To collect data on two categorical variables, construct two questions that you would ask consumers of your sporting goods store. (The two questions will become the two variables in which you would conduct a Chi-Square Test for Independence.)Construct a contingency table that you will use to store the results of the data collected. (Utilize the Tables tool to create this table in your response box. Look for the table icon which is located on the far left of all icons at the top of your response box.)What method of data collection will you utilize? In other words, how will you get consumers to answer these questions? Will this method create any possible sampling error or collection bias?

This test is utilized to decide whether two downright factors are autonomous or then again in case they are indeed identified with each other. Assuming two absolute factors are autonomous, the worth of one variable doesn't change the probability dissemination of the other.Similarly as with all earlier statistical tests we really want to characterize invalid and elective speculations. Additionally, as we have taken in, invalid speculation is the thing that is thought to be valid until we have proof to conflict with it. In this illustration, we are keen on exploring if two unmitigated factors are connected or related (i.e., subordinate). Thusly, until we have proof to propose that they are, we should expect that they are not. This is the inspiration driving the speculation for the Chi-square Test of Independence: Ho = In the population, the two clear-cut factors are free. Ha = In the population, the two clear-cut factors are dependent. The are multiple ways of expressing these theories. Rather than utilizing the words "free" and "ward", it might be said "there is no connection between the two straight out factors" versus "there is a connection between the two clear cut factors." Or "there is no relationship between the two downright factors" versus "there is a relationship between the two factors." The significant part is that the invalid theory alludes to the two categorical factors not being connected while the option is attempting to show that they are connected. for eg my first question will be : Q1: For a sporting goods store location is important : location is important for sporting goods store location is not important for sporting good store Q2: Quality Product Quality is important to sport a good store Quality is not important to sport a good store 2. let the sample size used in the table be 100. important not important total Q1 45 25 70 Q2 15 15 30 total 60 40 100 Let's focus on one cell, say Question 1 and Success with observed count 45. If we go back to our probability lesson, let Q1 denote the event and" I"denote the event '' "Important "Then P(Q1) = 45 + 25 / 100 = 0.7 and P(I) = 45+15 / 100 = 0.6 Review that assuming two occasions are independent, their convergence is the result of their separate probabilities. All in all, assuming Q1 and I are independent, P( Q1 ∩ I ) = P (Q1) P (I) =( 45+25/100) (45+15/100) = 0.45 If we considered counts rather than probabilities, we get the count by expanding the likelihood by the outright count. By the day's end. The expected count for cell with A = P (Q1) P(I) x (total count) =( (45+25)(45+15)/100*100 ) (100) =42 This is the count we would expect to check whether the two factors were free (for example expecting the invalid speculation is valid). Expected Cell Count The expected count for each cell in the null hypothesis is calculated as: E = ( row total ) ( column total ) / total sample size 3. The primary method of data collection I will Utilise be it more accurate than secondary data and servery should be conducted to collect the data with the help of the Questionnaire. if the sampling size must be bigger so the chances of error might be less and the sample should be collected from different populations so that it does not create any bias.