Egwald Economics - Cost Functions: Generalized CES-Diewert Cost Function

Egwald Web Services
Domain Names
Web Site Design

Egwald Economics: Microeconomics

Cost Functions

by

Elmer G. Wiens

Egwald's popular web pages are provided without cost to users.
Follow Elmer Wiens on Twitter:

N. Generalized CES-Diewert (Generalized Leontief) Cost Function

This web page replicates the procedures used to estimate the parameters of a Diewert cost function to approximate a CES cost function. To determine the Diewert cost function's efficacy in estimating varying elasticities of substitution among pairs of inputs, on this web page we approximate a Generalized CES cost function with the Diewert cost function.

Unlike the CES cost function, the Generalized CES cost function is not necessarily homothetic, while the Diewert cost function is homothetic by construction. Moreover, the Generalized CES's elasticity of scale is a function of its factor inputs, i.e. its elasticity of scale, ε_LKM, varies with factor prices and with output.

Consequently, when we estimate the Diewert cost function, we need to estimate the parameter nu1 of its returns to scale function separately, as we did when we approximated the CES production function by the Diewert production function.

The three factor Diewert (Generalized Leontief) (total) cost function is:

C(q;wL,wK,wM) = h(q) * c(wL,wK,wM) (**)

where the returns to scale function is:

h(q) = q^^(1/nu1)

a continuous, increasing function of q (q >= 1), with h(0) = 0 and h(1) = 1, where nu1 is a measure of the returns to scale,

and the unit cost function is:

c(wL,wK,wM) = cLL * wL + cKK * wK + cMM * wM + (dLK+dKL) * (wL*wK)^^(1/2) + (dLM +dML) * (wL*wM)^^(1/2) + (dKM+dMK) * (wK*wM)^^(1/2)

linear in its parameters cLL, cKK, cMM, dLK, dKL, dLM, dML, dKM, and dMK.

We shall use two methods to obtain estimates of the parameters:

À1: Estimate the parameters the cost function by way of its factor share functions — requires data relating output quantities to (cost minimizing) factor inputs, and input prices,

À2: Estimate the parameters of the cost function directly — requires data relating output quantities to total (minimum) cost and input prices.

We shall use the three factor Generalized CES production function to generate the required cost data, yielding a data set relating output, q, and factor prices, wL, wK, and wM, [randomized about the base prices (wL*, wK*, wM*)] to the Generalized CES cost minimizing factor inputs, L, K, and M.

For methods À1, and À2, we shall set nu1 = ε_LKM where q = 30 units of output, i.e. at the elasticity of scale of the Generalized CES cost function for q = 30.

To illustrate what can happen when nu1 is set incorrectly, we shall repeat methods À1, and À2 as methods À3, and À4, with nu1 = 1, i.e. under the assumption of constant returns to scale along the domain of q.

The three factor Generalized CES production function is:

q = A * [alpha * L^^-rhoL + beta * K^^-rhoK + gamma *M^^-rhoM]^^(-nu/rho) = f(L,K,M).

where L = labour, K = capital, M = materials and supplies, and q = product.

The parameter nu permits one to adjust the returns to scale, while the parameter rho is the geometric mean of rhoL, rhoK, and rhoM:

rho = (rhoL * rhoK * rhoM)^^1/3.

If rho = rhoL = rhoK = rhoM, we get the standard CES production function. If also, rho = 0, ie sigma = 1/(1+rho) = 1, we get the Cobb-Douglas production function.

Generalized CES Elasticity of Scale of Production:

ε_LKM = ε(L,K,M) = (nu / rho) * (alpha * rhoL * L^^-rhoL + beta * rhoK * K^^-rhoK + gamma * rhoM * M^^-rhoM) / (alpha * L^^-rhoL + beta * K^^-rhoK + gamma * M^^-rhoM).

See the Generalized CES production function.

À1: Estimate the factor demand equations separately.

