Can you explain why you are having trouble implementing it?

The most simplest model would be a simple linear regression model, but you stated you want to account for time. Please explain how you plan to account for time, as it will guide you in the model you want to use.

If you want to find the relation between two variable, simple linear regression will be enough. But this is not clear what is meant by 'over a certain amount of time'. Do you mean time is a variable here? If so, it is better to perform time series analysis.

Hi Everybody,

Thank you for responding. For additional context I have unemployment numbers and housing prices from 2011 to 2017 and i want to use a statistical model to see if there is a relationshio. I don't know if linear regression is the best staistcal model to apply.

The first thing you need to do is plot the data (Price vs. Unemployment), and see what the relationship looks like. It may be linear. It may be nonlinear but monotonic. Or it may be non-monotonic.

A simple linear model or Pearson correlation really only makes sense in the first case. In the second case, you could fit a nonlinear or polynomial model or use Spearman correlation. In the third case you could fit a nonlinear or polynomial model.

In reality, for this type of data, there is likely to be a lag between these two variables. Housing prices are thought to be a leading indicator. That is, they start to drop before the economy declines. Whereas unemployment is considered a lagging indicator. (See: https://www.moneycrashers.com/leading-lagging-economic-indicators/).

If you want to consider the relationship between these two variables seriously, you will need to take this lag into consideration (if it exists). You might explore time series models with lags and auto-correlation.

Thanks Salvatore S. Mangiafico I will look into the Spearman Correlation.

Prices are not in general show the linear regression. So if you want to study that you must go for non linear regression. Spearman correlation is preferred when data is qualitative and it also tend to linear regression as well as for quantitative data it is approximately similar to Karl Pearson Correlation Coefficient. If there is not the tendency of Linear regression then you must try correlation ratio.

Thanks Mritunjay Pal Singh I used both Spearman and Pearsons model.