Hi, I am working on a research project in finding market power of the rice milling industry in Sri Lanka for each year from 2003 to 2018. Here, I used a set of monthly secondary data. I used the following two regression models to find conjectural variational elasticity (known as theta in parameter)
Array
Equation 1 is the demand equation for rice Equation 2 is the rice miller's pricing equation. These equations were estimated using nlsur command indicated below
nlsur (WS_Ric_Prc = {a} * FG_Pdy_Prc + {bo} + {b1} * Ind_Lab_WR + {b2} * Fix_Dep_IR + {b3} * Ind_Elec_chag + {b4} * Imp_PP_bag + {b5} * Prc_per_Lit - {theta}/{eta} * WS_Ric_Prc - {theta03}/{eta03} * (D03 * WS_Ric_Prc) - {theta04}/{eta04} * (D04 * WS_Ric_Prc) - {theta05}/{eta05} * (D05 * WS_Ric_Prc) - {theta06}/{eta06} * (D06 * WS_Ric_Prc) - {theta07}/{eta07} * (D07 * WS_Ric_Prc) - {theta08}/{eta08}* (D08 * WS_Ric_Prc) - {theta09}/{eta09} * (D09 * WS_Ric_Prc) - {theta10}/{eta10} * (D10 * WS_Ric_Prc) - {theta11}/{eta11} * (D11 * WS_Ric_Prc) - {theta12}/{eta12} * (D12 * WS_Ric_Prc) - {theta13}/{eta13} * (D13 * WS_Ric_Prc) - {theta14}/{14eta} * (D14 * WS_Ric_Prc) - {theta15}/{15eta} * (D15 * WS_Ric_Prc) - {theta16}/{eta16} * (D16 * WS_Ric_Prc) - {theta17}/{eta17} * (D17 * WS_Ric_Prc)) (ln_Qty_Ric_Dem_ds = {d0} + {eta} * (ln_RT_Ric_Prc * D18) + {eta03} * (ln_RT_Ric_Prc * D03) + {eta04} * (ln_RT_Ric_Prc * D04) + {eta05} * (ln_RT_Ric_Prc * D05) + {eta06} * (ln_RT_Ric_Prc * D06) + {eta07} * (ln_RT_Ric_Prc * D07) + {eta08} * (ln_RT_Ric_Prc * D08) + {eta09} * (ln_RT_Ric_Prc * D09) + {eta10} * (ln_RT_Ric_Prc * D10) + {eta11} * (ln_RT_Ric_Prc * D11) + {eta12} * (ln_RT_Ric_Prc * D12) + {eta13} * (ln_RT_Ric_Prc * D13) + {eta14} * (ln_RT_Ric_Prc * D14) + {eta15} * (ln_RT_Ric_Prc * D15) + {eta16} * (ln_RT_Ric_Prc * D16) + {eta17} * (ln_RT_Ric_Prc * D16) + {eta17} * (ln_RT_Ric_Prc * D17) + {d1} * ln_Mnth_HH_Incm + {d2} * ln_Pop + {d3} * ln_RT_Wht_Prc + {d4} * L_ln_Qty_Ric_Dem_ds), initial(a 0.1 bo 1 b1 1 b2 1 b3 1 b4 1 theta 0.001 eta -0.07 theta03 0.001 theta04 0.001 theta05 0.001 theta06 0.001 theta07 0.001 theta08 0.001 theta09 0.001 theta10 0.001 theta11 0.001 theta12 0.001 theta13 0.001 theta14 0.001 theta15 0.001 theta16 0.001 theta17 0.001 eta03 -0.07 eta04 -0.07 eta05 -0.07 eta06 -0.07 eta07 -0.07 eta08 -0.07 eta09 -0.07 eta10 -0.07 eta11 -0.07 eta12 -0.07 eta13 -0.07 eta14 -0.07 eta15 -0.07 eta16 -0.07 eta17 -0.07 d0 0.1 d1 1 d2 1)
For the easiness, I here separated the equation
1. Pricing Equation code (Red font color code)
(WS_Ric_Prc = {a} * FG_Pdy_Prc + {bo} + {b1} * Ind_Lab_WR + {b2} * Fix_Dep_IR + {b3} * Ind_Elec_chag + {b4} * Imp_PP_bag + {b5} * Prc_per_Lit - {theta}/{eta} * WS_Ric_Prc - {theta03}/{eta03} * (D03 * WS_Ric_Prc) - {theta04}/{eta04} * (D04 * WS_Ric_Prc) - {theta05}/{eta05} * (D05 * WS_Ric_Prc) - {theta06}/{eta06} * (D06 * WS_Ric_Prc) - {theta07}/{eta07} * (D07 * WS_Ric_Prc) - {theta08}/{eta08}* (D08 * WS_Ric_Prc) - {theta09}/{eta09} * (D09 * WS_Ric_Prc) - {theta10}/{eta10} * (D10 * WS_Ric_Prc) - {theta11}/{eta11} * (D11 * WS_Ric_Prc) - {theta12}/{eta12} * (D12 * WS_Ric_Prc) - {theta13}/{eta13} * (D13 * WS_Ric_Prc) - {theta14}/{14eta} * (D14 * WS_Ric_Prc) - {theta15}/{15eta} * (D15 * WS_Ric_Prc) - {theta16}/{eta16} * (D16 * WS_Ric_Prc) - {theta17}/{eta17} * (D17 * WS_Ric_Prc))
