This function estimates maximum likelihood models with any number of fixed-effects.

femlm( fml, data, family = c("poisson", "negbin", "logit", "gaussian"), vcov, start = 0, fixef, fixef.rm = "perfect", offset, subset, split, fsplit, cluster, se, ssc, panel.id, fixef.tol = 1e-05, fixef.iter = 10000, nthreads = getFixest_nthreads(), lean = FALSE, verbose = 0, warn = TRUE, notes = getFixest_notes(), theta.init, combine.quick, mem.clean = FALSE, only.env = FALSE, env, ... ) fenegbin( fml, data, vcov, theta.init, start = 0, fixef, fixef.rm = "perfect", offset, subset, split, fsplit, cluster, se, ssc, panel.id, fixef.tol = 1e-05, fixef.iter = 10000, nthreads = getFixest_nthreads(), lean = FALSE, verbose = 0, warn = TRUE, notes = getFixest_notes(), combine.quick, mem.clean = FALSE, only.env = FALSE, env, ... )

fml | A formula representing the relation to be estimated. For example: |
---|---|

data | A data.frame containing the necessary variables to run the model. The variables of the non-linear right hand side of the formula are identified with this |

family | Character scalar. It should provide the family. The possible values are "poisson" (Poisson model with log-link, the default), "negbin" (Negative Binomial model with log-link), "logit" (LOGIT model with log-link), "gaussian" (Gaussian model). |

vcov | Versatile argument to specify the VCOV. In general, it is either a character scalar equal to a VCOV type, either a formula of the form: |

start | Starting values for the coefficients. Can be: i) a numeric of length 1 (e.g. |

fixef | Character vector. The names of variables to be used as fixed-effects. These variables should contain the identifier of each observation (e.g., think of it as a panel identifier). Note that the recommended way to include fixed-effects is to insert them directly in the formula. |

fixef.rm | Can be equal to "perfect" (default), "singleton", "both" or "none". Controls which observations are to be removed. If "perfect", then observations having a fixed-effect with perfect fit (e.g. only 0 outcomes in Poisson estimations) will be removed. If "singleton", all observations for which a fixed-effect appears only once will be removed. The meaning of "both" and "none" is direct. |

offset | A formula or a numeric vector. An offset can be added to the estimation. If equal to a formula, it should be of the form (for example) |

subset | A vector (logical or numeric) or a one-sided formula. If provided, then the estimation will be performed only on the observations defined by this argument. |

split | A one sided formula representing a variable (eg |

fsplit | A one sided formula representing a variable (eg |

cluster | Tells how to cluster the standard-errors (if clustering is requested). Can be either a list of vectors, a character vector of variable names, a formula or an integer vector. Assume we want to perform 2-way clustering over |

se | Character scalar. Which kind of standard error should be computed: “standard”, “hetero”, “cluster”, “twoway”, “threeway” or “fourway”? By default if there are clusters in the estimation: |

ssc | An object of class |

panel.id | The panel identifiers. Can either be: i) a one sided formula (e.g. |

fixef.tol | Precision used to obtain the fixed-effects. Defaults to |

fixef.iter | Maximum number of iterations in fixed-effects algorithm (only in use for 2+ fixed-effects). Default is 10000. |

nthreads | The number of threads. Can be: a) an integer lower than, or equal to, the maximum number of threads; b) 0: meaning all available threads will be used; c) a number strictly between 0 and 1 which represents the fraction of all threads to use. The default is to use 50% of all threads. You can set permanently the number of threads used within this package using the function |

lean | Logical, default is |

verbose | Integer, default is 0. It represents the level of information that should be reported during the optimisation process. If |

warn | Logical, default is |

notes | Logical. By default, two notes are displayed: when NAs are removed (to show additional information) and when some observations are removed because of only 0 (or 0/1) outcomes in a fixed-effect setup (in Poisson/Neg. Bin./Logit models). To avoid displaying these messages, you can set |

theta.init | Positive numeric scalar. The starting value of the dispersion parameter if |

combine.quick | Logical. When you combine different variables to transform them into a single fixed-effects you can do e.g. |

mem.clean | Logical, default is |

only.env | (Advanced users.) Logical, default is |

env | (Advanced users.) A |

... | Not currently used. |

A `fixest`

object. Note that `fixest`

objects contain many elements and most of them are for internal use, they are presented here only for information. To access them, it is safer to use the user-level methods (e.g. `vcov.fixest`

, `resid.fixest`

, etc) or functions (like for instance `fitstat`

to access any fit statistic).

The number of observations.

The linear formula of the call.

The call of the function.

The method used to estimate the model.

The family used to estimate the model.

A list containing different parts of the formula. Always contain the linear formula. Then, if relevant: `fixef`

: the fixed-effects; `NL`

: the non linear part of the formula.

The number of parameters of the model.

The names of each fixed-effect dimension.

The list (of length the number of fixed-effects) of the fixed-effects identifiers for each observation.

The size of each fixed-effect (i.e. the number of unique identifierfor each fixed-effect dimension).

Logical, convergence status.

The convergence message from the optimization procedures.

(When relevant.) List containing vectors of integers. It represents the sequential selection of observation vis a vis the original data set.

(When relevant.) In the case there were fixed-effects and some observations were removed because of only 0/1 outcome within a fixed-effect, it gives the list (for each fixed-effect dimension) of the fixed-effect identifiers that were removed.

The named vector of estimated coefficients.

The table of the coefficients with their standard errors, z-values and p-values.

The log-likelihood.

Number of iterations of the algorithm.

Log-likelihood of the null model (i.e. with the intercept only).

Log-likelihood of the model with only the fixed-effects.

Sum of the squared residuals of the null model (containing only with the intercept).

The adjusted pseudo R2.

The fitted values are the expected value of the dependent variable for the fitted model: that is \(E(Y|X)\).

The residuals (y minus the fitted values).

Squared correlation between the dependent variable and the expected predictor (i.e. fitted.values) obtained by the estimation.

The Hessian of the parameters.

The variance-covariance matrix of the parameters.

The standard-error of the parameters.

The matrix of the scores (first derivative for each observation).

The difference between the dependent variable and the expected predictor.

The sum of the fixed-effects coefficients for each observation.

(When relevant.) The offset formula.

(When relevant.) The weights formula.

Note that the functions `feglm`

and `femlm`

provide the same results when using the same families but differ in that the latter is a direct maximum likelihood optimization (so the two can really have different convergence rates).

You can combine two variables to make it a new fixed-effect using `^`

. The syntax is as follows: `fe_1^fe_2`

. Here you created a new variable which is the combination of the two variables fe_1 and fe_2. This is identical to doing `paste0(fe_1, "_", fe_2)`

but more convenient.

Note that pasting is a costly operation, especially for large data sets. Thus, the internal algorithm uses a numerical trick which is fast, but the drawback is that the identity of each observation is lost (i.e. they are now equal to a meaningless number instead of being equal to `paste0(fe_1, "_", fe_2)`

). These “identities” are useful only if you're interested in the value of the fixed-effects (that you can extract with `fixef.fixest`

). If you're only interested in coefficients of the variables, it doesn't matter. Anyway, you can use `combine.quick = FALSE`

to tell the internal algorithm to use `paste`

instead of the numerical trick. By default, the numerical trick is performed only for large data sets.

To use leads/lags of variables in the estimation, you can: i) either provide the argument `panel.id`

, ii) either set your data set as a panel with the function `panel`

. Doing either of the two will give you acceess to the lagging functions `l`

, `f`

and `d`

.

You can provide several leads/lags/differences at once: e.g. if your formula is equal to `f(y) ~ l(x, -1:1)`

, it means that the dependent variable is equal to the lead of `y`

, and you will have as explanatory variables the lead of `x1`

, `x1`

and the lag of `x1`

. See the examples in function `l`

for more details.

You can interact a numeric variable with a "factor-like" variable by using `i(factor_var, continuous_var, ref)`

, where `continuous_var`

will be interacted with each value of `factor_var`

and the argument `ref`

is a value of `factor_var`

taken as a reference (optional).

Using this specific way to create interactions leads to a different display of the interacted values in `etable`

and offers a special representation of the interacted coefficients in the function `coefplot`

. See examples.

