similar to: Subsetting Data

I'm trying to run a logit model and plot the probability curve for a number of the important predictors. I'm trying to do this with the Effects package. df=data.frame(income=c(5,5,3,3,6,5), won=c(0,0,1,1,1,0), age=c(18,18,23,50,19,39), home=c(0,0,1,0,0,1)) str(df) md1 = glm(factor(won) ~ income + age + home, data=df,

So I have the following data frame and I want to know how I can remove all "NA" values from each string, and also remove all "|" values from the START of the string. So they should something like "auto|insurance" or "auto|insurance|quote" one = data.frame(keyword=c("|auto", "NA|auto|insurance|quote", "NA|auto|insurance",

I have a logit model with about 10 predictors and I am trying to plot the probability curve for the model. Y=1 = 1 / 1+e^-z where z=B0 + B1X1 + ... + BnXi If the model had only one predictor, I know to do something like below. mod1 = glm(factor(won) ~ as.numeric(bid), data=mydat, family=binomial(link="logit")) all.x <- expand.grid(won=unique(won), bid=unique(bid)) y.hat.new

I'm working on a logistic regression in R with the car package but keep getting the following error message. It's only and warning and not an error, but I'm just not sure how to resolve the issues. glm.fit: algorithm did not converge glm.fit: fitted probabilities numerically 0 or 1 occurred d1 = data.frame(mwin=c(mwin), mbid=c(mbid)) m1 = zelig(mwin ~ mbid, data=d1,

I'm developing a naive bayes in R. I have the following data and am trying to predict on returned (class). dat = data.frame(home=c(0,1,1,0,0), gender=c("M","M","F","M","F"), returned=c(0,0,1,1,0)) str(dat) dat$home <- as.factor(dat$home) dat$returned <- as.factor(dat$returned) library(e1071) m <- naiveBayes(returned ~ ., dat) m

Lets say I have a linear model and I want to find the average expented value of the dependent variable. So let's assume that I'm studying the price I pay for coffee. Price = B0 + B1(weather) + B2(gender) + ... What I'm trying to find is the predicted price for every possible combination of values in the independent variables. So Expected price when: weather=1, gender=male weather=1,

I have the following variable, time, which is a character variable and it's structured as follows. > head(as.character(dat$time), 30) [1] "00:00:01" "00:00:16" "00:00:24" "00:00:25" "00:00:25" "00:00:40" "00:01:50" "00:01:54" "00:02:33" "00:02:43" "00:03:22" [12]

I have the following data and am trying to find the percentage of bid values purchased for that price. So let's say I have a bid of 5 and it's sold 2 times for $3 and $5. Since the original bid was $5, the percentage of times that that bid value results in a sold purchase AT that specific bid level was 1/3 because of the three time where the bid was three, it ended up being sold for $5

I'm running a linear model in R using the car package. I have a variable education, which i have recoded and regrouped to my wishes. However, R seems to place each element of that variable in alphabetical order. When I am running the model, don't I need the model order from lowest to highest to make an inference that a one unit change in one variable produced a one unit change in

I don't have a logistic regression model and am trying to generate probability curves for all possible combinations of the variables. My logit model has 5+ variables, and I want to draw curves for every scenario. See code below. When home_owner is 0 and 1, I want curves. The same goes for all other variables categories, so that I have permutations for all possible combinations. I've

I have a data frame with a column of values that I want to bucket (group) into specific levels. > str(dat)'data.frame': 3678 obs. of 39 variables: $ id : int 23 76 129 156 166 180 200 214 296 344 ... $ final_purchase_amount : Factor w/ 32 levels "\\N","1082","1109",..: 1 1 1 1 1 1 1 1 1 1 ... So I ran the following to

I'm running R in Ubuntu 10.10 and am trying to install the RODBC package. However, I get the following error message: ERROR: configuration failed for package ‘RODBC’ * removing ‘/home/amathew/R/i686-pc-linux-gnu-library/2.13/RODBC’ The downloaded packages are in ‘/tmp/RtmpekzPOQ/downloaded_packages’ Warning message: In install.packages() : installation of package 'RODBC' had

Hi folks, I have a simple question that I just can't solve. I'm trying to merge two columns in my data frame. > sessionInfo() R version 2.13.0 (2011-04-13) Platform: i686-pc-linux-gnu (32-bit) > head(dat) Year Month Number 2002 Jan 0 2002 Feb 0 2002 March 0 2002 April 1 2002 May 0 2002 June 0 I tried to do the following, but it

I'm trying to teach myself about Bayesian Networks and am working with the following data and the bnlearn package. I understand the conceptual aspects of BNs, but I'm not sure how to specify the response variables in R when constructing a dag plot. I've cecked ?hc and done numerous google searches without luck. Can anyone help? library("bnlearn")

I'm trying to calculate predicted probabilities in R with Zelig and keep getting the following error. Can anyone help? > x.low <- setx(mod, type=1)Error in dta[complete.cases(mf), names(dta) %in% vars, drop = FALSE] : incorrect number of dimensions When I ran the model, I ran everything but the explanatory variable as a numeric variable. Now, I'm trying everything and no

Let's say I have the following data frame and the date column has two different ways in which date is presented. How can I use as.Date or the lubridate package to have one date structure for the entire colum df = data.frame(Date=c("5/1/13","8/1/13","9/1/13","Apr-10", "Apr-11","Apr-12","Apr-13")) It's

Let's say I have a variable, day, which is saved as a factor with 7 levels, and I use it in a logistic regression model. I ran the model using the car package in R and printed out the results. mod1 = glm(factor(status1) ~ factor(day), data=mydat, family=binomial(link="logit")) print(summary(mod1)) The result I get is: Coefficients: Estimate Std. Error z value

I'm trying to run a function inside a function but get an error message. lst <- list(roots = c("car insurance", "auto insurance"), roots2 = c("insurance"), prefix = c("cheap", "budget"), prefix2 = c("low cost"), suffix = c("quote", "quotes"), suffix2 = c("rate", "rates"), suffix3 =

Let's say that I have a string and I want to know if a single word is present in the string. I've written the following function to see if the word "Geico" is mentioned in the string "Cheap Geico car insurance". However, it doesn't work, and I assume it has something to do with the any() function. Do I need to use regular expressions? (I hope not) main <-

I've been looking into the effects package and it seems to be a great tool for plotting the probabilities of the response variable by the predictors. However, I'm wonder if I can use the effects package to plot the probabilities on the y axis and one predictor on the x axis, with the curve having the info for another predictor. So let's say our response variable is win, a binary