In case of questions or problems, see your local TSP consultant or send a description of the problem and the associated TSP output to:

Size: px
Start display at page:

Download "In case of questions or problems, see your local TSP consultant or send a description of the problem and the associated TSP output to:"

Transcription

1 PROGRAM this copy licensed for use by: TSP/GiveWin 4.5 User #45AGT TSP Version 4.5 (10/02/00) TSP/GiveWin 10MB Copyright (C) 2000 TSP International ALL RIGHTS RESERVED 02/27/01 10:34AM In case of questions or problems, see your local TSP consultant or send a description of the problem and the associated TSP output to: TSP International P.O. Box 61015, Station A Palo Alto, CA USA COMMAND *************************************************************** 1 INPUT 'LOGIN.TSP' *; 1 options memory=8 ; 2 options crt limwarn=0 memory=10 ; 3 3? Do not suppress warnings or the smpl printing until you are 3? sure the job works, but it is helpful to reduce the amount of 3? printing at that point. 3 3 supres smpl ; 4 4? This dataset contains 10 years of data on ~1200 firms for 4? employment, sales, R&D (half are zeros), investment, debt, 4? capital, etc. The high tech sectors have been excluded 4? to reduce data storage. 4? Growth rate defined as the difference in log(employment), 4? annualized. 4 4 smpl ; 5 read (file="sgrowth.dta") ; 6 6? id firm id 6? year 4 digit year, between 1986 and ? sic 4 digit sic code 6? ind ~2 digit industry code 6? sales annual sales ($M) 6? emply employment (1000s) 6? invest investment ($M) 6? rnd R&D spending ($M) 6? cashfl cash flow ($M) 6? kstock knowledge stock ($M) 6? netcap net capital stock ($M) 6? debt long term debt ($M) 6? q Tobin's q 6 6? Renaming the variables from the stata file names. 6 6 sales = s ; 7 rnd = r ;

2 8 emply = e ; 9 invest = i ; 10 kstock = rstock ; 11 netcap = c_ ; 12 debt = b ; title 'Problem 1' ;? ==================== 14 msd (all) sales emply invest rnd cashfl kstock netcap debt q ; 15 hist year ; 16 drnd = rnd<.001 ; 17 dkstock = kstock< ; 18 msd drnd dkstock ; 19? Means by Year 19 do i=86 to 95 ; 20 select year=1900+i ; 21 msd sales emply invest rnd cashfl kstock netcap debt q ; 22 enddo ; 23 select 1 ; title 'Problem 2' ;? ==================== 25 loge = log(emply) ; 26 logesq = loge*loge ; 27 list zhet c loge logesq ; 28 28? Choose firms that are there in 1989, 1990 & ? Defining the sample of good observations good = year=1990 & id=id(+4) & id=id(-1) ; 29 select good ; 30 dloge4 = (loge(+4)-loge)/4 ;? One way to compute the growth rate. 31 gre4 = (emply(+4)-emply)/(emply*4) ;? Another way to compute it. 32 msd (corr,all) dloge4 gre4 ; 33 hist gre4 ; 34 good = good & gre4<1 ;? Trim outliers in the growth rate. 35 select ~good ;? Set the growth rate to missing 36 dloge4 ; gre4=@miss ;? if it is invalid (firm exited) select good ; 39 logel = loge(-1) ;? Make a lagged size variable 40 msd (corr,all) dloge4 gre4 loge logel ; 41 olsq (robust) dloge4 loge c ; 42 42? Results for regressing growth on size are similar to Hall (1987). 42? A doubling of employment size associated with growth rate that is 42? 0.5% lower. The standard error of the regression (in annual growth 42? rate terms) is approximately 12.5 percent. 42? The test statistics indicate that the disturbance may be hetero- 42? skedastic or non-normal, or both title 'Problem 3' ;? = 43 inst (robust,inst=(c,logel)) dloge4 loge c ; 44 44? As in Hall (1987), using an instrument for size makes very little 44? difference, so the negative size-growth relationship cannot be due 44? to serially uncorrelated measurement error (regression to the mean) title 'Problem 4' ;? = 45 select year=1990 ;? Sample is all firms in in94 = good ;? Indicator for survival to 1994 (use good data only). 47

3 47 olsq (robust) dloge4 c loge ; 48 probit (hcov=nbw) in94 c loge ; 49 lmhetp zhet ; 50 50? Estimated Mills ratio is stored by the previous Probit. 50 olsq (robust) dloge4 c ; 51 select in94 ;? Look at Mills Ratio for observed data 52 ; 53 53? Estimates of sigma1 and rho from the Heckman method. 53 select in94 ;? Ad hoc estimate of var(dep var) 54? based on obs which have low Mills 54? ratio correction. 54 msd ; 55 set sigma1 ; 56 frml ; 57 print sigma1 ; 58 analyz rho ; 59 59? Note that the implied rho is -.98 with a very large standard error 59? (conditional on the sigma1 estimate). 59? The value is consistent with anything between -1 and 1. 59? We will get better precision from ML, a more efficient method title 'Problem 5' ;? == 60 select year=1990 ; 61 sampsel (hcov=nbw,maxit=100,tol=.01) in94 c loge dloge4 c loge ; 62 62? The sample selection results reveal that there are two maxima: 62? 62? 1) similar to Hall (1987), with rho very small and insignificant, 62? and no effects on the other coefficients. 62? 2) similar to the Heckman estimate, with a very negative rho and 62? a corresponding effect on the size coefficient (this is the opposite 62? of what we might have expected - firms that survive unexpectedly 62? in spite of their size have a lower growth rate than predicted by 62? their size. This may imply that there are two types of firms - 62? stable (which both grow slowly and survive) and volatile - grow 62? more quickly but are more likely to exit ? The fact that there are two maxima probably explains why Hall's 62? results changed so much between Table III and IV/V ? Save parameter estimates for starting values in weighted version. 62 param d0 d1 b1 b0 sigma rho ; 63 d0 d1 b0 b1 sigma rho ; 64? Log of estimated variance of residuals. 64 logvar = log(@res*@res) ; 65 loge2 = loge*loge ; title 'Problem 6' ;? == select ~in94 ; 68 dloge4 = 0 ;? so the observations for missing growth are not 69? dropped from the estimation. 69 select year=1990 ; 70 frml xb b0+b1*loge; 71 frml zd d0+d1*loge; 72 frml nu1 (dloge4-xb)/sigma ; 73 eqsub nu1 xb ; 74 frml logleq logl = (1-in94)*lcnorm(-zd) + in94*[ -log(sigma) 74 + lnorm(nu1) + lcnorm( (zd+rho*nu1)/sqrt(1-rho*rho) ) ] ; 75 eqsub logleq nu1 zd ;

4 76 76 ml logleq ; title 'Problem 7' ;? == msd logvar ; 79 olsq logvar c loge loge2 ; 80 forcst logfit ; 81 su = sqrt(exp(logfit)) ; 82 msd (pair) su logfit ; 83 wloge = loge/su ; 84 wc = 1/su ; 85 probit (hcov=nbw) in94 wc wloge ; 86 lmhetp zhet ; 87 87? Use ML to do the weighted Probit - note the answer is the same 87? as the previous one frml hsprob in94*lcnorm(xb) + (1-in94)*lcnorm(-xb) ; 88 frml xb (b0 + b1*loge)/su ; 89 eqsub hsprob xb ; 90 param b0.005 b1.005 ; 91 genr xb fit ; 92 msd (all) fit in94 ; 93 ml (silent,hcov=nbw,maxit=100,tol=.01) hsprob ; 94 94? Additional variables for Table V; Clean on them. 94 logq = log(q) ; 95 rnda = rnd/netcap ; 96 inve = invest/emply ; 97 rnde = rnd/emply ; 98 good = rnda<1 & rnde<100 & inve<100 & abs(logq)<2.3 ; 99 lrnde = 0 ; 100 select ~drnd & year=1990 ; 101 lrnde = log(rnde) ; 102 select year=1990 ; 103 linve = log(inve) ; select good & year=1990 & ~miss(linve) ; 105 msd (all,pair) logq rnda linve lrnde drnd in94 dloge4 ; 106 probit (hcov=nbw) in94 c loge logq rnda ; 107 lmhetp zhet ; 108 olsq (robust) dloge4 c loge linve lrnde drnd ; sampsel (hcov=nbw,maxit=100,tol=.01) in94 c loge logq rnda 109 dloge4 c loge linve lrnde drnd ; ? Now do the weighted version dot dloge4 c loge logq rnda linve lrnde drnd ; 111 w. =./su ; 112 enddot ; 113 wt = 1/su**2 ; 114 probit (hcov=nbw) in94 wc wloge wlogq wrnda ; 115 lmhetp zhet ; ? Weighted Least Squares - two different ways to do it ; 116 olsq (weight=wt,robust) dloge4 c loge linve lrnde drnd ; 117 olsq (robust) wdloge4 wc wloge wlinve wlrnde wdrnd ; 118 sampsel (hcov=nbw,maxit=100,tol=.01) in94 wc wloge wlogq wrnda 118 wdloge4 wc wloge wlinve wlrnde wdrnd ; ? Estimates for the weighted version of this model are somewhat 119? different from those in Table V, but the basic results on size-

5 119? growth and the correlation of the two equations are the same. 119? One of the reasons the results may be different is that this 119? sample excludes fast-growing technology intensive firms, so that 119? R&D and investment do not have as great a predictive effet on 119? growth. 119 input lmhetp ; 119 Proc LMhetp Zs; 120? LM test for heterosedasticity of Probit model 120? Follows Godfrey, "Misspecification tests in Econometrics", p ? Input argument: Zs - list of variables for heteroskedasticity 120? function 120? Assumes no missing data, although gaps in smpl allowed. 120 title "Godfrey's LM Test for Heteroskedasticity in Probit Eq" ; 121 local Xs den yt xb phi tmp1 tmp2 tx_xs tx_zs; 122 list RHS variables from last Probit estimation 123 den = sqrt(@fit*(1-@fit)); 124 yt this is a divide by zero sometimes 125? but those observations would be automatically 125? dropped from the regression 125 forcst xb;? Fitted value for latent variable 126 phi = norm(xb); 127? transform X variables 127 list(prefix=tx_) tx_xs Xs; local tx_xs; 129 tmp1 = phi/den; 130 dot Xs; 131 tx_. =.*tmp1; 132 enddot; 133? transform Z variables 133 list(prefix=tz_) tx_zs Zs; local tx_zs; 135 tmp2 = -xb*tmp1; 136 dot Zs; 137 tz_. =.*tmp2; 138 enddot; 139 olsq(silent) yt tx_zs tx_xs; 140 set LMhet2 explained sum of squares 141 cdf(chisq,df=@ncid) LMhet2; 142 Endproc; EXECUTION ****************************************************************************** * Problem 1 ========= Number of Observations: SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q

6 SALES D D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Median 1st Qrt 3rd Qrt IQ Range SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q Line 14 (MSD ): 32.7 seconds. HISTOGRAM OF YEAR Number of observations: MINIMUM MAXIMUM * ********************* ********************************** ************************* ******************** ********************* **************************** ***************************************** ****************************** ****** MINIMUM MAXIMUM Number of Observations: DRND DKSTOCK DRND DKSTOCK Number of Observations: 1014

7 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Number of Observations: 1107 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Number of Observations: 1166 SALES EMPLY INVEST RND CASHFL

8 KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Number of Observations: 1126 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Number of Observations: 1101 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q

9 SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Number of Observations: 1106 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Number of Observations: 1141 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL

10 KSTOCK NETCAP D DEBT Q Number of Observations: 1199 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Number of Observations: 1150 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q

11 Number of Observations: 1035 SALES EMPLY INVEST RND CASHFL KSTOCK NETCAP DEBT Q SALES D EMPLY INVEST RND CASHFL KSTOCK NETCAP D DEBT Q Problem 2 ========= Number of Observations: 897 Results of Covariance procedure ========== DLOGE GRE DLOGE GRE Median 1st Qrt 3rd Qrt IQ Range DLOGE GRE DLOGE4 GRE4 DLOGE GRE Correlation Matrix HISTOGRAM OF GRE4 MINIMUM MAXIMUM

12 ***************************************** ** * * * * * * * * MINIMUM MAXIMUM Number of Observations: 888 Results of Covariance procedure ========== DLOGE GRE LOGE LOGEL DLOGE GRE LOGE LOGEL Median 1st Qrt 3rd Qrt IQ Range DLOGE GRE LOGE LOGEL Correlation Matrix DLOGE4 GRE4 LOGE LOGEL DLOGE GRE LOGE LOGEL Equation 1 ============ Method of estimation = Ordinary Least Squares Dependent variable: DLOGE4 Number of observations: 888 Mean of dep. var. = E-02 LM het. test = [.002] Std. dev. of dep. var. = Durbin-Watson = [<.333] Sum of squared residuals = Jarque-Bera test = [.000] Variance of residuals = Ramsey's RESET2 = [.398] Std. error of regression = F (zero slopes) = [.000]

13 R-squared = Schwarz B.I.C. = Adjusted R-squared = Log likelihood = Estimated Variable Coefficient Error t-statistic P-value LOGE E E [.001] C E E [.171] Errors are heteroskedastic-consistent (HCTYPE=2). Problem 3 ========= Dependent variable: DLOGE4 Endogenous variables: LOGE Included exogenous variables: C Excluded exogenous variables: LOGEL Number of observations: 888 Equation 2 ============ Method of estimation = Instrumental Variable Mean of dep. var. = E-02 R-squared = Std. dev. of dep. var. = Adjusted R-squared = Sum of squared residuals = Durbin-Watson = [<.326] Variance of residuals = E'PZ*E = 0. Std. error of regression = Estimated Variable Coefficient Error t-statistic P-value LOGE E E [.000] C E E [.147] Errors are heteroskedastic-consistent Problem 4 ========= Equation 3 ============ Method of estimation = Ordinary Least Squares Dependent variable: DLOGE4 Number of observations: 888 Mean of dep. var. = E-02 LM het. test = [.002] Std. dev. of dep. var. = Durbin-Watson = [<.333] Sum of squared residuals = Jarque-Bera test = [.000] Variance of residuals = Ramsey's RESET2 = [.398] Std. error of regression = F (zero slopes) = [.000] R-squared = Schwarz B.I.C. = Adjusted R-squared = Log likelihood = Estimated Variable Coefficient Error t-statistic P-value C E E [.171]

14 LOGE E E [.001] Errors are heteroskedastic-consistent (HCTYPE=2). Equation 4 ============ PROBIT ESTIMATION Working space used: 7741 STARTING VALUES C LOGE VALUE F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= E- 04 CONVERGENCE ACHIEVED AFTER 4 ITERATIONS 8 FUNCTION EVALUATIONS. Dependent variable: IN94 Number of observations = 1101 Scaled R-squared = Number of positive obs. = 888 LR (zero slopes) = [.000] Mean of dep. var. = Schwarz B.I.C. = Sum of squared residuals = Log likelihood = R-squared = Fraction of Correct Predictions = C [.000] LOGE [.000] Errors computed from (Newton) analytic second derivatives C [.000] LOGE [.000] Errors computed from (BHHH) covariance of analytic first derivatives C [.000] LOGE [.000] Errors computed from (Eicker-White) analytic first and second derivatives dp/dx 0 1 C LOGE

15 Godfrey's LM Test for Heteroskedasticity in Probit Eq =========== CHISQ(4) Test Statistic: , Upper tail area: Equation 6 ============ Method of estimation = Ordinary Least Squares Dependent variable: DLOGE4 Number of observations: 888 Mean of dep. var. = E-02 LM het. test = [.094] Std. dev. of dep. var. = Durbin-Watson = [<.362] Sum of squared residuals = Jarque-Bera test = [.000] Variance of residuals = Ramsey's RESET2 = [.550] Std. error of regression = F (zero slopes) = [.001] R-squared = Schwarz B.I.C. = Adjusted R-squared = Log likelihood = Estimated Variable Coefficient Error t-statistic P-value C [.410] LOGE [.493] Errors are heteroskedastic-consistent (HCTYPE=2). HISTOGRAM MINIMUM MAXIMUM ********************* ***************************************** ************************************* ************************* ************* ******** **** ** * * MINIMUM MAXIMUM SIGMA1 = Results of Parameter Analysis ======== RHO [.493]

16 Wald Test for the Hypothesis that the given set of Parameters are jointly zero: CHISQ(1) = ; P-value = F Test for the Hypothesis that the given set of Parameters are jointly zero: F(1,11128) = ; P-value = Constrained original coefficients ============ Estimated Variable Coefficient Error t-statistic P-value C E E [.116] LOGE E E [1.00] Problem 5 ========= Equation 7 ============ Sample Selection Estimation 204 function evaluations used for grid search on RHO. Working space used: STARTING VALUES C LOGE C LOGE VALUE SIGMA RHO VALUE F= FNEW= ISQZ= 0 STEP= CRIT= E- 01 F= FNEW= ISQZ= 0 STEP= CRIT= E- 02 F= FNEW= ISQZ= 0 STEP= CRIT= E- 05 CONVERGENCE ACHIEVED AFTER 3 ITERATIONS 6 FUNCTION EVALUATIONS. Working space used: F= FNEW= ISQZ= 0 STEP= CRIT= E- 01 F= FNEW= ISQZ= 0 STEP= CRIT= E- 04 F= FNEW= ISQZ= 0 STEP= CRIT= E- 08 CONVERGENCE ACHIEVED AFTER 3 ITERATIONS

17 12 FUNCTION EVALUATIONS. NOTE: multiple local minima for objective function # RHO -LogL Probit Dependent variable: IN94 Regression Dependent variable: DLOGE4 Number of observations = 1101 Schwarz B.I.C. = Number of positive obs. = 888 Log likelihood = Fraction of positive obs. = C [.000] LOGE [.000] C E [.000] LOGE E [.000] SIGMA E [.000] RHO [.000] Errors computed from (Newton) analytic second derivatives C [.000] LOGE [.000] C E [.000] LOGE E [.000] SIGMA E [.000] RHO [.000] Errors computed from (BHHH) covariance of analytic first derivatives C [.000] LOGE [.000] C E [.000] LOGE E [.000] SIGMA [.000] RHO [.000] Errors computed from (Eicker-White) analytic first and second derivatives dp/dx 0 1 C LOGE Problem 6 =========

18 MAXIMUM LIKELIHOOD ESTIMATION ======== EQUATION: LOGLEQ Working space used: 7273 STARTING VALUES D0 D1 B0 B1 VALUE SIGMA RHO VALUE F= FNEW= ISQZ= 0 STEP= CRIT= E- 11 CONVERGENCE ACHIEVED AFTER 1 ITERATIONS 2 FUNCTION EVALUATIONS. Number of observations = 1101 Log likelihood = Schwarz B.I.C. = D [.000] D [.000] B E [.000] B E [.000] SIGMA E [.000] RHO [.000] Errors computed from (BHHH) covariance of analytic first derivatives Problem 7 ========= Number of Observations: 888 LOGVAR LOGVAR Equation 8 ============ Method of estimation = Ordinary Least Squares

19 Dependent variable: LOGVAR Number of observations: 888 Mean of dep. var. = LM het. test = [.620] Std. dev. of dep. var. = Durbin-Watson = [<.312] Sum of squared residuals = Jarque-Bera test = [.000] Variance of residuals = Ramsey's RESET2 = [.082] Std. error of regression = F (zero slopes) = [.000] R-squared = Schwarz B.I.C. = Adjusted R-squared = Log likelihood = Estimated Variable Coefficient Error t-statistic P-value C [.000] LOGE [.000] LOGE [.050] Number of Observations: 1101 Num.Obs SU LOGFIT SU LOGFIT Equation 9 ============ PROBIT ESTIMATION Working space used: 7741 STARTING VALUES WC WLOGE VALUE F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= E- 03 F= FNEW= ISQZ= 0 STEP= CRIT= E- 10 CONVERGENCE ACHIEVED AFTER 5 ITERATIONS 10 FUNCTION EVALUATIONS. Dependent variable: IN94 Number of observations = 1101 Scaled R-squared = Number of positive obs. = 888 LR (zero slopes) = [.000] Mean of dep. var. = Schwarz B.I.C. = Sum of squared residuals = Log likelihood =

20 R-squared = Fraction of Correct Predictions = WC E [.000] WLOGE E E [.009] Errors computed from (Newton) analytic second derivatives WC E [.000] WLOGE E E [.005] Errors computed from (BHHH) covariance of analytic first derivatives WC E [.000] WLOGE E E [.015] Errors computed from (Eicker-White) analytic first and second derivatives dp/dx 0 1 WC WLOGE Godfrey's LM Test for Heteroskedasticity in Probit Eq =========== CHISQ(4) Test Statistic: , Upper tail area: Number of Observations: 1101 FIT IN FIT IN Median 1st Qrt 3rd Qrt IQ Range FIT IN

21 Number of Observations: 1065 Num.Obs LOGQ RNDA LINVE LRNDE DRND IN DLOGE Median LOGQ RNDA LINVE LRNDE DRND IN DLOGE st Qrt 3rd Qrt IQ Range LOGQ RNDA LINVE LRNDE DRND IN DLOGE Equation 11 ============ PROBIT ESTIMATION Working space used: STARTING VALUES C LOGE LOGQ RNDA VALUE F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= E- 04 F= FNEW= ISQZ= 0 STEP= CRIT= E- 11 CONVERGENCE ACHIEVED AFTER 5 ITERATIONS 10 FUNCTION EVALUATIONS. Dependent variable: IN94 Number of observations = 1065 Scaled R-squared = Number of positive obs. = 864 LR (zero slopes) = [.000] Mean of dep. var. = Schwarz B.I.C. = Sum of squared residuals = Log likelihood = R-squared =

22 Fraction of Correct Predictions = C [.000] LOGE [.000] LOGQ [.615] RNDA [.315] Errors computed from (Newton) analytic second derivatives C [.000] LOGE [.000] LOGQ [.632] RNDA [.333] Errors computed from (BHHH) covariance of analytic first derivatives C [.000] LOGE [.000] LOGQ [.598] RNDA [.300] Errors computed from (Eicker-White) analytic first and second derivatives dp/dx 0 1 C LOGE LOGQ RNDA Godfrey's LM Test for Heteroskedasticity in Probit Eq =========== CHISQ(7) Test Statistic: , Upper tail area: Equation 13 ============ Method of estimation = Ordinary Least Squares Dependent variable: DLOGE4 Number of observations: 1065 Mean of dep. var. = E-02 LM het. test = [.000] Std. dev. of dep. var. = Durbin-Watson = [<.583] Sum of squared residuals = Jarque-Bera test = [.000] Variance of residuals = Ramsey's RESET2 = [.034] Std. error of regression = F (zero slopes) = [.001] R-squared = Schwarz B.I.C. =

23 Adjusted R-squared = Log likelihood = Estimated Variable Coefficient Error t-statistic P-value C E [.087] LOGE E E [.004] LINVE E E [.157] LRNDE E E [.858] DRND E [.032] Errors are heteroskedastic-consistent (HCTYPE=2). Equation 14 ============ Sample Selection Estimation 238 function evaluations used for grid search on RHO. Working space used: STARTING VALUES C LOGE LOGQ RNDA VALUE C LOGE LINVE LRNDE VALUE DRND SIGMA RHO VALUE F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= E- 02 F= FNEW= ISQZ= 0 STEP= CRIT= E- 06 CONVERGENCE ACHIEVED AFTER 4 ITERATIONS 8 FUNCTION EVALUATIONS. Working space used: F= FNEW= ISQZ= 0 STEP= CRIT= E- 01 F= FNEW= ISQZ= 0 STEP= CRIT= E- 03 F= FNEW= ISQZ= 0 STEP= CRIT= E- 05 CONVERGENCE ACHIEVED AFTER 3 ITERATIONS 14 FUNCTION EVALUATIONS. NOTE: multiple local minima for objective function # RHO -LogL Probit Dependent variable: IN94

24 Regression Dependent variable: DLOGE4 Number of observations = 1065 Schwarz B.I.C. = Number of positive obs. = 864 Log likelihood = Fraction of positive obs. = C [.000] LOGE [.000] LOGQ [.015] RNDA [.529] C [.049] LOGE E [.000] LINVE E E [.065] LRNDE E E [.729] DRND E [.019] SIGMA E [.000] RHO [.000] Errors computed from (Newton) analytic second derivatives C [.000] LOGE [.000] LOGQ [.017] RNDA [.516] C E [.044] LOGE E [.000] LINVE E E [.040] LRNDE E E [.735] DRND E [.031] SIGMA E [.000] RHO [.000] Errors computed from (BHHH) covariance of analytic first derivatives C [.000] LOGE [.000] LOGQ [.017] RNDA [.548] C [.116] LOGE E [.000] LINVE E E [.146] LRNDE E E [.727] DRND E [.013] SIGMA [.000] RHO [.000] Errors computed from (Eicker-White) analytic first and second derivatives dp/dx 0 1 C LOGE LOGQ RNDA

25 Equation 15 ============ PROBIT ESTIMATION Working space used: STARTING VALUES WC WLOGE WLOGQ WRNDA VALUE F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= F= FNEW= ISQZ= 0 STEP= CRIT= E- 03 F= FNEW= ISQZ= 0 STEP= CRIT= E- 09 CONVERGENCE ACHIEVED AFTER 5 ITERATIONS 10 FUNCTION EVALUATIONS. Dependent variable: IN94 Number of observations = 1065 Scaled R-squared = Number of positive obs. = 864 LR (zero slopes) = [.000] Mean of dep. var. = Schwarz B.I.C. = Sum of squared residuals = Log likelihood = R-squared = Fraction of Correct Predictions = WC E [.000] WLOGE E E [.008] WLOGQ E E [.608] WRNDA [.206] Errors computed from (Newton) analytic second derivatives WC E [.000] WLOGE E E [.004] WLOGQ E E [.626] WRNDA [.228] Errors computed from (BHHH) covariance of analytic first derivatives WC E [.000] WLOGE E E [.015] WLOGQ E E [.592] WRNDA [.186] Errors computed from analytic first and second derivatives

26 (Eicker-White) dp/dx 0 1 WC WLOGE WLOGQ WRNDA Godfrey's LM Test for Heteroskedasticity in Probit Eq =========== CHISQ(7) Test Statistic: , Upper tail area: Equation 17 ============ Method of estimation = Weighted Regression Weight: WT Dependent variable: DLOGE4 Number of observations: 1065 (Statistics based on transformed data) Mean of dep. var. = E-02 Std. dev. of dep. var. = Sum of squared residuals = Variance of residuals = Std. error of regression = R-squared = Adjusted R-squared = Durbin-Watson = Sum of weights = F (zero slopes) = [.000] Schwarz B.I.C. = Log likelihood = (Statistics based on original data) Mean of dep. var. = E-02 Std. dev. of dep. var. = Sum of squared residuals = Variance of residuals = Std. error of regression = R-squared = Adjusted R-squared = Durbin-Watson = Estimated Variable Coefficient Error t-statistic P-value C E [.032] LOGE E E [.000] LINVE E E [.023] LRNDE E E [.795] DRND E [.008] Errors are heteroskedastic-consistent (HCTYPE=2). Equation 18

27 ============ Method of estimation = Ordinary Least Squares Dependent variable: WDLOGE4 Number of observations: 1065 Mean of dep. var. = LM het. test = [.000] Std. dev. of dep. var. = Durbin-Watson = [<.592] Sum of squared residuals = Jarque-Bera test = [.000] Variance of residuals = Ramsey's RESET2 = [.019] Std. error of regression = F (zero slopes) = [.000] R-squared = Schwarz B.I.C. = Adjusted R-squared = Log likelihood = Estimated Variable Coefficient Error t-statistic P-value WC E [.032] WLOGE E E [.000] WLINVE E E [.023] WLRNDE E E [.795] WDRND E [.008] Errors are heteroskedastic-consistent (HCTYPE=2). Equation 19 ============ Sample Selection Estimation 231 function evaluations used for grid search on RHO. Working space used: STARTING VALUES WC WLOGE WLOGQ WRNDA VALUE WC WLOGE WLINVE WLRNDE VALUE WDRND SIGMA RHO VALUE F= FNEW= ISQZ= 0 STEP= CRIT= E- 01 F= FNEW= ISQZ= 0 STEP= CRIT= E- 04 CONVERGENCE ACHIEVED AFTER 2 ITERATIONS 4 FUNCTION EVALUATIONS. Probit Dependent variable: IN94 Regression Dependent variable: WDLOGE4 Number of observations = 1065 Schwarz B.I.C. = Number of positive obs. = 864 Log likelihood = Fraction of positive obs. =

28 WC E [.000] WLOGE E E [.071] WLOGQ E [.001] WRNDA [.133] WC E [.002] WLOGE E [.000] WLINVE E E [.090] WLRNDE E E [.877] WDRND E [.004] SIGMA [.000] RHO [.000] Errors computed from (Newton) analytic second derivatives WC E [.000] WLOGE E E [.066] WLOGQ E [.002] WRNDA [.159] WC [.004] WLOGE E [.000] WLINVE E E [.103] WLRNDE E E [.876] WDRND E [.005] SIGMA [.000] RHO [.000] Errors computed from (BHHH) covariance of analytic first derivatives WC E [.000] WLOGE E E [.081] WLOGQ E [.001] WRNDA [.115] WC E [.002] WLOGE E [.000] WLINVE E E [.086] WLRNDE E E [.884] WDRND E [.005] SIGMA [.000] RHO [.000] Errors computed from (Eicker-White) analytic first and second derivatives dp/dx 0 1 WC WLOGE WLOGQ WRNDA ****************************************************************************** * END OF OUTPUT.

29 TOTAL NUMBER OF NUMERIC WARNINGS: 214 TOTAL NUMBER OF WARNING MESSAGES: 62 MEMORY USAGE: ITEM: DATA ARRAY TOTAL MEMORY UNITS: (4-BYTE WORDS) (MEGABYTES) MEMORY ALLOCATED : MEMORY ACTUALLY REQUIRED : CURRENT VARIABLE STORAGE :

OLSQ. Function: Usage:

OLSQ. Function: Usage: OLSQ OLSQ (HCTYPE=robust SE type, HI, ROBUSTSE, SILENT, TERSE, UNNORM, WEIGHT=name of weighting variable, WTYPE=weight type) dependent variable list of independent variables ; Function: OLSQ is the basic

More information

13.2 Example: W, LM and LR Tests

13.2 Example: W, LM and LR Tests 13.2 Example: W, LM and LR Tests Date file = cons99.txt (same data as before) Each column denotes year, nominal household expenditures ( 10 billion yen), household disposable income ( 10 billion yen) and

More information

LSQ. Function: Usage:

LSQ. Function: Usage: LSQ LSQ (DEBUG, HETERO, INST=list of instrumental variables,iteru, COVU=OWN or name of residual covariance matrix,nonlinear options) list of equation names ; Function: LSQ is used to obtain least squares

More information

Economics 471: Econometrics Department of Economics, Finance and Legal Studies University of Alabama

Economics 471: Econometrics Department of Economics, Finance and Legal Studies University of Alabama Economics 471: Econometrics Department of Economics, Finance and Legal Studies University of Alabama Course Packet The purpose of this packet is to show you one particular dataset and how it is used in

More information

Answer all questions from part I. Answer two question from part II.a, and one question from part II.b.

Answer all questions from part I. Answer two question from part II.a, and one question from part II.b. B203: Quantitative Methods Answer all questions from part I. Answer two question from part II.a, and one question from part II.b. Part I: Compulsory Questions. Answer all questions. Each question carries

More information

BJEST. Function: Usage:

BJEST. Function: Usage: BJEST BJEST (CONSTANT, CUMPLOT, EXACTML, NAR=number of AR parameters, NBACK=number of back-forecasted residuals,ndiff=degree of differencing, NLAG=number of autocorrelations,nma=number of MA parameters,

More information

CHAPTER 6: SPECIFICATION VARIABLES

CHAPTER 6: SPECIFICATION VARIABLES Recall, we had the following six assumptions required for the Gauss-Markov Theorem: 1. The regression model is linear, correctly specified, and has an additive error term. 2. The error term has a zero

More information

TSP 5.0 User s Guide. Bronwyn H. Hall. and. Clint Cummins

TSP 5.0 User s Guide. Bronwyn H. Hall. and. Clint Cummins TSP 5.0 User s Guide Bronwyn H. Hall and Clint Cummins TSP International 2005 Copyright 2005 by TSP International First edition (Version 4.0) published 1980. TSP is a software product of TSP International.

More information

Brief Sketch of Solutions: Tutorial 3. 3) unit root tests

Brief Sketch of Solutions: Tutorial 3. 3) unit root tests Brief Sketch of Solutions: Tutorial 3 3) unit root tests.5.4.4.3.3.2.2.1.1.. -.1 -.1 -.2 -.2 -.3 -.3 -.4 -.4 21 22 23 24 25 26 -.5 21 22 23 24 25 26.8.2.4. -.4 - -.8 - - -.12 21 22 23 24 25 26 -.2 21 22

More information

Romanian Economic and Business Review Vol. 3, No. 3 THE EVOLUTION OF SNP PETROM STOCK LIST - STUDY THROUGH AUTOREGRESSIVE MODELS

Romanian Economic and Business Review Vol. 3, No. 3 THE EVOLUTION OF SNP PETROM STOCK LIST - STUDY THROUGH AUTOREGRESSIVE MODELS THE EVOLUTION OF SNP PETROM STOCK LIST - STUDY THROUGH AUTOREGRESSIVE MODELS Marian Zaharia, Ioana Zaheu, and Elena Roxana Stan Abstract Stock exchange market is one of the most dynamic and unpredictable

More information

Jeffrey M. Wooldridge Michigan State University

Jeffrey M. Wooldridge Michigan State University Fractional Response Models with Endogenous Explanatory Variables and Heterogeneity Jeffrey M. Wooldridge Michigan State University 1. Introduction 2. Fractional Probit with Heteroskedasticity 3. Fractional

More information

4. Examples. Results: Example 4.1 Implementation of the Example 3.1 in SAS. In SAS we can use the Proc Model procedure.

4. Examples. Results: Example 4.1 Implementation of the Example 3.1 in SAS. In SAS we can use the Proc Model procedure. 4. Examples Example 4.1 Implementation of the Example 3.1 in SAS. In SAS we can use the Proc Model procedure. Simulate data from t-distribution with ν = 6. SAS: data tdist; do i = 1 to 500; y = tinv(ranuni(158),6);

More information

Microeconometrics (PhD) Problem set 2: Dynamic Panel Data Solutions

Microeconometrics (PhD) Problem set 2: Dynamic Panel Data Solutions Microeconometrics (PhD) Problem set 2: Dynamic Panel Data Solutions QUESTION 1 Data for this exercise can be prepared by running the do-file called preparedo posted on my webpage This do-file collects

More information

Handout 12. Endogeneity & Simultaneous Equation Models

Handout 12. Endogeneity & Simultaneous Equation Models Handout 12. Endogeneity & Simultaneous Equation Models In which you learn about another potential source of endogeneity caused by the simultaneous determination of economic variables, and learn how to

More information

How To Do Piecewise Exponential Survival Analysis in Stata 7 (Allison 1995:Output 4.20) revised

How To Do Piecewise Exponential Survival Analysis in Stata 7 (Allison 1995:Output 4.20) revised WM Mason, Soc 213B, S 02, UCLA Page 1 of 15 How To Do Piecewise Exponential Survival Analysis in Stata 7 (Allison 1995:Output 420) revised 4-25-02 This document can function as a "how to" for setting up

More information

ECON2228 Notes 10. Christopher F Baum. Boston College Economics. cfb (BC Econ) ECON2228 Notes / 48

ECON2228 Notes 10. Christopher F Baum. Boston College Economics. cfb (BC Econ) ECON2228 Notes / 48 ECON2228 Notes 10 Christopher F Baum Boston College Economics 2014 2015 cfb (BC Econ) ECON2228 Notes 10 2014 2015 1 / 48 Serial correlation and heteroskedasticity in time series regressions Chapter 12:

More information

Case of single exogenous (iv) variable (with single or multiple mediators) iv à med à dv. = β 0. iv i. med i + α 1

Case of single exogenous (iv) variable (with single or multiple mediators) iv à med à dv. = β 0. iv i. med i + α 1 Mediation Analysis: OLS vs. SUR vs. ISUR vs. 3SLS vs. SEM Note by Hubert Gatignon July 7, 2013, updated November 15, 2013, April 11, 2014, May 21, 2016 and August 10, 2016 In Chap. 11 of Statistical Analysis

More information

Reading Assignment. Serial Correlation and Heteroskedasticity. Chapters 12 and 11. Kennedy: Chapter 8. AREC-ECON 535 Lec F1 1

Reading Assignment. Serial Correlation and Heteroskedasticity. Chapters 12 and 11. Kennedy: Chapter 8. AREC-ECON 535 Lec F1 1 Reading Assignment Serial Correlation and Heteroskedasticity Chapters 1 and 11. Kennedy: Chapter 8. AREC-ECON 535 Lec F1 1 Serial Correlation or Autocorrelation y t = β 0 + β 1 x 1t + β x t +... + β k

More information

Are Chinese Cities Too Small? Supplementary Material. Key to Variables in Dataset. J. Vernon Henderson and Chun-Chung Au September 30, 2005

Are Chinese Cities Too Small? Supplementary Material. Key to Variables in Dataset. J. Vernon Henderson and Chun-Chung Au September 30, 2005 Are Chinese Cities Too Small? Supplementary Material J Vernon Henderson and Chun-Chung Au September 30, 2005 In this supplement are (1) a print-out from Limdep of material in Table 2 in the paper, including

More information

ECON2228 Notes 10. Christopher F Baum. Boston College Economics. cfb (BC Econ) ECON2228 Notes / 54

ECON2228 Notes 10. Christopher F Baum. Boston College Economics. cfb (BC Econ) ECON2228 Notes / 54 ECON2228 Notes 10 Christopher F Baum Boston College Economics 2014 2015 cfb (BC Econ) ECON2228 Notes 10 2014 2015 1 / 54 erial correlation and heteroskedasticity in time series regressions Chapter 12:

More information

Description Remarks and examples Reference Also see

Description Remarks and examples Reference Also see Title stata.com example 38g Random-intercept and random-slope models (multilevel) Description Remarks and examples Reference Also see Description Below we discuss random-intercept and random-slope models

More information

Lecture 8. Using the CLR Model

Lecture 8. Using the CLR Model Lecture 8. Using the CLR Model Example of regression analysis. Relation between patent applications and R&D spending Variables PATENTS = No. of patents (in 1000) filed RDEXP = Expenditure on research&development

More information

Econ 510 B. Brown Spring 2014 Final Exam Answers

Econ 510 B. Brown Spring 2014 Final Exam Answers Econ 510 B. Brown Spring 2014 Final Exam Answers Answer five of the following questions. You must answer question 7. The question are weighted equally. You have 2.5 hours. You may use a calculator. Brevity

More information

Econometrics. 8) Instrumental variables

Econometrics. 8) Instrumental variables 30C00200 Econometrics 8) Instrumental variables Timo Kuosmanen Professor, Ph.D. http://nomepre.net/index.php/timokuosmanen Today s topics Thery of IV regression Overidentification Two-stage least squates

More information

Final Exam. 1. Definitions: Briefly Define each of the following terms as they relate to the material covered in class.