It is important to note that *if you do not care about the standard-errors of the interactions*, then you can add interactions in the fixed-effects part of the formula, it will be incomparably faster (using the syntax `factor_var[continuous_var]`

, as explained in the section “Varying slopes”).

The function `i`

has in fact more arguments, please see details in its associated help page.

Standard-errors can be computed in different ways, you can use the arguments `se`

and `ssc`

in `summary.fixest`

to define how to compute them. By default, in the presence of fixed-effects, standard-errors are automatically clustered.

The following vignette: On standard-errors describes in details how the standard-errors are computed in `fixest`

and how you can replicate standard-errors from other software.

You can use the functions `setFixest_vcov`

and `setFixest_ssc`

to permanently set the way the standard-errors are computed.

Multiple estimations can be performed at once, they just have to be specified in the formula. Multiple estimations yield a `fixest_multi`

object which is ‘kind of’ a list of all the results but includes specific methods to access the results in a handy way. Please have a look at the dedicated vignette: Multiple estimations.

To include multiple dependent variables, wrap them in `c()`

(`list()`

also works). For instance `fml = c(y1, y2) ~ x1`

would estimate the model `fml = y1 ~ x1`

and then the model `fml = y2 ~ x1`

.

To include multiple independent variables, you need to use the stepwise functions. There are 4 stepwise functions: `sw`

, `sw0`

, `csw`

, `csw0`

, and `mvsw`

. Of course `sw`

stands for stepwise, and `csw`

for cumulative stepwise. Finally `mvsw`

is a bit special, it stands for multiverse stepwise. Let's explain that.
Assume you have the following formula: `fml = y ~ x1 + sw(x2, x3)`

. The stepwise function `sw`

will estimate the following two models: `y ~ x1 + x2`

and `y ~ x1 + x3`

. That is, each element in `sw()`

is sequentially, and separately, added to the formula. Would have you used `sw0`

in lieu of `sw`

, then the model `y ~ x1`

would also have been estimated. The `0`

in the name means that the model without any stepwise element also needs to be estimated.
The prefix `c`

means cumulative: each stepwise element is added to the next. That is, `fml = y ~ x1 + csw(x2, x3)`

would lead to the following models `y ~ x1 + x2`

and `y ~ x1 + x2 + x3`

. The `0`

has the same meaning and would also lead to the model without the stepwise elements to be estimated: in other words, `fml = y ~ x1 + csw0(x2, x3)`

leads to the following three models: `y ~ x1`

, `y ~ x1 + x2`

and `y ~ x1 + x2 + x3`

.
Finally `mvsw`

will add, in a stepwise fashion all possible combinations of the variables in its arguments. For example `mvsw(x1, x2, x3)`

is equivalent to `sw0(x1, x2, x3, x1 + x2, x1 + x3, x2 + x3, x1 + x2 + x3)`

. The number of models to estimate grows at a factorial rate: so be cautious!

Multiple independent variables can be combined with multiple dependent variables, as in `fml = c(y1, y2) ~ cw(x1, x2, x3)`

which would lead to 6 estimations. Multiple estimations can also be combined to split samples (with the arguments `split`

, `fsplit`

).

You can also add fixed-effects in a stepwise fashion. Note that you cannot perform stepwise estimations on the IV part of the formula (`feols`

only).

If NAs are present in the sample, to avoid too many messages, only NA removal concerning the variables common to all estimations is reported.

A note on performance. The feature of multiple estimations has been highly optimized for `feols`

, in particular in the presence of fixed-effects. It is faster to estimate multiple models using the formula rather than with a loop. For non-`feols`

models using the formula is roughly similar to using a loop performance-wise.

When the data set has been set up globally using `setFixest_estimation`

`(data = data_set)`

, the argument `vcov`

can be used implicitly. This means that calls such as `feols(y ~ x, "HC1")`

, or `feols(y ~ x, ~id)`

, are valid: i) the data is automatically deduced from the global settings, and ii) the `vcov`

is deduced to be the second argument.

Although the argument 'data' is placed in second position, the data can be piped to the estimation functions. For example, with R >= 4.1, `mtcars |> feols(mpg ~ cyl)`

works as `feols(mpg ~ cyl, mtcars)`

.

To use multiple dependent variables in `fixest`

estimations, you need to include them in a vector: like in `c(y1, y2, y3)`

.

