主题:【原创】TFP浅解 -- 大雪满天
1.After taking the log, we are interpolating the series with the exponential function,which is different with the linear function. What we are estimating is the growth rate between the time interval. it is not a simple ratio relationship between the dependent variable and the independent variable. I think that is the economic meaning to do so.
You might miss the condition at the first beginning:
The most basic technique for doing this is to assume constant rates of change in all the variables (obscured by noise), and regress on the data to find the best estimate of these rates in the historical data available (using an Ordinary least squares regression). Economists always do this by first taking the natural log of their equation (to separate out the variables on the right-hand-side of the equation); logging both sides of this production function produces a simple linear regression with an error term,
2.From math point,to do so is NOT just because it is easy to obtain the simple regression.
The dependent variable is nonnegative,which violates the normal assumption of the linear regression, we can not directly use simple linear regression to estimate the relationship between the independent variable and dependent variable. Instead, we have to make the transformation to estimate the relationship between the independent variable and the change of the dependent variable, which can be either positive or negative. It is quite different.
- 相关回复 上下关系8
🙂【原创】TFP浅解 40 大雪满天 字5311 2009-03-24 08:34:11
🙂难道加了对数就改变量纲了? 思想的行者 字318 2010-06-27 18:19:57
🙂I can NOT agree wit you
🙂看不出你说的与LZ的有什么矛盾 frnkl 字14 2009-03-25 19:22:36
🙂I can NOT accept conclusion stpearl 字249 2009-03-25 20:45:38
🙂困惑 frnkl 字191 2009-03-25 20:56:46
🙂西西河还可以这样? 别来无样 字26 2009-03-25 08:11:56
🙂Wiki资料:TFP与Solow Residual的关系 2 frnkl 字2398 2009-03-24 13:44:32