Here I used theta03 to theta 17 is the change in conjectural variation with respect to theta considered as the conjectural variation of the year 2018, D03 to D17 are dummy variables indicating the year 2003 to 2017 where 2018 was considered as the base year
2. Demand Equation (Green color font)
(ln_Qty_Ric_Dem_ds = {d0} + {eta} * (ln_RT_Ric_Prc * D18) + {eta03} * (ln_RT_Ric_Prc * D03) + {eta04} * (ln_RT_Ric_Prc * D04) + {eta05} * (ln_RT_Ric_Prc * D05) + {eta06} * (ln_RT_Ric_Prc * D06) + {eta07} * (ln_RT_Ric_Prc * D07) + {eta08} * (ln_RT_Ric_Prc * D08) + {eta09} * (ln_RT_Ric_Prc * D09) + {eta10} * (ln_RT_Ric_Prc * D10) + {eta11} * (ln_RT_Ric_Prc * D11) + {eta12} * (ln_RT_Ric_Prc * D12) + {eta13} * (ln_RT_Ric_Prc * D13) + {eta14} * (ln_RT_Ric_Prc * D14) + {eta15} * (ln_RT_Ric_Prc * D15) + {eta16} * (ln_RT_Ric_Prc * D16) + {eta17} * (ln_RT_Ric_Prc * D16) + {eta17} * (ln_RT_Ric_Prc * D17) + {d1} * ln_Mnth_HH_Incm + {d2} * ln_Pop + {d3} * ln_RT_Wht_Prc + {d4} * L_ln_Qty_Ric_Dem_ds)
Here the eta is known as own price elasticity of rice eta 03 to eta17 are own price elasticity of rice from 2003 to 2017 the particular year was indicated by dummy variables D03 to D17 and eta
3. Initial values (light green font color)
initial(a 0.1 bo 1 b1 1 b2 1 b3 1 b4 1 theta 0.001 eta -0.07 theta03 0.001 theta04 0.001 theta05 0.001 theta06 0.001 theta07 0.001 theta08 0.001 theta09 0.001 theta10 0.001 theta11 0.001 theta12 0.001 theta13 0.001 theta14 0.001 theta15 0.001 theta16 0.001 theta17 0.001 eta03 -0.07 eta04 -0.07 eta05 -0.07 eta06 -0.07 eta07 -0.07 eta08 -0.07 eta09 -0.07 eta10 -0.07 eta11 -0.07 eta12 -0.07 eta13 -0.07 eta14 -0.07 eta15 -0.07 eta16 -0.07 eta17 -0.07 d0 0.1 d1 1 d2 1)
When I run this code the result was :
could not evaluate equation 1
starting values invalid or some RHS variables have missing values
r(480);
Can anyone help to resolve this issue?
Related Posts with Issue in estimating non-linear seamingly unrealated regression
Export mdesc table to ExcelI am wondering if there is way to export (not copy paste) and mdesc table (run on the full set of my…
Compute the solution to the dual problem using LinearProgram() classHi! First of all, happy new year to everyone reading this post! I am fairly new to Mata and am usi…
Marginal effects for interaction after MlogitDear all, I'm new in this forum and also pretty new to Stata, so I don't know if my question is act…
Displaying mean values for groups on a lineHello Statalisters, I wish to display the means of a continuous variable for different values of a …
How many variables are necessary to carry out a logistic regression?Is it possible with only 2 events in the group of exposed (n=5) and 32 in the group of non-exposed (…
Subscribe to:
Post Comments (Atom)
0 Response to Issue in estimating non-linear seamingly unrealated regression
Post a Comment