Assuming dLK = dKL, dLM = dML, and dKM = dMK, the Diewert unit cost function becomes:

c(wL,wK,wM) = cLL * wL + cKK * wK + cMM * wM + 2 * dLK * (wL*wK)^^(1/2) + 2 * dLM * (wL*wM)^^(1/2) + 2 * dKM * (wK*wM)^^(1/2)

Taking the partial derivative of the cost function with respect to an input price, we get the factor demand function for that input:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/nu1) * [cLL + dLK * (wK / wL)^^(1/2) + dLM * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/nu1) * [cKK + dKL * (wL / wK)^^(1/2) + dKM * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/nu1) * [cMM + dML * (wL / wM)^^(1/2) + dMK * (wK / wM)^^(1/2)]

Since it is likely that, as measured numerically, dLK != dKL, dLM != dML, and dKM != dMK, these distinctions are maintained in the factor demand equations.

After dividing each factor demand equation by q^(1/nu1), we can estimate the parameters of these three linear in parameters equations using linear multiple regression.

Having obtained the unrestricted estimates of the coefficients of the factor demand functions, we shall compute the restricted least squares estimates with dLK = dKL, dLM = dML, and dKM = dMK.

The substituted values of the estimated parameters determine the Diewert cost function.

I. Stage 1. Generate cost data with the Generalized CES production function, yielding a data set relating output, q, and factor prices, wL, wK, and wM, [randomized about the base prices (wL*, wK*, wM*)] to the Generalized CES cost minimizing factor inputs, L, K, and M. The base factor prices and the randomizing distribution are specified in the form below.

Stage 2. Obtain the Diewert cost function by substituting the estimates (obtained via linear multiple regression) of the parameters of the three factor demand equations into the cost function.

II. The estimated coefficients of the Diewert cost function will vary with the parameters nu, rho, rhoL, rhoK, rhoM, alpha, beta and gamma of the Generalized CES production function.

Set the parameters below to re-run with your own Generalized CES parameters.

The restrictions ensure that the least-cost problems can be solved to obtain the underlying Generalized CES cost function, using the parameters as specified.
Intermediate (and other) values of the parameters also work.

Restrictions:
.8 < nu < 1.1;
-.6 < rhoL = rho < .6;
-.6 < rho < -.2 → rhoK = .95 * rho, rhoM = rho/.95;
-.2 <= rho < -.1 → rhoK = .9 * rho, rhoM = rho / .9;
-.1 <= rho < 0 → rhoK = .87 * rho, rhoM = rho / .87;
0 <= rho < .1 → rhoK = .7 * rho, rhoM = rho / .7;
.1 <= rho < .2 → rhoK = .67 * rho, rhoM = rho / .67;
.2 <= rho < .6 → rhoK = .6 * rho, rhoM = rho / .6;
rho = 0 → nu = alpha + beta + gamma (Cobb-Douglas)
4 <= wL* <= 11, 7<= wK* <= 16, 4 <= wM* <= 10

Generalized CES Production Function Parameters

nu:

rho:

Base Factor Prices

wL*

wK*

wM*

Distribution to Randomize Factor Prices

Use [-2, 2] Uniform distribution
Use .25 * Normal (μ = 0, σ² = 1)

The Generalized CES production function as specified:

q = 1 * [0.35 * L^^{- 0.17647} + 0.4 * K^^{- 0.11823} + 0.25 *M^^{- 0.26339}]^^(-1/0.17647) = f(L,K,M).

The factor prices are distributed about the base factor prices by adding a random number distributed uniformly in the [-2, 2] domain.

Generalized CES elasticity of scale at q = 30: ε_LKM = nu1 = 0.92

III. For these coefficients of the CES Generalized production function, I generated a sequence (displayed in the "Generalized CES-Diewert Cost Function" table) of factor prices, outputs, and the corresponding cost minimizing inputs. Then I used these data to estimate the coefficients of each factor share equation separately:

QR Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cLL	-0.111331	0.004	-30.471
dLK	0.532179	0.004	146.879
dLM	0.511219	0.003	161.035

R2 = 0.9998

R2b = 0.9998

# obs = 31

QR Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cKK	0.00142	0.027	0.053
dKL	0.458881	0.028	16.515
dKM	0.387237	0.023	16.743

R2 = 0.9495

R2b = 0.9458

# obs = 31

QR Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cMM	-0.129224	0.033	-3.926
dML	0.618911	0.041	15.058
dMK	0.307136	0.04	7.745

R2 = 0.9817

R2b = 0.9804

# obs = 31

The three estimated factor demand functions are:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/0.92) * [-0.1113 + 0.5322 * (wK / wL)^^(1/2) + 0.5112 * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/0.92) * [0.0014 + 0.4589 * (wL / wK)^^(1/2) + 0.3872 * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/0.92) * [-0.1292 + 0.6189 * (wL / wM)^^(1/2) + 0.3071 * (wK / wM)^^(1/2)]

As estimated, generally dLK != dKL, dLM != dML, and dKM != dMK: Young's Theorem doesn't hold without constraints across equations. Consequently, I use the sum of the cross parameters in the Diewert cost function.

