwhile the numer of times the robot reponds and the number of times it ignores the pattern.
I am trying to verify whether there is relationship of association between the new clappings and the robot's responsitivity. The teacher told me that I have to use the chi-square and the Cramer V to evaluate the association. But I don 't see how can I create the contingency table. I was thinking of making categories of new clappings (1clap, 2 claps, 3 claps, 4 claps, multiple claps) and categories of responses (forward, back, left and right). Thus I will have a 4*4 contingency table.

Please tell me can i assume in this case that the Null hypothesis as follows:

H0: There is no relationship beween the new clapping and the response.
H1: There is a relationship between the new clapping and the response.

Please, as soon as possible if anybody have an idea about Cramer and can help me with this i ll be very grateful.