Final Exam. 1. Definitions: Briefly Define each of the following terms as they relate to the material covered in class. Name Answer Key Economics 170 Spring 2003 Honor pledge: I have neither given nor received aid on this exam including the preparation of my one page formula list and the preparation of the Stata assignment

More information

CDF. Function: Usage:

CDF. Function: Usage: CDF CDF (BIVNORM or CHISQ or DICKEYF or F or NORMAL or T or WTDCHI, DF=degrees of freedom for CHISQ or T, DF1=numerator degrees of freedom for F, DF2=denominator degrees of freedom for F, NLAGS=number

More information

1. You have data on years of work experience, EXPER, its square, EXPER2, years of education, EDUC, and the log of hourly wages, LWAGE

1. You have data on years of work experience, EXPER, its square, EXPER2, years of education, EDUC, and the log of hourly wages, LWAGE 1. You have data on years of work experience, EXPER, its square, EXPER, years of education, EDUC, and the log of hourly wages, LWAGE You estimate the following regressions: (1) LWAGE =.00 + 0.05*EDUC +

More information

Chapter 7. Testing Linear Restrictions on Regression Coefficients

Chapter 7. Testing Linear Restrictions on Regression Coefficients Chapter 7 Testing Linear Restrictions on Regression Coefficients 1.F-tests versus t-tests In the previous chapter we discussed several applications of the t-distribution to testing hypotheses in the linear

More information

Problem set - Selection and Diff-in-Diff

Problem set - Selection and Diff-in-Diff Problem set - Selection and Diff-in-Diff 1. You want to model the wage equation for women You consider estimating the model: ln wage = α + β 1 educ + β 2 exper + β 3 exper 2 + ɛ (1) Read the data into

More information

A Guide to Modern Econometric:

A Guide to Modern Econometric: A Guide to Modern Econometric: 4th edition Marno Verbeek Rotterdam School of Management, Erasmus University, Rotterdam B 379887 )WILEY A John Wiley & Sons, Ltd., Publication Contents Preface xiii 1 Introduction

More information

CRE METHODS FOR UNBALANCED PANELS Correlated Random Effects Panel Data Models IZA Summer School in Labor Economics May 13-19, 2013 Jeffrey M.

CRE METHODS FOR UNBALANCED PANELS Correlated Random Effects Panel Data Models IZA Summer School in Labor Economics May 13-19, 2013 Jeffrey M. CRE METHODS FOR UNBALANCED PANELS Correlated Random Effects Panel Data Models IZA Summer School in Labor Economics May 13-19, 2013 Jeffrey M. Wooldridge Michigan State University 1. Introduction 2. Linear

More information

Econ 427, Spring Problem Set 3 suggested answers (with minor corrections) Ch 6. Problems and Complements:

Econ 427, Spring Problem Set 3 suggested answers (with minor corrections) Ch 6. Problems and Complements: Econ 427, Spring 2010 Problem Set 3 suggested answers (with minor corrections) Ch 6. Problems and Complements: 1. (page 132) In each case, the idea is to write these out in general form (without the lag

More information

FinQuiz Notes

FinQuiz Notes Reading 10 Multiple Regression and Issues in Regression Analysis 2. MULTIPLE LINEAR REGRESSION Multiple linear regression is a method used to model the linear relationship between a dependent variable

More information

Exercises (in progress) Applied Econometrics Part 1

Exercises (in progress) Applied Econometrics Part 1 Exercises (in progress) Applied Econometrics 2016-2017 Part 1 1. De ne the concept of unbiased estimator. 2. Explain what it is a classic linear regression model and which are its distinctive features.

More information

Econometrics. 9) Heteroscedasticity and autocorrelation

Econometrics. 9) Heteroscedasticity and autocorrelation 30C00200 Econometrics 9) Heteroscedasticity and autocorrelation Timo Kuosmanen Professor, Ph.D. http://nomepre.net/index.php/timokuosmanen Today s topics Heteroscedasticity Possible causes Testing for

More information

F9 F10: Autocorrelation

F9 F10: Autocorrelation F9 F10: Autocorrelation Feng Li Department of Statistics, Stockholm University Introduction In the classic regression model we assume cov(u i, u j x i, x k ) = E(u i, u j ) = 0 What if we break the assumption?

More information

Quantitative Methods Final Exam (2017/1)

Quantitative Methods Final Exam (2017/1) Quantitative Methods Final Exam (2017/1) 1. Please write down your name and student ID number. 2. Calculator is allowed during the exam, but DO NOT use a smartphone. 3. List your answers (together with

More information

MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS

MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS Page 1 MSR = Mean Regression Sum of Squares MSE = Mean Squared Error RSS = Regression Sum of Squares SSE = Sum of Squared Errors/Residuals α = Level

More information

Section 2 NABE ASTEF 65

Section 2 NABE ASTEF 65 Section 2 NABE ASTEF 65 Econometric (Structural) Models 66 67 The Multiple Regression Model 68 69 Assumptions 70 Components of Model Endogenous variables -- Dependent variables, values of which are determined

More information

Binary Dependent Variables

Binary Dependent Variables Binary Dependent Variables In some cases the outcome of interest rather than one of the right hand side variables - is discrete rather than continuous Binary Dependent Variables In some cases the outcome

More information

Introduction to Linear regression analysis. Part 2. Model comparisons

Introduction to Linear regression analysis. Part 2. Model comparisons Introduction to Linear regression analysis Part Model comparisons 1 ANOVA for regression Total variation in Y SS Total = Variation explained by regression with X SS Regression + Residual variation SS Residual

More information

Using EViews Vox Principles of Econometrics, Third Edition

Using EViews Vox Principles of Econometrics, Third Edition Using EViews Vox Principles of Econometrics, Third Edition WILLIAM E. GRIFFITHS University of Melbourne R. CARTER HILL Louisiana State University GUAY С LIM University of Melbourne JOHN WILEY & SONS, INC

More information

TIME SERIES DATA ANALYSIS USING EVIEWS

TIME SERIES DATA ANALYSIS USING EVIEWS TIME SERIES DATA ANALYSIS USING EVIEWS I Gusti Ngurah Agung Graduate School Of Management Faculty Of Economics University Of Indonesia Ph.D. in Biostatistics and MSc. in Mathematical Statistics from University

More information

Empirical Economic Research, Part II

Empirical Economic Research, Part II Based on the text book by Ramanathan: Introductory Econometrics Robert M. Kunst robert.kunst@univie.ac.at University of Vienna and Institute for Advanced Studies Vienna December 7, 2011 Outline Introduction

More information

Dealing With and Understanding Endogeneity

Dealing With and Understanding Endogeneity Dealing With and Understanding Endogeneity Enrique Pinzón StataCorp LP October 20, 2016 Barcelona (StataCorp LP) October 20, 2016 Barcelona 1 / 59 Importance of Endogeneity Endogeneity occurs when a variable,

More information

i (x i x) 2 1 N i x i(y i y) Var(x) = P (x 1 x) Var(x)

i (x i x) 2 1 N i x i(y i y) Var(x) = P (x 1 x) Var(x) ECO 6375 Prof Millimet Problem Set #2: Answer Key Stata problem 2 Q 3 Q (a) The sample average of the individual-specific marginal effects is 0039 for educw and -0054 for white Thus, on average, an extra

More information

Subject-specific observed profiles of log(fev1) vs age First 50 subjects in Six Cities Study

Subject-specific observed profiles of log(fev1) vs age First 50 subjects in Six Cities Study Subject-specific observed profiles of log(fev1) vs age First 50 subjects in Six Cities Study 1.4 0.0-6 7 8 9 10 11 12 13 14 15 16 17 18 19 age Model 1: A simple broken stick model with knot at 14 fit with

More information

2. We care about proportion for categorical variable, but average for numerical one.

2. We care about proportion for categorical variable, but average for numerical one. Probit Model 1. We apply Probit model to Bank data. The dependent variable is deny, a dummy variable equaling one if a mortgage application is denied, and equaling zero if accepted. The key regressor is

More information

-redprob- A Stata program for the Heckman estimator of the random effects dynamic probit model

-redprob- A Stata program for the Heckman estimator of the random effects dynamic probit model -redprob- A Stata program for the Heckman estimator of the random effects dynamic probit model Mark B. Stewart University of Warwick January 2006 1 The model The latent equation for the random effects

More information

Functional Form. Econometrics. ADEi.

Functional Form. Econometrics. ADEi. Functional Form Econometrics. ADEi. 1. Introduction We have employed the linear function in our model specification. Why? It is simple and has good mathematical properties. It could be reasonable approximation,

More information

Outline. Linear OLS Models vs: Linear Marginal Models Linear Conditional Models. Random Intercepts Random Intercepts & Slopes

Outline. Linear OLS Models vs: Linear Marginal Models Linear Conditional Models. Random Intercepts Random Intercepts & Slopes Lecture 2.1 Basic Linear LDA 1 Outline Linear OLS Models vs: Linear Marginal Models Linear Conditional Models Random Intercepts Random Intercepts & Slopes Cond l & Marginal Connections Empirical Bayes

More information

Regression without measurement error using proc calis

Regression without measurement error using proc calis Regression without measurement error using proc calis /* calculus2.sas */ options linesize=79 pagesize=500 noovp formdlim='_'; title 'Calculus 2: Regression with no measurement error'; title2 ''; data

More information

SAS Example 3: Deliberately create numerical problems

SAS Example 3: Deliberately create numerical problems SAS Example 3: Deliberately create numerical problems Four experiments 1. Try to fit this model, failing the parameter count rule. 2. Set φ 12 =0 to pass the parameter count rule, but still not identifiable.

More information

More on Specification and Data Issues

More on Specification and Data Issues More on Specification and Data Issues Ping Yu School of Economics and Finance The University of Hong Kong Ping Yu (HKU) Specification and Data Issues 1 / 35 Functional Form Misspecification Functional

More information

ANEXO 1 MODELO CON LM1 NOMINAL DESESTACIONALIZADO. Statistic

ANEXO 1 MODELO CON LM1 NOMINAL DESESTACIONALIZADO. Statistic ANEXO MODELO CON LM NOMINAL DESESTACIONALIZADO.. Pruebas de Raiz Unitaria Null Hypothesis: D (LM) has a unit root Exogenous: Constant, Linear Trend Lag Length: 2 (Automatic based on AIC, MAXLAG=2) t ElliottRothenbergStock

More information

Gravity Analysis of Regional Economic Interdependence: In case of Japan

Gravity Analysis of Regional Economic Interdependence: In case of Japan Prepared for the 21 st INFORUM World Conference 26-31 August 2013, Listvyanka, Russia Gravity Analysis of Regional Economic Interdependence: In case of Japan Toshiaki Hasegawa Chuo University Tokyo, JAPAN

More information

Volatility. Gerald P. Dwyer. February Clemson University

Volatility. Gerald P. Dwyer. February Clemson University Volatility Gerald P. Dwyer Clemson University February 2016 Outline 1 Volatility Characteristics of Time Series Heteroskedasticity Simpler Estimation Strategies Exponentially Weighted Moving Average Use

More information

Dynamic Panels. Chapter Introduction Autoregressive Model

Dynamic Panels. Chapter Introduction Autoregressive Model Chapter 11 Dynamic Panels This chapter covers the econometrics methods to estimate dynamic panel data models, and presents examples in Stata to illustrate the use of these procedures. The topics in this

More information

Final Exam. Question 1 (20 points) 2 (25 points) 3 (30 points) 4 (25 points) 5 (10 points) 6 (40 points) Total (150 points) Bonus question (10)

Final Exam. Question 1 (20 points) 2 (25 points) 3 (30 points) 4 (25 points) 5 (10 points) 6 (40 points) Total (150 points) Bonus question (10) Name Economics 170 Spring 2004 Honor pledge: I have neither given nor received aid on this exam including the preparation of my one page formula list and the preparation of the Stata assignment for the

More information

Question 1 [17 points]: (ch 11)

Question 1 [17 points]: (ch 11) Question 1 [17 points]: (ch 11) A study analyzed the probability that Major League Baseball (MLB) players "survive" for another season, or, in other words, play one more season. They studied a model of

More information

ECON 4551 Econometrics II Memorial University of Newfoundland. Panel Data Models. Adapted from Vera Tabakova s notes

ECON 4551 Econometrics II Memorial University of Newfoundland. Panel Data Models. Adapted from Vera Tabakova s notes ECON 4551 Econometrics II Memorial University of Newfoundland Panel Data Models Adapted from Vera Tabakova s notes 15.1 Grunfeld s Investment Data 15.2 Sets of Regression Equations 15.3 Seemingly Unrelated

More information

Lampiran. Lampiran 1 Data Penelitian TAHUN Y X1 X2 X3 X4_AS X4_JPG X4_INDH 1995

Lampiran. Lampiran 1 Data Penelitian TAHUN Y X1 X2 X3 X4_AS X4_JPG X4_INDH 1995 Lampiran Lampiran 1 Data Penelitian TAHUN Y X1 X2 X3 X4_AS X4_JPG X4_INDH 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 3,107,163 3,102,431 3,443,555

More information

Probit Estimation in gretl

Probit Estimation in gretl Probit Estimation in gretl Quantitative Microeconomics R. Mora Department of Economics Universidad Carlos III de Madrid Outline Introduction 1 Introduction 2 3 The Probit Model and ML Estimation The Probit

More information

Multivariate Regression: Part I

Multivariate Regression: Part I Topic 1 Multivariate Regression: Part I ARE/ECN 240 A Graduate Econometrics Professor: Òscar Jordà Outline of this topic Statement of the objective: we want to explain the behavior of one variable as a

More information

Graduate Econometrics Lecture 4: Heteroskedasticity

Graduate Econometrics Lecture 4: Heteroskedasticity Graduate Econometrics Lecture 4: Heteroskedasticity Department of Economics University of Gothenburg November 30, 2014 1/43 and Autocorrelation Consequences for OLS Estimator Begin from the linear model

More information

Lecture 3 Linear random intercept models

Lecture 3 Linear random intercept models Lecture 3 Linear random intercept models Example: Weight of Guinea Pigs Body weights of 48 pigs in 9 successive weeks of follow-up (Table 3.1 DLZ) The response is measures at n different times, or under

More information

Multi-Equation Structural Models: Seemingly Unrelated Regression Models

Multi-Equation Structural Models: Seemingly Unrelated Regression Models Chapter 15 Multi-Equation Structural Models: Seemingly Unrelated Regression Models Section 15.1 Seemingly Unrelated Regression Models Modeling Approaches Econometric (Structural) Models Time-Series Models

More information

08 Endogenous Right-Hand-Side Variables. Andrius Buteikis,

08 Endogenous Right-Hand-Side Variables. Andrius Buteikis, 08 Endogenous Right-Hand-Side Variables Andrius Buteikis, andrius.buteikis@mif.vu.lt http://web.vu.lt/mif/a.buteikis/ Introduction Consider a simple regression model: Y t = α + βx t + u t Under the classical

More information

Treatment interactions with nonexperimental data in Stata

Treatment interactions with nonexperimental data in Stata The Stata Journal (2011) 11, umber4,pp.1 11 Treatment interactions with nonexperimental data in Stata Graham K. Brown Centre for Development Studies University of Bath Bath, UK g.k.brown@bath.ac.uk Thanos

More information

Problem Set 5 ANSWERS

Problem Set 5 ANSWERS Economics 20 Problem Set 5 ANSWERS Prof. Patricia M. Anderson 1, 2 and 3 Suppose that Vermont has passed a law requiring employers to provide 6 months of paid maternity leave. You are concerned that women

More information

New York University Department of Economics. Applied Statistics and Econometrics G Spring 2013

New York University Department of Economics. Applied Statistics and Econometrics G Spring 2013 New York University Department of Economics Applied Statistics and Econometrics G31.1102 Spring 2013 Text: Econometric Analysis, 7 h Edition, by William Greene (Prentice Hall) Optional: A Guide to Modern

More information

Testing Hypothesis after Probit Estimation

Testing Hypothesis after Probit Estimation Testing Hypothesis after Probit Estimation Quantitative Microeconomics R. Mora Department of Economics Universidad Carlos III de Madrid Outline Introduction 1 Introduction 2 3 The Probit Model and ML Estimation

More information

Introduction

Introduction =============================================================================== mla.doc MLA 3.2 05/31/97 =============================================================================== Copyright (c) 1993-97

More information

Autocorrelation. Think of autocorrelation as signifying a systematic relationship between the residuals measured at different points in time

Autocorrelation. Think of autocorrelation as signifying a systematic relationship between the residuals measured at different points in time Autocorrelation Given the model Y t = b 0 + b 1 X t + u t Think of autocorrelation as signifying a systematic relationship between the residuals measured at different points in time This could be caused

More information

Christopher Dougherty London School of Economics and Political Science

Christopher Dougherty London School of Economics and Political Science Introduction to Econometrics FIFTH EDITION Christopher Dougherty London School of Economics and Political Science OXFORD UNIVERSITY PRESS Contents INTRODU CTION 1 Why study econometrics? 1 Aim of this

More information

An Introduction to Econometrics. A Self-contained Approach. Frank Westhoff. The MIT Press Cambridge, Massachusetts London, England

An Introduction to Econometrics. A Self-contained Approach. Frank Westhoff. The MIT Press Cambridge, Massachusetts London, England An Introduction to Econometrics A Self-contained Approach Frank Westhoff The MIT Press Cambridge, Massachusetts London, England How to Use This Book xvii 1 Descriptive Statistics 1 Chapter 1 Prep Questions

More information

Generalized linear models

Generalized linear models Generalized linear models Christopher F Baum ECON 8823: Applied Econometrics Boston College, Spring 2016 Christopher F Baum (BC / DIW) Generalized linear models Boston College, Spring 2016 1 / 1 Introduction

More information

Monday 7 th Febraury 2005

Monday 7 th Febraury 2005 Monday 7 th Febraury 2 Analysis of Pigs data Data: Body weights of 48 pigs at 9 successive follow-up visits. This is an equally spaced data. It is always a good habit to reshape the data, so we can easily

More information

Some general observations.

Some general observations. Modeling and analyzing data from computer experiments. Some general observations. 1. For simplicity, I assume that all factors (inputs) x1, x2,, xd are quantitative. 2. Because the code always produces

More information

Multivariate probit regression using simulated maximum likelihood

Multivariate probit regression using simulated maximum likelihood Multivariate probit regression using simulated maximum likelihood Lorenzo Cappellari & Stephen P. Jenkins ISER, University of Essex stephenj@essex.ac.uk 1 Overview Introduction and motivation The model

More information

Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006

Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006 Eksamen på Økonomistudiet 2006-II Econometrics 2 June 9, 2006 This is a four hours closed-book exam (uden hjælpemidler). Please answer all questions. As a guiding principle the questions 1 to 4 have equal

More information

Empirical Application of Panel Data Regression

Empirical Application of Panel Data Regression Empirical Application of Panel Data Regression 1. We use Fatality data, and we are interested in whether rising beer tax rate can help lower traffic death. So the dependent variable is traffic death, while

More information

2. Linear regression with multiple regressors

2. Linear regression with multiple regressors 2. Linear regression with multiple regressors Aim of this section: Introduction of the multiple regression model OLS estimation in multiple regression Measures-of-fit in multiple regression Assumptions

More information

Cointegration and Error-Correction

Cointegration and Error-Correction Chapter 9 Cointegration and Error-Correction In this chapter we will estimate structural VAR models that include nonstationary variables. This exploits the possibility that there could be a linear combination

More information

VAR-based Granger-causality Test in the Presence of Instabilities

VAR-based Granger-causality Test in the Presence of Instabilities VAR-based Granger-causality Test in the Presence of Instabilities Barbara Rossi ICREA Professor at University of Pompeu Fabra Barcelona Graduate School of Economics, and CREI Barcelona, Spain. barbara.rossi@upf.edu

More information

A Quick Guide to GPE/GAUSS

A Quick Guide to GPE/GAUSS A Quick Guide to GPE/GAUSS Copyright (c) 2001, by Kuan-Pin Lin and Applied Data Associates GPE (GAUSS Programming for Econometricians and Financial Analysts) is a package of econometric procedures written

More information

Types of economic data

Types of economic data Types of economic data Time series data Cross-sectional data Panel data 1 1-2 1-3 1-4 1-5 The distinction between qualitative and quantitative data The previous data sets can be used to illustrate an important

More information

Description Remarks and examples Reference Also see

Description Remarks and examples Reference Also see Title stata.com example 20 Two-factor measurement model by group Description Remarks and examples Reference Also see Description Below we demonstrate sem s group() option, which allows fitting models in

More information

Contents. Part I Statistical Background and Basic Data Handling 5. List of Figures List of Tables xix

Contents. Part I Statistical Background and Basic Data Handling 5. List of Figures List of Tables xix Contents List of Figures List of Tables xix Preface Acknowledgements 1 Introduction 1 What is econometrics? 2 The stages of applied econometric work 2 Part I Statistical Background and Basic Data Handling

More information

Multiple Regression: Inference

Multiple Regression: Inference Multiple Regression: Inference The t-test: is ˆ j big and precise enough? We test the null hypothesis: H 0 : β j =0; i.e. test that x j has no effect on y once the other explanatory variables are controlled

More information

Outline. 2. Logarithmic Functional Form and Units of Measurement. Functional Form. I. Functional Form: log II. Units of Measurement

Outline. 2. Logarithmic Functional Form and Units of Measurement. Functional Form. I. Functional Form: log II. Units of Measurement Outline 2. Logarithmic Functional Form and Units of Measurement I. Functional Form: log II. Units of Measurement Read Wooldridge (2013), Chapter 2.4, 6.1 and 6.2 2 Functional Form I. Functional Form: log

More information

Applied Econometrics. Applied Econometrics. Applied Econometrics. Applied Econometrics. What is Autocorrelation. Applied Econometrics

Applied Econometrics. Applied Econometrics. Applied Econometrics. Applied Econometrics. What is Autocorrelation. Applied Econometrics Autocorrelation 1. What is 2. What causes 3. First and higher orders 4. Consequences of 5. Detecting 6. Resolving Learning Objectives 1. Understand meaning of in the CLRM 2. What causes 3. Distinguish

More information

Exam ECON3150/4150: Introductory Econometrics. 18 May 2016; 09:00h-12.00h.

Exam ECON3150/4150: Introductory Econometrics. 18 May 2016; 09:00h-12.00h. Exam ECON3150/4150: Introductory Econometrics. 18 May 2016; 09:00h-12.00h. This is an open book examination where all printed and written resources, in addition to a calculator, are allowed. If you are

More information

Practice exam questions

Practice exam questions Practice exam questions Nathaniel Higgins nhiggins@jhu.edu, nhiggins@ers.usda.gov 1. The following question is based on the model y = β 0 + β 1 x 1 + β 2 x 2 + β 3 x 3 + u. Discuss the following two hypotheses.

More information

November 9th-12th 2010, Port of Spain, Trinidad

November 9th-12th 2010, Port of Spain, Trinidad By: Damie Sinanan and Dr. Roger Hosein 42nd Annual Monetary Studies Conference Financial Stability, Crisis Preparedness and Risk Management in the Caribbean November 9th-12th 2010, Port of Spain, Trinidad

More information

Greene, Econometric Analysis (7th ed, 2012)

Greene, Econometric Analysis (7th ed, 2012) EC771: Econometrics, Spring 2012 Greene, Econometric Analysis (7th ed, 2012) Chapters 2 3: Classical Linear Regression The classical linear regression model is the single most useful tool in econometrics.

More information

A Non-Parametric Approach of Heteroskedasticity Robust Estimation of Vector-Autoregressive (VAR) Models

A Non-Parametric Approach of Heteroskedasticity Robust Estimation of Vector-Autoregressive (VAR) Models Journal of Finance and Investment Analysis, vol.1, no.1, 2012, 55-67 ISSN: 2241-0988 (print version), 2241-0996 (online) International Scientific Press, 2012 A Non-Parametric Approach of Heteroskedasticity

More information

The Regression Tool. Yona Rubinstein. July Yona Rubinstein (LSE) The Regression Tool 07/16 1 / 35

The Regression Tool. Yona Rubinstein. July Yona Rubinstein (LSE) The Regression Tool 07/16 1 / 35 The Regression Tool Yona Rubinstein July 2016 Yona Rubinstein (LSE) The Regression Tool 07/16 1 / 35 Regressions Regression analysis is one of the most commonly used statistical techniques in social and

More information

ECON Introductory Econometrics. Lecture 5: OLS with One Regressor: Hypothesis Tests

ECON Introductory Econometrics. Lecture 5: OLS with One Regressor: Hypothesis Tests ECON4150 - Introductory Econometrics Lecture 5: OLS with One Regressor: Hypothesis Tests Monique de Haan (moniqued@econ.uio.no) Stock and Watson Chapter 5 Lecture outline 2 Testing Hypotheses about one

More information

G. S. Maddala Kajal Lahiri. WILEY A John Wiley and Sons, Ltd., Publication

G. S. Maddala Kajal Lahiri. WILEY A John Wiley and Sons, Ltd., Publication G. S. Maddala Kajal Lahiri WILEY A John Wiley and Sons, Ltd., Publication TEMT Foreword Preface to the Fourth Edition xvii xix Part I Introduction and the Linear Regression Model 1 CHAPTER 1 What is Econometrics?

More information