The estimated factor demand elasticities are obtained by:

ε_L,wL = ∂ln(L(q;wL,wK,wM))/∂ln(wL) = -.5 * (q^^1/nu1) / L(q;wL,wK,wM)) * (dLK * (wK/wL)^^1/2 + dLM * (wM/wL)^^1/2),

ε_L,wK = ∂ln(L(q;wL,wK,wM))/∂ln(wK) = .5 * (q^^1/nu1) / L(q;wL,wK,wM)) * dLK * (wK/wL)^^1/2,

ε_L,wM = ∂ln(L(q;wL,wK,wM))/∂ln(wM) = .5 * (q^^1/nu1) / L(q;wL,wK,wM)) * dLM * (wM/wL)^^1/2,

ε_L,q = ∂ln(L(q;wL,wK,wM))/∂ln(q) = 1/nu1, etc.

For example, with wL = 7, wK = 13, wM = 6, and q = 30:

ε_L,wL	ε_L,wK	ε_L,wM	ε_L,q
ε_K,wL	ε_K,wK	ε_K,wM	ε_K,q
ε_M,wL	ε_M,wK	ε_M,wM	ε_M,q

-0.5512	0.3335	0.2177	1.087
0.28	-0.4988	0.2188	1.087
0.3372	0.228	-0.5652	1.087

IV. The Diewert cost function as obtained from the unrestricted factor demand equations is:

C(q;wL,wK,wM) = q^^(1/nu1) * [cLL * wL + cKK * wK + cMM * wM + (dLK+dKL) * (wL*wK)^^(1/2) + (dLM +dML) * (wL*wM)^^(1/2) + (dKM+dMK) * (wK*wM)^^(1/2)]

= q^^(1/0.92) * [-0.11133 * wL + 0.00142 * wK + -0.12922 * wM + 0.99106 * (wL*wK)^^(1/2) + 1.13013 * (wL*wM)^^(1/2) + 0.69437 * (wK*wM)^^(1/2)] (***)

V. The Restricted Factor Demand Equations.

Having obtained the unrestricted estimates of the coefficients of the factor demand functions, we compute the restricted least squares estimates with dLK = dKL, dLM = dML, and dKM = dMK.

QR Restricted Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cLL	-0.095005	0.025386	-3.742372
dLK	0.487991	0.021177	23.043632
dLM	0.557448	0.01661	33.560983
cKK	-0.002543	0.022831	-0.111403
dKL	0.487991	0.021177	23.043632
dKM	0.361776	0.017656	20.489825
cMM	-0.142184	0.02036	-6.983352
dML	0.557448	0.01661	33.560983
dMK	0.361776	0.017656	20.489825

R2 = 0.9971

R2b = 0.9968

# obs = 93

dLK = dKL, dLM = dML, and dKM = dMK

The three estimated, restricted factor demand functions are:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/0.92) * [-0.095 + 0.488 * (wK / wL)^^(1/2) + 0.5574 * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/0.92) * [-0.0025 + 0.488 * (wL / wK)^^(1/2) + 0.3618 * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/0.92) * [-0.1422 + 0.5574 * (wL / wM)^^(1/2) + 0.3618 * (wK / wM)^^(1/2)]

The estimated factor demand elasticities are obtained by:

For example, with wL = 7, wK = 13, wM = 6, and q = 30:

ε_L,wL	ε_L,wK	ε_L,wM	ε_L,q
ε_K,wL	ε_K,wK	ε_K,wM	ε_K,q
ε_M,wL	ε_M,wK	ε_M,wM	ε_M,q

-0.5437	0.3061	0.2376	1.087
0.2978	-0.5021	0.2044	1.087
0.3033	0.2683	-0.5716	1.087

