Hi!

I am wondering how you present the results of non parametric regression test.

I run the nonparametric regression using R, and the package np

I get p- values but no df or t statistic.

For example

For the normal regression tests I did with other data, I presented the sample size, degrees of freedom, t statistic and the p value.

So how do I present the results of the above nonparametric test like the normal regression tests?

Any advice and input will be greatly appreciated!

Thanks!

I am wondering how you present the results of non parametric regression test.

I run the nonparametric regression using R, and the package np

I get p- values but no df or t statistic.

For example

> library(np)

> prop <- npreg(Respprop ~ Colony + Localden + Agg.prop, regtype = "ll",bwmethod = "cv.aic",gradients = TRUE, data = resp)

> summary(prop)

Regression Data: 176 training points, in 3 variable(s)

No. Complete Observations: 176

No. Incomplete (NA) Observations: 8

Observations omitted or excluded: 5 14 41 98 114 165 181 184

Colony Localden Agg.prop

Bandwidth(s): 1783119425 3.558041 0.4823368

Kernel Regression Estimator: Local-Linear

Bandwidth Type: Fixed

Residual standard error: 0.205017

R-squared: 0.2364211

Continuous Kernel Type: Second-Order Gaussian

No. Continuous Explanatory Vars.: 3

> npsigtest(prop)

Kernel Regression Significance Test

Type I Test with IID Bootstrap (399 replications, Pivot = TRUE, joint = FALSE)

Explanatory variables tested for significance:

Colony (1), Localden (2), Agg.prop (3)

Colony Localden Agg.prop

Bandwidth(s): 1783119425 3.558041 0.4823368

Individual Significance Tests

P Value:

Colony 0.69173

Localden < 2e-16 ***

Agg.prop < 2e-16 ***

> prop <- npreg(Respprop ~ Colony + Localden + Agg.prop, regtype = "ll",bwmethod = "cv.aic",gradients = TRUE, data = resp)

> summary(prop)

Regression Data: 176 training points, in 3 variable(s)

No. Complete Observations: 176

No. Incomplete (NA) Observations: 8

Observations omitted or excluded: 5 14 41 98 114 165 181 184

Colony Localden Agg.prop

Bandwidth(s): 1783119425 3.558041 0.4823368

Kernel Regression Estimator: Local-Linear

Bandwidth Type: Fixed

Residual standard error: 0.205017

R-squared: 0.2364211

Continuous Kernel Type: Second-Order Gaussian

No. Continuous Explanatory Vars.: 3

> npsigtest(prop)

Kernel Regression Significance Test

Type I Test with IID Bootstrap (399 replications, Pivot = TRUE, joint = FALSE)

Explanatory variables tested for significance:

Colony (1), Localden (2), Agg.prop (3)

Colony Localden Agg.prop

Bandwidth(s): 1783119425 3.558041 0.4823368

Individual Significance Tests

P Value:

Colony 0.69173

Localden < 2e-16 ***

Agg.prop < 2e-16 ***

For the normal regression tests I did with other data, I presented the sample size, degrees of freedom, t statistic and the p value.

So how do I present the results of the above nonparametric test like the normal regression tests?

Any advice and input will be greatly appreciated!

Thanks!

Last edited: