Best Answer

There are many possible reasons. Here are some of the more common ones:

The underlying relationship is not be linear.

The regression has very poor predictive power (coefficient of regression close to zero).

The errors are not independent, identical, normally distributed.

Outliers distorting regression.

Calculation error.

Study guides

☆

Q: Why are your predictions inaccurate using a linear regression model?

Write your answer...

Submit

Still have questions?

Continue Learning about Statistics

Linear regression can be used in statistics in order to create a model out a dependable scalar value and an explanatory variable. Linear regression has applications in finance, economics and environmental science.

I want to develop a regression model for predicting YardsAllowed as a function of Takeaways, and I need to explain the statistical signifance of the model.

The value depends on the slope of the line.

One of the main reasons for doing so is to check that the assumptions of the errors being independent and identically distributed is true. If that is not the case then the simple linear regression is not an appropriate model.

When you use linear regression to model the data, there will typically be some amount of error between the predicted value as calculated from your model, and each data point. These differences are called "residuals". If those residuals appear to be essentially random noise (i.e. they resemble a normal (a.k.a. "Gaussian") distribution), then that offers support that your linear model is a good one for the data. However, if your errors are not normally distributed, then they are likely correlated in some way which indicates that your model is not adequately taking into consideration some factor in your data. It could mean that your data is non-linear and that linear regression is not the appropriate modeling technique.

Related questions

Linear regression can be used in statistics in order to create a model out a dependable scalar value and an explanatory variable. Linear regression has applications in finance, economics and environmental science.

I want to develop a regression model for predicting YardsAllowed as a function of Takeaways, and I need to explain the statistical signifance of the model.

Ridge regression is used in linear regression to deal with multicollinearity. It reduces the MSE of the model in exchange for introducing some bias.

The value depends on the slope of the line.

in general regression model the dependent variable is continuous and independent variable is discrete type. in genral regression model the variables are linearly related. in logistic regression model the response varaible must be categorical type. the relation ship between the response and explonatory variables is non-linear.

It could be any value

One of the main reasons for doing so is to check that the assumptions of the errors being independent and identically distributed is true. If that is not the case then the simple linear regression is not an appropriate model.

A correlation coefficient close to 0 makes a linear regression model unreasonable. Because If the correlation between the two variable is close to zero, we can not expect one variable explaining the variation in other variable.

George Portides has written: 'Robust regression with application to generalized linear model'

O. A. Sankoh has written: 'Influential observations in the linear regression model and Trenkler's iteration estimator' -- subject(s): Regression analysis, Estimation theory

+ Linear regression is a simple statistical process and so is easy to carry out. + Some non-linear relationships can be converted to linear relationships using simple transformations. - The error structure may not be suitable for regression (independent, identically distributed). - The regression model used may not be appropriate or an important variable may have been omitted. - The residual error may be too large.

You can conclude that there is not enough evidence to reject the null hypothesis. Or that your model was incorrectly specified. Consider the exact equation y = x2. A regression of y against x (for -a < x < a) will give a regression coefficient of 0. Not because there is no relationship between y and x but because the relationship is not linear: the model is wrong! Do a regression of y against x2 and you will get a perfect regression!

People also asked