VI. The Diewert cost function as obtained from the restricted factor demand equations is:

C(q;wL,wK,wM) = q^^(1/nu) * [cLL * wL + cKK * wK + cMM * wM + (dLK+dKL) * (wL*wK)^^(1/2) + (dLM +dML) * (wL*wM)^^(1/2) + (dKM+dMK) * (wK*wM)^^(1/2)]

= q^^(1/0.92) * [-0.095 * wL + -0.00254 * wK + -0.14218 * wM + 0.97598 * (wL*wK)^^(1/2) + 1.1149 * (wL*wM)^^(1/2) + 0.72355 * (wK*wM)^^(1/2)] (***)

VII. Note:
1. C(q;wL,wK,wM) linear homogeneous in factor prices requires for any t > 0 that the unit cost function c(wL,wK,wM) obey:

c(t*wL,t*wK,t*wM) = t * c(wL,wK,wM).

For example, with wL = 7, wK = 13, wM = 6, and t = 2:

2 * c(7, 13, 6) = 42.75 = 42.75 = c(14, 26,12).

2. The matrix ∇²C of second order partial derivatives of the cost function C(q;wL,wK,wM) = h(q)*c(wL,wK,wM) is symmetric:

∂²C/∂q∂wL = h'(q) * ∂c/∂wL = ∂²C/∂wL∂q,

∂²C/∂q∂wK = h'(q) * ∂c/∂wK = ∂²C/∂wK∂q,

∂²C/∂q∂wM = h'(q) * ∂c/∂wM = ∂²C/∂wM∂q,

∂²c/∂wL∂wK = .25 * (dLK+dKL)/(wL*wK)^^(1/2) = ∂²c/∂wK∂wL,

∂²c/∂wL∂wM = .25 * (dLM+dML)/(wL*wM)^^(1/2) = ∂²c/∂wM∂wL,

∂²c/∂wK∂wM = .25 * (dKM+dMK)/(wL*wK)^^(1/2) = ∂²c/∂wM∂wK, and

∂²c/∂wL∂wL = -.25((dLK+dKL)*wK^^(1/2) + (dLM+dML)*wM^^(1/2))/wL^^(3/2),

∂²c/∂wK∂wK = -.25((dKL+dLK)*wL^^(1/2) + (dKM+dMK)*wM^^(1/2))/wK^^(3/2),

∂²c/∂wM∂wM = -.25((dML+dLM)*wL^^(1/2) + (dMK+dKM)*wK^^(1/2))/wM^^(3/2).

3. The cost function C(q;wL,wK,wM) is a concave in factor prices if the Hessian matrix H = ∇²_wwc(wL,wK,wM) of second order partial derivatives with respect to factor prices is negative semidefinite. The values of the second order partial derivatives depend on factor prices. As an example, consider the case where wL = 7, wK = 13, and wM = 6:

H = ∇²_wwc =

-0.08437	0.02558	0.04301
0.02558	-0.02323	0.02048
0.04301	0.02048	-0.09455

The principal minors of H are H1 = -0.084365, H2 = 0.001305, and H3 = 0.

If these principal minors alternate in sign, starting with negative, with H3 <= 0, the matrix H is negative (semi)definite,
and the cost function C(q;wL,wK,wM) is a concave function in factor prices at wL = 7, wK = 13, and wM = 6.

The eigenvalues of H are e1 = -0.1328, e2 = -0.0693, and e3 = 0.
H3 = e1 * e2 * e3 = 0.

VIII. The factor share functions are:

sL(q;wL,wK,wM) = wL * L(q; wL, wK, wM) / C(q;wL,wK,wM) = wL * ∂C/∂wL / C(q;wL,wK,wM) ,

sK(q;wL,wK,wM)= wK * K(q; wL, wK, wM) / C(q;wL,wK,wM) = wK * ∂C/∂wK / C(q;wL,wK,wM),

sM(q;wL,wK,wM)= wM * M(q; wL, wK, wM) / C(q;wL,wK,wM) = wM * ∂C/∂wM / C(q;wL,wK,wM).