First, if names are stored in a vector, they can readily be inserted in a formula to perform multiple estimations using the dot square bracket operator. For instance if `my_lhs = c("y1", "y2")`

, calling `fixest`

with, say `feols(.[my_lhs] ~ x1, etc)`

is equivalent to using `feols(c(y1, y2) ~ x1, etc)`

. Beware that this is a special feature unique to the *left-hand-side* of `fixest`

estimations (the default behavior of the DSB operator is to aggregate with sums, see `xpd`

).

Second, you can use a regular expression to grep the left-hand-sides on the fly. When the `..("regex")`

feature is used naked on the LHS, the variables grepped are inserted into `c()`

. For example `..("Pe") ~ Sepal.Length, iris`

is equivalent to `c(Petal.Length, Petal.Width) ~ Sepal.Length, iris`

. Beware that this is a special feature unique to the *left-hand-side* of `fixest`

estimations (the default behavior of `..("regex")`

is to aggregate with sums, see `xpd`

).

In a formula, the dot square bracket (DSB) operator can: i) create manifold variables at once, or ii) capture values from the current environment and put them verbatim in the formula.

Say you want to include the variables `x1`

to `x3`

in your formula. You can use `xpd(y ~ x.[1:3])`

and you'll get `y ~ x1 + x2 + x3`

.

To summon values from the environment, simply put the variable in square brackets. For example: `for(i in 1:3) xpd(y.[i] ~ x)`

will create the formulas `y1 ~ x`

to `y3 ~ x`

depending on the value of `i`

.

You can include a full variable from the environment in the same way: `for(y in c("a", "b")) xpd(.[y] ~ x)`

will create the two formulas `a ~ x`

and `b ~ x`

.

The DSB can even be used within variable names, but then the variable must be nested in character form. For example `y ~ .["x.[1:2]_sq"]`

will create `y ~ x1_sq + x2_sq`

. Using the character form is important to avoid a formula parsing error. Double quotes must be used. Note that the character string that is nested will be parsed with the function `dsb`

, and thus it will return a vector.

By default, the DSB operator expands vectors into sums. You can add a comma, like in `.[, x]`

, to expand with commas--the content can then be used within functions. For instance: `c(x.[, 1:2])`

will create `c(x1, x2)`

(and *not* `c(x1 + x2)`

).

In all `fixest`

estimations, this special parsing is enabled, so you don't need to use `xpd`

.

You can even use multiple square brackets within a single variable, but then the use of nesting is required. For example, the following `xpd(y ~ .[".[letters[1:2]]_.[1:2]"])`

will create `y ~ a_1 + b_2`

. Remember that the nested character string is parsed with `dsb`

, which explains this behavior.

Berge, Laurent, 2018, "Efficient estimation of maximum likelihood models with multiple fixed-effects: the R package FENmlm." CREA Discussion Papers, 13 (https://wwwen.uni.lu/content/download/110162/1299525/file/2018_13).

For models with multiple fixed-effects:

Gaure, Simen, 2013, "OLS with multiple high dimensional category variables", Computational Statistics & Data Analysis 66 pp. 8--18

On the unconditionnal Negative Binomial model:

Allison, Paul D and Waterman, Richard P, 2002, "Fixed-Effects Negative Binomial Regression Models", Sociological Methodology 32(1) pp. 247--265

See also `summary.fixest`

to see the results with the appropriate standard-errors, `fixef.fixest`

to extract the fixed-effects coefficients, and the function `etable`

to visualize the results of multiple estimations.
And other estimation methods: `feols`

, `feglm`

, `fepois`

, `feNmlm`

.

Laurent Berge

# Load trade data data(trade) # We estimate the effect of distance on trade => we account for 3 fixed-effects # 1) Poisson estimation est_pois = femlm(Euros ~ log(dist_km) | Origin + Destination + Product, trade) # 2) Log-Log Gaussian estimation (with same FEs) est_gaus = update(est_pois, log(Euros+1) ~ ., family = "gaussian") # Comparison of the results using the function etable etable(est_pois, est_gaus) #> est_pois est_gaus #> Dependent Var.: Euros log(Euros+1) #> #> log(dist_km) -1.528*** (0.1156) -2.168*** (0.1542) #> Fixed-Effects: ------------------ ------------------ #> Origin Yes Yes #> Destination Yes Yes #> Product Yes Yes #> _______________ __________________ __________________ #> Family Poisson Gaussian #> S.E.: Clustered by: Origin by: Origin #> Observations 38,325 38,325 #> Squared Cor. 0.60377 0.70434 #> Pseudo R2 0.76039 0.23563 #> BIC 1.43e+12 152,008.4 #> --- #> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 # Now using two way clustered standard-errors etable(est_pois, est_gaus, se = "twoway") #> est_pois est_gaus #> Dependent Var.: Euros log(Euros+1) #> #> log(dist_km) -1.528*** (0.1307) -2.168*** (0.1712) #> Fixed-Effects: ------------------ ------------------ #> Origin Yes Yes #> Destination Yes Yes #> Product Yes Yes #> _______________ __________________ __________________ #> Family Poisson Gaussian #> S.E.: Clustered by: Orig. & Dest. by: Orig. & Dest. #> Observations 38,325 38,325 #> Squared Cor. 0.60377 0.70434 #> Pseudo R2 0.76039 0.23563 #> BIC 1.43e+12 152,008.4 #> --- #> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 # Comparing different types of standard errors sum_hetero = summary(est_pois, se = "hetero") sum_oneway = summary(est_pois, se = "cluster") sum_twoway = summary(est_pois, se = "twoway") sum_threeway = summary(est_pois, se = "threeway") etable(sum_hetero, sum_oneway, sum_twoway, sum_threeway) #> sum_hetero sum_oneway sum_twoway #> Dependent Var.: Euros Euros Euros #> #> log(dist_km) -1.528*** (0.0220) -1.528*** (0.1156) -1.528*** (0.1307) #> Fixed-Effects: ------------------ ------------------ ------------------ #> Origin Yes Yes Yes #> Destination Yes Yes Yes #> Product Yes Yes Yes #> _______________ __________________ __________________ __________________ #> S.E. type Heteroskedas.-rob. by: Origin by: Orig. & Dest. #> Observations 38,325 38,325 38,325 #> Squared Cor. 0.60377 0.60377 0.60377 #> Pseudo R2 0.76039 0.76039 0.76039 #> BIC 1.43e+12 1.43e+12 1.43e+12 #> #> sum_threeway #> Dependent Var.: Euros #> #> log(dist_km) -1.528*** (0.1340) #> Fixed-Effects: ------------------ #> Origin Yes #> Destination Yes #> Product Yes #> _______________ __________________ #> S.E. type by: Orig. & Dest. & Prod. #> Observations 38,325 #> Squared Cor. 0.60377 #> Pseudo R2 0.76039 #> BIC 1.43e+12 #> --- #> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 # # Multiple estimations: # # 6 estimations est_mult = femlm(c(Ozone, Solar.R) ~ Wind + Temp + csw0(Wind:Temp, Day), airquality) # We can display the results for the first lhs: etable(est_mult[lhs = 1]) #> model 1 model 2 model 3 #> Dependent Var.: Ozone Ozone Ozone #> #> (Intercept) 0.5334** (0.1943) 0.8890* (0.4430) 0.8028. (0.4441) #> Wind -0.0761*** (0.0052) -0.1151** (0.0439) -0.1152** (0.0440) #> Temp 0.0483*** (0.0020) 0.0441*** (0.0051) 0.0444*** (0.0051) #> Wind x Temp 0.0005 (0.0005) 0.0005 (0.0005) #> Day 0.0051*** (0.0015) #> _______________ ___________________ __________________ __________________ #> S.E. type IID IID IID #> Observations 116 116 116 #> Squared Cor. 0.62615 0.63129 0.63379 #> Pseudo R2 0.53377 0.53402 0.53759 #> BIC 1,564.7 1,568.7 1,561.5 #> --- #> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 # And now the second (access can be made by name) etable(est_mult[lhs = "Solar.R"]) #> model 1 model 2 model 3 #> Dependent Var.: Solar.R Solar.R Solar.R #> #> (Intercept) 3.777*** (0.0714) 4.343*** (0.1689) 4.529*** (0.1708) #> Wind 0.0119*** (0.0020) -0.0415** (0.0146) -0.0433** (0.0147) #> Temp 0.0169*** (0.0008) 0.0098*** (0.0021) 0.0088*** (0.0021) #> Wind x Temp 0.0007*** (0.0002) 0.0007*** (0.0002) #> Day -0.0061*** (0.0007) #> _______________ __________________ __________________ ___________________ #> S.E. type IID IID IID #> Observations 146 146 146 #> Squared Cor. 0.08076 0.08166 0.08983 #> Pseudo R2 0.06045 0.06207 0.07100 #> BIC 8,192.6 8,183.5 8,110.7 #> --- #> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 # Now we focus on the two last right hand sides # (note that .N can be used to specify the last item) etable(est_mult[rhs = 2:.N]) #> model 1 model 2 model 3 #> Dependent Var.: Ozone Solar.R Ozone #> #> (Intercept) 0.8890* (0.4430) 4.343*** (0.1689) 0.8028. (0.4441) #> Wind -0.1151** (0.0439) -0.0415** (0.0146) -0.1152** (0.0440) #> Temp 0.0441*** (0.0051) 0.0098*** (0.0021) 0.0444*** (0.0051) #> Wind x Temp 0.0005 (0.0005) 0.0007*** (0.0002) 0.0005 (0.0005) #> Day 0.0051*** (0.0015) #> _______________ __________________ __________________ __________________ #> S.E. type IID IID IID #> Observations 116 146 116 #> Squared Cor. 0.63129 0.08166 0.63379 #> Pseudo R2 0.53402 0.06207 0.53759 #> BIC 1,568.7 8,183.5 1,561.5 #> #> model 4 #> Dependent Var.: Solar.R #> #> (Intercept) 4.529*** (0.1708) #> Wind -0.0433** (0.0147) #> Temp 0.0088*** (0.0021) #> Wind x Temp 0.0007*** (0.0002) #> Day -0.0061*** (0.0007) #> _______________ ___________________ #> S.E. type IID #> Observations 146 #> Squared Cor. 0.08983 #> Pseudo R2 0.07100 #> BIC 8,110.7 #> --- #> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 # Combining with split est_split = fepois(c(Ozone, Solar.R) ~ sw(poly(Wind, 2), poly(Temp, 2)), airquality, split = ~ Month) # You can display everything at once with the print method est_split #> Standard-errors: IID #> #> #> # SAMPLE: 5 #> #> #> ### Dep. var.: Ozone #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.30403 0.042415 77.89732 < 2.2e-16 *** #> poly(Wind, 2)1 -6.41466 0.617300 -10.39149 < 2.2e-16 *** #> poly(Wind, 2)2 3.07584 0.570194 5.39437 6.8765e-08 *** #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 4.05816 0.109394 37.09674 < 2.2e-16 *** #> poly(Temp, 2)1 11.28467 1.448123 7.79261 6.5637e-15 *** #> poly(Temp, 2)2 2.50568 1.171805 2.13830 3.2492e-02 * #> #> ### Dep. var.: Solar.R #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.207784 0.018194 286.23787 < 2.2e-16 *** #> poly(Wind, 2)1 -0.569626 0.271696 -2.09656 3.6033e-02 * #> poly(Wind, 