❝

本文主要介绍空间计量及R操作（面板空间计量篇）

❞

本文主要介绍空间计量及R操作（面板空间计量篇）

❞

1、数据介绍

Produc

相关数据来源于：Munnell A (1990). “Why Has Productivity Growth Declined? Productivity and Public Investment.” New England Economic Review, 3–22.

原文已经下载并上传至计量经济学社群，可以免费进入查看！

US States Production

从1970年到1986年的48个观测截面的面板数据

数据格式：数据框

变量介绍：

state：the state

year：the year

region：the region

pcap：public capital stock

hwy：highway and streets

water：water and sewer facilities

util：other public buildings and structures

pc：private capital stock

gsp;gross state product

emp：labor input measured by the employment in non–agricultural payrolls

unemp：state unemployment rate

展开全文

Details:total number of observations : 816

observation : regional

country : United States

数据来源：

Online complements to Baltagi (2001):

http://www.wiley.com/legacy/wileychi/baltagi/

Online complements to Baltagi (2013):http://bcs.wiley.com/he-bcs/Books?action=resource&bcsId=4338&itemId=1118672321&resourceId=13452

参考文献：Baltagi B (2001). Econometric Analysis of Panel Data, 3rd edition. John Wiley and Sons ltd.

Baltagi B (2013). Econometric Analysis of Panel Data, 5th edition. John Wiley and Sons ltd.

Baltagi BH, Pinnoi N (1995). “Public capital stock and state productivity growth: further evidence from an error components model.” Empirical Economics, 20, 351-359.

Munnell A (1990). “Why Has Productivity Growth Declined? Productivity and Public Investment.” New England Economic Review, 3–22.

1、导入数据

2、查看数据

3、查看数据结构

4、导入查看空间权重矩阵及介绍

2、传统的面案数据分析

需要使用到的命令是plm，该函数表示：面板数据估计，面板数据的线性模型估计使用plm函数。

语法格式为：

选项含义表示：

2.1 传统的个体固定效应面板模型

代码为

Oneway (individual) effect Within Model

Call:plm(formula = df, data = Produc, effect = "individual", model = "within", index= c( "state", "year"))

Balanced Panel: n = 48, T = 17, N = 816

Residuals:Min. 1st Qu. Median 3rd Qu. Max. - 0. 1359569- 0. 0233995 - 0. 0033379 0. 0184788 0. 1844763

Coefficients:Estimate Std. Error t-value Pr(>|t|) log(pcap) - 0.088029 0. 027081 - 3.25060. 001202** log(pc) 0. 2324370. 02293 010.1369< 2.2e- 16*** log(emp) 0. 8577680. 02546633.6834< 2.2e- 16*** ---Signif. codes: 0‘***’ 0. 001‘**’ 0. 01‘*’ 0. 05‘.’ 0. 1‘ ’ 1

Total Sum of Squares: 18.941Residual Sum of Squares: 1.1529R-Squared: 0. 93913Adj. R-Squared: 0. 93515F-statistic: 3934.33on 3and765DF, p-value: < 2.22e- 16

2.2 传统的个体随机效应面板模型

代码为

结果为：

Call:plm(formula = df, data = Produc, effect = "individual", model = "random", index = c( "state", "year"))

Balanced Panel: n = 48, T = 17, N = 816

Effects:var std.dev shareidiosyncratic 0.001507 0.038822 0.184individual 0.006702 0.081863 0.816theta: 0.8857

Residuals:Min. 1st Qu. Median 3rd Qu. Max. -0.118735 -0.025222 -0.003688 0.021632 0.217416

Coefficients:Estimate Std. Error z-value Pr(>|z|) (Intercept) 2.611567 0.114880 22.7331 < 2e-16 ***log(pcap) -0.046151 0.022643 -2.0382 0.04153 * log(pc) 0.252960 0.018208 13.8926 < 2e-16 ***log(emp) 0.812907 0.022039 36.8854 < 2e-16 ***---Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Total Sum of Squares: 29.789Residual Sum of Squares: 1.261R-Squared: 0.95767Adj. R-Squared: 0.95751Chisq: 18370.4 on 3 DF, p-value: < 2.22e-16

3、空间面案数据分析

空间面板数据分析分为极大似然估计和广义矩估计，命令分别是spml和 spgm

spml语法格式为：

spgm语法格式为：

1、spgm操作案例

代码为

Call:spgm(formula = log(gsp) ~ log(pcap) + log(pc) + log(emp) + unemp, data = Produc, listw = usaww, spatial.error = TRUE, moments = "fullweights")

Residuals:Min. 1st Qu. Median 3rd Qu. Max. -0.1496836 -0.0174426 -0.0019014 0.0142554 0.1703041

Estimated spatial coefficient, variance components and theta:Estimaterho 0.499871sigma^2_v 0.001105

Coefficients:Estimate Std. Error t-value Pr(>|t|) log(pcap) 0.0043026 0.0253425 0.1698 0.86519 log(pc) 0.2144604 0.0232533 9.2228 < 2e-16 *** log(emp) 0.7830897 0.0279794 27.9881 < 2e-16 *** unemp -0.0025609 0.0010546 -2.4282 0.01517 * ---Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

2、极大似然估计的个体随机效应

代码为

Call: spreml(formula= formula, data = data, index = index, w = listw2mat(listw), w2= listw2mat(listw2), lag = lag, errors = errors, cl = cl)

Residuals: Min.1st Qu. Median Mean 3rd Qu. Max. -0.2477-0.0411 0.0123 0.0191 0.0727 0.4841

Errorvariance parameters:EstimateStd. Error t-value Pr(>|t|) phi7.53078 1.85638 4.0567 4.977e-05 ***rho0.53683 0.05603 9.5811 < 2.2e-16 ***

Spatialautoregressive coefficient:EstimateStd. Error t-value Pr(>|t|)lambda0.0018204 0.0400679 0.0454 0.9638

Coefficients: EstimateStd. Error t-value Pr(>|t|) (Intercept)2.3735772 0.1394744 17.0180 < 2.2e-16 ***log(pcap)0.0425017 0.0222146 1.9132 0.055719 . log(pc)0.2415075 0.0202970 11.8987 < 2.2e-16 ***log(emp)0.7419063 0.0244212 30.3796 < 2.2e-16 ***unemp-0.0034560 0.0010605 -3.2589 0.001118 ** ---Signif.codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

3、极大似然估计的个体固定效应

代码为

Call:spml(formula = df, data = Produc, index= c( "state", "year"), listw = mat2listw(usaww), model = "within", effect = "individual", lag = T, spatial.error = "b")

Residuals:Min. 1st Qu. Median 3rd Qu. Max. - 0. 1335552- 0. 0220919 - 0. 0032048 0. 0171787 0. 1748911

Spatial error parameter:Estimate Std. Error t-value Pr(>|t|) rho 0. 4553120. 042538 10.704< 2.2e- 16***

Spatial autoregressive coefficient:Estimate Std. Error t-value Pr(>|t|) lambda 0.088576 0. 0263123.36630. 0007618 ***

Coefficients:Estimate Std. Error t-value Pr(>|t|) log(pcap) - 0. 0103497 0. 0255345- 0. 40530. 6852log(pc) 0. 19057810. 0242829 7.84834.219e- 15*** log(emp) 0. 75523720. 0290385 26.0081< 2.2e- 16*** unemp - 0. 00306130. 0010315- 2.96780. 0030** ---Signif. codes: 0‘***’ 0. 001‘**’ 0. 01‘*’ 0. 05‘.’ 0. 1‘ ’ 1

>