IX. Uzawa Partial Elasticities of Substitution:

u_LK = C(q;wL,wK,wM) * ∂L(q;wL,wK,wM)/∂wK / (L(q;wL,wK,wM) * K(q;wL,wK,wM)),

u_LM = C(q;wL,wK,wM) * ∂L(q;wL,wK,wM)/∂wM / (L(q;wL,wK,wM) * M(q;wL,wK,wM)),

u_KL = C(q;wL,wK,wM) * ∂K(q;wL,wK,wM)/∂wL / (K(q;wL,wK,wM) * L(q;wL,wK,wM)),

u_KM = C(q;wL,wK,wM) * ∂K(q;wL,wK,wM)/∂wM / (K(q;wL,wK,wM) * M(q;wL,wK,wM)),

u_ML = C(q;wL,wK,wM) * ∂M(q;wL,wK,wM)/∂wL / (M(q;wL,wK,wM) * L(q;wL,wK,wM)),

u_MK = C(q;wL,wK,wM) * ∂M(q;wL,wK,wM)/∂wK / (M(q;wL,wK,wM) * M(q;wL,wK,wM)),

Imposing the dLK = dKL, dLM = dML, and dKM = dMK restrictions in the factor demand functions, we get (approximate?) equality of the cross partial elasticities of substitution:

u_LK = u_KL, u_LM = u_ML, and u_KM = u_MK.

as seen in the following table.

X. Table of Results: check that the estimated Diewert cost function and input amounts for a given level of output agree with the Generalized CES production function's minimized cost and inputs. Also, compare the Allen partial elasticities of substitution, s_LK, s_LM, and s_MK, with the Uzawa partial elasticities of substitution, u_LK, u_LM, and u_KM.

Generalized CES-Diewert Cost Function À1: Estimate the Translog cost function using restricted factor shares Parameters: rho = 0.17647, rhoL = 0.17647, rhoK = 0.11823, rhoM = 0.26339
					nu = 1 — Generalized CES Cost Data —								nu1 = 0.92 — Diewert Cost Data —				Factor Shares			Uzawa Elasticities						∇²_wwc(w)
obs #	q	wL	wK	wM	L	K	M	s_LK	s_LM	s_KM	ε_LKM	cost	est cost	est L	est K	est M	sL	sK	sM	u_LK	u_LM	u_KL	u_KM	u_ML	u_MK	e₁	e₂	e₃
1	18	8.36	11.3	7.84	23.28	16.5	20.75	0.9	0.79	0.84	0.934	543.76	541.2	23.43	16.63	20.08	0.362	0.347	0.291	0.81	0.92	0.81	0.72	0.92	0.72	-0.1	-0.062	-0
2	19	6.62	11.18	4.82	24.95	14.54	27.04	0.9	0.79	0.83	0.925	458.12	458.07	24.91	14.98	26.07	0.36	0.366	0.274	0.85	0.85	0.85	0.71	0.85	0.71	-0.158	-0.078	-0
3	20	8.14	14.92	6.44	27.59	15.02	27.8	0.9	0.79	0.83	0.924	627.72	627.85	27.55	15.46	26.86	0.357	0.367	0.276	0.85	0.85	0.85	0.72	0.85	0.72	-0.121	-0.061	-0
4	21	8.84	12.46	5.92	25.77	17.68	29.77	0.9	0.79	0.83	0.925	624.41	624.18	25.74	18	29.11	0.365	0.359	0.276	0.86	0.88	0.86	0.69	0.88	0.69	-0.125	-0.062	0
5	22	8.78	13.98	6.12	28.42	17.58	31.6	0.89	0.79	0.83	0.923	688.74	689.04	28.39	17.95	30.87	0.362	0.364	0.274	0.86	0.86	0.86	0.7	0.86	0.7	-0.123	-0.06	-0
6	23	5.76	13.3	7.04	38.19	17.21	26.68	0.9	0.79	0.83	0.926	636.64	636.24	38.15	17.58	25.96	0.345	0.367	0.287	0.8	0.85	0.8	0.79	0.85	0.79	-0.146	-0.065	0
7	24	7.52	12.5	5.06	31.43	18.8	35.68	0.89	0.79	0.83	0.921	651.91	652.68	31.37	19.18	34.99	0.361	0.367	0.271	0.86	0.85	0.86	0.7	0.85	0.7	-0.15	-0.07	-0
8	25	8.92	14.28	5.08	31.3	19.37	40.57	0.89	0.79	0.83	0.918	761.88	763.26	31.19	19.81	39.79	0.365	0.371	0.265	0.88	0.84	0.88	0.68	0.84	0.68	-0.152	-0.06	-0
9	26	5.34	13.9	7.38	46.66	19.08	29.17	0.9	0.79	0.83	0.924	729.64	729.79	46.51	19.45	28.6	0.34	0.37	0.289	0.79	0.84	0.79	0.81	0.84	0.81	-0.159	-0.062	-0
10	27	7.46	12.5	6.5	37.92	22.75	34.64	0.9	0.79	0.83	0.923	792.38	792.78	38.01	22.85	34.4	0.358	0.36	0.282	0.83	0.87	0.83	0.73	0.87	0.73	-0.121	-0.066	-0
11	28	7.2	11.08	7.56	40.05	26	31.45	0.9	0.79	0.83	0.928	814.25	814.72	40.46	25.8	31.42	0.358	0.351	0.292	0.8	0.91	0.8	0.74	0.91	0.74	-0.113	-0.065	-0
12	29	7.5	12.62	7.12	41.83	25.13	35.47	0.9	0.79	0.83	0.924	883.34	883.95	42.02	25.08	35.43	0.357	0.358	0.285	0.82	0.88	0.82	0.74	0.88	0.74	-0.115	-0.063	0
13	30	7	13	6	43.79	24.14	40.13	0.89	0.79	0.83	0.92	861.17	861.92	43.8	24.25	40.02	0.356	0.366	0.279	0.84	0.85	0.84	0.73	0.85	0.73	-0.133	-0.069	0
14	31	7	13.5	6.36	46.54	24.89	40.56	0.89	0.79	0.83	0.92	919.69	920.47	46.55	24.95	40.52	0.354	0.366	0.28	0.83	0.85	0.83	0.74	0.85	0.74	-0.129	-0.067	-0
15	32	7.26	12.72	6.14	45.96	26.76	42.42	0.89	0.79	0.83	0.92	934.47	935.25	46	26.71	42.59	0.357	0.363	0.28	0.84	0.86	0.84	0.73	0.86	0.73	-0.128	-0.068	-0
16	33	7.84	11.56	4.96	42.18	28.53	49.28	0.89	0.79	0.83	0.917	904.92	905.39	42.08	28.46	49.69	0.364	0.363	0.272	0.87	0.87	0.87	0.68	0.87	0.68	-0.151	-0.069	-0
17	34	6.04	11.86	7.56	55.64	29.55	37.17	0.9	0.79	0.83	0.924	967.52	968.68	56.02	29.32	37.39	0.349	0.359	0.292	0.79	0.88	0.79	0.78	0.88	0.78	-0.135	-0.063	-0
18	35	7.2	12.28	7.28	52.25	31.37	41.51	0.89	0.79	0.83	0.922	1063.68	1065.15	52.58	30.98	42.06	0.355	0.357	0.287	0.81	0.88	0.81	0.75	0.88	0.75	-0.117	-0.064	0
19	36	7.96	13.76	5.42	49.64	29.37	54.11	0.89	0.79	0.83	0.914	1092.51	1092.58	49.49	29.28	54.56	0.361	0.369	0.271	0.86	0.84	0.86	0.7	0.84	0.7	-0.141	-0.065	-0
20	37	7.46	14.6	7.7	58.32	31.14	45.24	0.89	0.79	0.83	0.919	1238.11	1239.19	58.45	30.85	45.82	0.352	0.363	0.285	0.81	0.86	0.81	0.76	0.86	0.76	-0.114	-0.059	-0
21	38	6.24	11.94	7.18	61.07	33.35	43.32	0.89	0.79	0.83	0.921	1090.37	1091.89	61.42	32.89	44.01	0.351	0.36	0.289	0.8	0.88	0.8	0.77	0.88	0.77	-0.132	-0.065	-0
22	39	6.34	14.22	7.54	66.68	31.74	45.81	0.89	0.79	0.83	0.918	1219.51	1220.48	66.7	31.47	46.43	0.347	0.367	0.287	0.8	0.85	0.8	0.78	0.85	0.78	-0.132	-0.061	-0
23	40	9	12.86	4.76	49.61	34.8	66.06	0.89	0.79	0.83	0.912	1208.51	1206.94	49.27	34.5	67.2	0.367	0.368	0.265	0.89	0.86	0.89	0.66	0.86	0.66	-0.161	-0.061	-0
24	41	7.4	13.04	6.22	60.24	35.39	54.84	0.89	0.79	0.83	0.916	1248.31	1248.46	60.24	34.82	56.04	0.357	0.364	0.279	0.84	0.86	0.84	0.73	0.86	0.73	-0.126	-0.067	0
25	42	5.46	13.96	5.54	72.95	31.03	56.47	0.89	0.79	0.83	0.912	1144.33	1143.64	72.48	30.84	57.29	0.346	0.376	0.278	0.83	0.81	0.83	0.77	0.81	0.77	-0.165	-0.079	-0
26	43	5.86	13.1	7.76	75.9	36.48	47.46	0.89	0.79	0.83	0.919	1290.89	1292.38	76.1	35.92	48.44	0.345	0.364	0.291	0.79	0.86	0.79	0.79	0.86	0.79	-0.141	-0.06	-0
27	44	7.3	13.46	4.22	61.09	34.49	74.72	0.89	0.79	0.83	0.908	1225.44	1222.16	60.62	34.2	75.64	0.362	0.377	0.261	0.89	0.82	0.89	0.69	0.82	0.69	-0.187	-0.072	0
28	45	7.88	14.34	4.2	61.32	35.04	79.97	0.89	0.79	0.83	0.906	1321.52	1317.15	60.79	34.77	80.82	0.364	0.379	0.258	0.9	0.81	0.9	0.68	0.81	0.68	-0.191	-0.067	-0
29	46	6.28	11.16	6.06	70.57	41.49	56.98	0.89	0.79	0.83	0.916	1251.45	1252.13	70.79	40.44	58.8	0.355	0.36	0.285	0.82	0.87	0.82	0.74	0.87	0.74	-0.137	-0.074	-0
30	47	5.4	12.52	6.98	84.18	39.37	53.28	0.89	0.79	0.83	0.917	1319.43	1320.12	84.2	38.63	54.7	0.344	0.366	0.289	0.79	0.85	0.79	0.79	0.85	0.79	-0.155	-0.066	-0
31	48	6.7	13.28	5.14	73.01	39	70.52	0.89	0.79	0.83	0.91	1369.56	1366.09	72.61	38.25	72.3	0.356	0.372	0.272	0.86	0.83	0.86	0.73	0.83	0.73	-0.153	-0.075	-0
AVE:	33	7.16	12.94	6.25	49.29	27.24	44.45	0.89	0.79	0.83	0.92	964.01	963.99	49.29	27.24	44.45	0.356	0.365	0.279	0.83	0.86	0.83	0.73	0.86	0.73	-0.139	-0.066	-0

