# How to Fix in R: invalid type (list) for variable

One error you may encounter in R is:

```Error in model.frame.default(formula = y ~ x, drop.unused.levels = TRUE) :
invalid type (list) for variable 'x'
```

This error usually occurs when you attempt to fit a regression model or an ANOVA model in R and use a list for one of the variables instead of a vector.

This tutorial shares how to fix this error in practice.

## How to Reproduce the Error

Suppose I attempt to fit a simple linear regression model in R:

```#define variables
x <- list(1, 4, 4, 5, 7, 8, 9, 10, 13, 14)
y <- c(10, 13, 13, 14, 18, 20, 22, 24, 29, 31)

#attempt to fit regression model
model <- lm(y ~ x)

Error in model.frame.default(formula = y ~ x, drop.unused.levels = TRUE) :
invalid type (list) for variable 'x'
```

I receive an error because the lm() function can only take vectors as input and the x variable is currently a list.

## How to Avoid the Error

The easiest way to avoid this error is to simply use the unlist() function to convert the list variable to a vector:

```#define variables
x <- list(1, 4, 4, 5, 7, 8, 9, 10, 13, 14)
y <- c(10, 13, 13, 14, 18, 20, 22, 24, 29, 31)

#attempt to fit regression model
model <- lm(y ~ unlist(x))

#view the model output
summary(model)

Call:
lm(formula = y ~ unlist(x))

Residuals:
Min      1Q  Median      3Q     Max
-1.1282 -0.4194 -0.1087  0.2966  1.7068

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept)  6.58447    0.55413   11.88 2.31e-06 ***
unlist(x)    1.70874    0.06544   26.11 4.97e-09 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.8134 on 8 degrees of freedom
Multiple R-squared:  0.9884,	Adjusted R-squared:  0.987
F-statistic: 681.8 on 1 and 8 DF,  p-value: 4.97e-09
```

Notice that we’re able to fit the simple linear regression model without any errors this time because we used unlist() to convert variable x to a vector.

Note that if you’re fitting a multiple linear regression model and you have multiple predictor variables that are currently list objects, you can use unlist() to convert each of them to vectors before fitting the regression model:

```#define variables
x1 <- list(1, 4, 4, 5, 7, 8, 9, 10, 13, 14)
x2 <- list(20, 16, 16, 15, 16, 12, 10, 8, 8, 4)
y <- c(10, 13, 13, 14, 18, 20, 22, 24, 29, 31)

#fit multiple linear regression model
model <- lm(y ~ unlist(x1) + unlist(x2))

#view the model output
summary(model)

Call:
lm(formula = y ~ unlist(x1) + unlist(x2))

Residuals:
Min      1Q  Median      3Q     Max
-1.1579 -0.4211 -0.1386  0.3108  1.7130

Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept)  8.34282    4.44971   1.875 0.102932
unlist(x1)   1.61339    0.24899   6.480 0.000341 ***
unlist(x2)  -0.08346    0.20937  -0.399 0.702044
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.8599 on 7 degrees of freedom
Multiple R-squared:  0.9887,	Adjusted R-squared:  0.9854
F-statistic: 305.1 on 2 and 7 DF,  p-value: 1.553e-07```

Once again we don’t receive any errors since we converted each of the list objects to vectors.