a)
Therefore, the fitted response function is:
π^i=e^(β0+β1xi)/1+e^(β0+β1xi)
By plugging in β0 = -4.5 and β1 = 0.125, we get the response function:
π^i=e^(0.125xi−4.5)/1+e^(0.125xi−4.5)
Plot Logistic Regression xx <- with(data.17, seq(min(x), max(x), len = 200)) plot(y ~ x, data.17, pch = 19, col = "gray40", xlab = "The dollar increase in annual dues", ylab = "Fitted Value") lines(xx, predict(logit.17, data.frame(x = xx), type = "resp"), lwd = 2, col='blue') a= coef(logit.17)[1] b= coef(logit.17)[2] curve(exp(a+b*x)/(1+exp(a+b*x)), from = min(data.17$x), to = max(data.17$x), col='green',add=T) title("Scatter Plot with Logistic Mean Response Functions")
b)
cat("the estimated probability that association members will not renew their membership if \n the dues are increased by $4 is", predict(logit.17, type = "response",new data = list(x=4)))
the estimated probability that association members will not renew their membership if the dues are increased by $40 is 0.05487487
c)
The e^β1 is 1.133237, which means for every one dollar increase in the annual dues, the odds ratio of getting membership un-renewed (Y=1) versus renewed (Y=0) increase by 1.133237 times.
The board of directors of a professional association conducted a survey of 30 members to assess t...
If Possible, please use MiniTab to get answers! Full Data Set: Y X 0 30 1 30 0 30 0 31 0 32 0 33 1 34 0 35 0 35 1 35 1 36 0 37 0 38 1 39 0 40 1 40 1 40 0 41 1 42 1 43 1 44 0 45 1 45 1 45 0 46 1 47 1 48 0 49 1 50 1 50 0 55 1 55 1 60 0...