À2: Estimate the Diewert cost function directly.

XI. If we have a data set relating the input (factor) prices, wL, wK, and wM, to the total (minimum) cost of producing output for varying levels output, but do not have data on the required levels of inputs, we can estimate the Diewert cost function directly. We will use the same sequence (displayed in the "Diewert Cost Function" table) of factor prices, outputs, and total (minimum) cost as used in À1. The estimated coefficients of the cost function will vary with the parameters nu, rho, rhoL, rhoK, rhoM, alpha, beta and gamma of the Generalized CES production function used to generate these data.

QR Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cLL	0.082054	0.071	1.156
cKK	0.295149	0.054	5.5
cMM	0.00813	0.055	0.148
2*dLK	0.550351	0.113	4.872
2*dLM	1.353231	0.084	16.154
2*dKM	0.326039	0.079	4.141

R2 = 0.9998

R2b = 0.9998

# obs = 31

The Diewert cost function as obtained by direct estimation is:

C(q;wL,wK,wM) = q^^(1/nu1) * [cLL * wL + cKK * wK + cMM * wM + 2 * dLK * (wL*wK)^^(1/2) + 2 * dLM * (wL*wM)^^(1/2) + 2 * dKM * (wK*wM)^^(1/2)]

= q^^(1/0.92) * [0.08205 * wL + 0.29515 * wK + 0.00813 * wM + 0.55035 * (wL*wK)^^(1/2) + 1.35323 * (wL*wM)^^(1/2) + 0.32604 * (wK*wM)^^(1/2)] (***)

XII. Its three derived factor demand functions are:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/0.92) * [0.0821 + 0.2752 * (wK / wL)^^(1/2) + 0.6766 * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/0.92) * [0.2951 + 0.2752 * (wL / wK)^^(1/2) + 0.163 * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/0.92) * [0.0081 + 0.6766 * (wL / wM)^^(1/2) + 0.163 * (wK / wM)^^(1/2)]