2)2 -1.834732 0.250895 -7.31274 2.6176e-13 *** #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.10262 0.052341 97.48802 < 2.2e-16 *** #> poly(Temp, 2)1 -2.63000 0.635659 -4.13744 3.512e-05 *** #> poly(Temp, 2)2 -5.59769 0.432368 -12.94657 < 2.2e-16 *** #> #> #> # SAMPLE: 6 #> #> #> ### Dep. var.: Ozone #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.07100 0.124756 24.61599 < 2.2e-16 *** #> poly(Wind, 2)1 6.09901 1.922777 3.17198 0.001514 ** #> poly(Wind, 2)2 -2.28442 1.031893 -2.21381 0.026842 * #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.41843 0.080824 42.29472 < 2.2e-16 *** #> poly(Temp, 2)1 3.26499 1.293450 2.52425 0.01159456 * #> poly(Temp, 2)2 5.66897 1.562592 3.62792 0.00028571 *** #> #> ### Dep. var.: Solar.R #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.218537 0.014191 367.74415 < 2.2e-16 *** #> poly(Wind, 2)1 2.220448 0.177688 12.49633 < 2.2e-16 *** #> poly(Wind, 2)2 -0.624761 0.139873 -4.46664 7.9458e-06 *** #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.200307 0.019697 264.014030 < 2.2e-16 *** #> poly(Temp, 2)1 3.286120 0.364969 9.003834 < 2.2e-16 *** #> poly(Temp, 2)2 0.155763 0.322767 0.482586 0.62939 #> #> #> # SAMPLE: 7 #> #> #> ### Dep. var.: Ozone #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.778200 0.043180 87.49820 < 2.2e-16 *** #> poly(Wind, 2)1 -6.722474 0.703358 -9.55768 < 2.2e-16 *** #> poly(Wind, 2)2 -0.959048 0.681576 -1.40710 0.1594 #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 2.59501 0.190413 13.62828 < 2.2e-16 *** #> poly(Temp, 2)1 24.89459 3.062021 8.13011 4.2888e-16 *** #> poly(Temp, 2)2 -8.57801 1.768706 -4.84988 1.2354e-06 *** #> #> ### Dep. var.: Solar.R #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.360516 0.014178 378.099115 < 2.2e-16 *** #> poly(Wind, 2)1 -0.682752 0.216716 -3.150439 0.0016303 ** #> poly(Wind, 2)2 0.013888 0.277451 0.050054 0.9600792 #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.10937 0.056186 90.93638 < 2.2e-16 *** #> poly(Temp, 2)1 4.82809 0.928155 5.20181 1.9735e-07 *** #> poly(Temp, 2)2 -1.11475 0.615860 -1.81007 7.0285e-02 . #> #> #> # SAMPLE: 8 #> #> #> ### Dep. var.: Ozone #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.755844 0.041522 90.453699 < 2.2e-16 *** #> poly(Wind, 2)1 -6.956477 0.697914 -9.967528 < 2.2e-16 *** #> poly(Wind, 2)2 -0.344133 0.486153 -0.707869 0.47903 #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.14340 0.097610 32.20355 < 2.2e-16 *** #> poly(Temp, 2)1 17.29925 1.746264 9.90643 < 2.2e-16 *** #> poly(Temp, 2)2 -5.78006 0.896709 -6.44586 1.1495e-10 *** #> #> ### Dep. var.: Solar.R #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.134474 0.016224 316.48225 < 2.2e-16 *** #> poly(Wind, 2)1 -0.459093 0.272152 -1.68690 0.0916227 . #> poly(Wind, 2)2 0.683835 0.246613 2.77291 0.0055558 ** #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 4.926595 0.041382 119.05115 < 2.2e-16 *** #> poly(Temp, 2)1 4.222008 0.816701 5.16959 2.3461e-07 *** #> poly(Temp, 2)2 -0.794082 0.462440 -1.71716 8.5950e-02 . #> #> #> # SAMPLE: 9 #> #> #> ### Dep. var.: Ozone #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.36418 0.036953 91.04039 < 2.2e-16 *** #> poly(Wind, 2)1 -4.04407 0.492839 -8.20566 2.2933e-16 *** #> poly(Wind, 2)2 2.98908 0.470324 6.35536 2.0794e-10 *** #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.36946 0.038292 87.99344 < 2.2e-16 *** #> poly(Temp, 2)1 6.10018 0.690949 8.82870 < 2.2e-16 *** #> poly(Temp, 2)2 2.25482 0.627045 3.59595 0.00032321 *** #> #> ### Dep. var.: Solar.R #> #> Expl. vars.: poly(Wind, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.122995 0.014639 349.966703 < 2.2e-16 *** #> poly(Wind, 2)1 -0.564257 0.193672 -2.913473 0.0035743 ** #> poly(Wind, 2)2 0.144413 0.224957 0.641955 0.5209022 #> --- #> Expl. vars.: poly(Temp, 2) #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 5.111358 0.015302 334.02914 < 2.2e-16 *** #> poly(Temp, 2)1 1.286054 0.251169 5.12026 3.0511e-07 *** #> poly(Temp, 2)2 -0.928769 0.260074 -3.57117 3.5539e-04 *** # Different way of displaying the results with "compact" summary(est_split, "compact") #> sample lhs rhs (Intercept) poly(Wind, 2)1 #> 1 5 Ozone poly(Wind, 2) 3.3*** (0.0424) -6.41*** (0.617) #> 2 5 Ozone poly(Temp, 2) 4.06*** (0.109) #> 3 5 Solar.R poly(Wind, 2) 5.21*** (0.0182) -0.57* (0.272) #> 4 5 Solar.R poly(Temp, 2) 5.1*** (0.0523) #> 5 6 Ozone poly(Wind, 2) 3.07*** (0.125) 6.1** (1.92) #> 6 6 Ozone poly(Temp, 2) 3.42*** (0.0808) #> 7 6 Solar.R poly(Wind, 2) 5.22*** (0.0142) 2.22*** (0.178) #> 8 6 Solar.R poly(Temp, 2) 5.2*** (0.0197) #> 9 7 Ozone poly(Wind, 2) 3.78*** (0.0432) -6.72*** (0.703) #> 10 7 Ozone poly(Temp, 2) 2.6*** (0.19) #> 11 7 Solar.R poly(Wind, 2) 5.36*** (0.0142) -0.683** (0.217) #> 12 7 Solar.R poly(Temp, 2) 5.11*** (0.0562) #> 13 8 Ozone poly(Wind, 2) 3.76*** (0.0415) -6.96*** (0.698) #> 14 8 Ozone poly(Temp, 2) 3.14*** (0.0976) #> 15 8 Solar.R poly(Wind, 2) 5.13*** (0.0162) -0.459. (0.272) #> 16 8 Solar.R poly(Temp, 2) 4.93*** (0.0414) #> 17 9 Ozone poly(Wind, 2) 3.36*** (0.037) -4.04*** (0.493) #> 18 9 Ozone poly(Temp, 2) 3.37*** (0.0383) #> 19 9 Solar.R poly(Wind, 2) 5.12*** (0.0146) -0.564** (0.194) #> 20 9 Solar.R poly(Temp, 2) 5.11*** (0.0153) #> poly(Wind, 2)2 poly(Temp, 2)1 poly(Temp, 2)2 #> 1 3.08*** (0.57) #> 2 11.3*** (1.45) 2.51* (1.17) #> 3 -1.83*** (0.251) #> 4 -2.63*** (0.636) -5.6*** (0.432) #> 5 -2.28* (1.03) #> 6 3.26* (1.29) 5.67*** (1.56) #> 7 -0.625*** (0.14) #> 8 3.29*** (0.365) 0.156 (0.323) #> 9 -0.959 (0.682) #> 10 24.9*** (3.06) -8.58*** (1.77) #> 11 0.0139 (0.277) #> 12 4.83*** (0.928) -1.11. (0.616) #> 13 -0.344 (0.486) #> 14 17.3*** (1.75) -5.78*** (0.897) #> 15 0.684** (0.247) #> 16 4.22*** (0.817) -0.794. (0.462) #> 17 2.99*** (0.47) #> 18 6.1*** (0.691) 2.25*** (0.627) #> 19 0.144 (0.225) #> 20 1.29*** (0.251) -0.929*** (0.26) # You can still select which sample/LHS/RHS to display est_split[sample = 1:2, lhs = 1, rhs = 1] #> Standard-errors: IID #> Dep. var.: Ozone #> Expl. vars.: poly(Wind, 2) #> Sample: 5 #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.30403 0.042415 77.89732 < 2.2e-16 *** #> poly(Wind, 2)1 -6.41466 0.617300 -10.39149 < 2.2e-16 *** #> poly(Wind, 2)2 3.07584 0.570194 5.39437 6.8765e-08 *** #> --- #> Sample: 6 #> Estimate Std. Error t value Pr(>|t|) #> (Intercept) 3.07100 0.124756 24.61599 < 2.2e-16 *** #> poly(Wind, 2)1 6.09901 1.922777 3.17198 0.001514 ** #> poly(Wind, 2)2 -2.28442 1.031893 -2.21381 0.026842 *