The derived factor demand elasticities are obtained by:

For example, with wL = 7, wK = 13, wM = 6, and q = 30:

ε_L,wL	ε_L,wK	ε_L,wM	ε_L,q
ε_K,wL	ε_K,wK	ε_K,wM	ε_K,q
ε_M,wL	ε_M,wK	ε_M,wM	ε_M,q

-0.4621	0.1731	0.2891	1.087
0.1661	-0.2572	0.0911	1.087
0.3733	0.1226	-0.4958	1.087

XIII. Notes:
1. As derived, dLK = dKL, dLM = dML, and dKM = dMK: Young's Theorem holds by construction.

2. C(q;wL,wK,wM) linear homogeneous in factor prices requires for any t > 0 that the unit cost function c(wL,wK,wM) obey:

c(t*wL,t*wK,t*wM) = t * c(wL,wK,wM).

For example, with wL = 7, wK = 13, wM = 6, and t = 2:

2 * c(7, 13, 6) = 42.72 = 42.72 = c(14, 26,12).

3. The matrix ∇²C of second order partial derivatives of the cost function C(q;wL,wK,wM) = h(q)*c(wL,wK,wM) is symmetric.

4. The cost function C(q;wL,wK,wM) is a concave in factor prices if the Hessian matrix H = ∇²_wwc(wL,wK,wM) of second order partial derivatives with respect to factor prices is negative semidefinite. The values of the second order partial derivatives depend on factor prices. As an example, consider the case where wL = 7, wK = 13, and wM = 6:

H = ∇²_wwc =

-0.07153	0.01442	0.0522
0.01442	-0.01203	0.00923
0.0522	0.00923	-0.0809

The principal minors of H are H1 = -0.07153, H2 = 0.000652, and H3 = 0.

If these principal minors alternate in sign, starting with negative, with H3 <= 0, the matrix H is negative (semi)definite,
and the cost function C(q;wL,wK,wM) is a concave function in factor prices at wL = 7, wK = 13, and wM = 6.

The eigenvalues of H are e1 = -0.1287, e2 = -0.0358, and e3 = 0.
H3 = e1 * e2 * e3 = 0.

XIV. Table of Results: check that the estimated Diewert cost function and input amounts for a given level of output agree with the Generalized CES production function's minimized cost and inputs. Also, compare the Allen partial elasticities of substitution, s_LK, s_LM, and s_MK, with the Uzawa partial elasticities of substitution, u_LK, u_LM, and u_KM.

Generalized CES-Diewert Cost Function À2: Estimate the Diewert cost function directly Parameters: rho = 0.17647, rhoL = 0.17647, rhoK = 0.11823, rhoM = 0.26339
					nu = 1 — Generalized CES Cost Data —								nu1 = 0.92 — Diewert Cost Data —				Factor Shares			Uzawa Elasticities						∇²_wwc(w)
obs #	q	wL	wK	wM	L	K	M	s_LK	s_LM	s_KM	ε_LKM	cost	est cost	est L	est K	est M	sL	sK	sM	u_LK	u_LM	u_KL	u_KM	u_ML	u_MK	e₁	e₂	e₃
1	18	8.36	11.3	7.84	23.28	16.5	20.75	0.9	0.79	0.84	0.934	543.76	542.9	24.47	15.45	20.89	0.377	0.322	0.302	0.47	1.03	0.47	0.34	1.03	0.34	-0.1	-0.032	-0
2	19	6.62	11.18	4.82	24.95	14.54	27.04	0.9	0.79	0.83	0.925	458.12	457.86	24.96	15.07	25.76	0.361	0.368	0.271	0.48	1.05	0.48	0.32	1.05	0.32	-0.152	-0.041	-0
3	20	8.14	14.92	6.44	27.59	15.02	27.8	0.9	0.79	0.83	0.924	627.72	627.58	27.42	15.71	26.39	0.356	0.374	0.271	0.47	1.05	0.47	0.33	1.05	0.33	-0.117	-0.032	-0
4	21	8.84	12.46	5.92	25.77	17.68	29.77	0.9	0.79	0.83	0.925	624.41	624.38	26.34	17.49	29.32	0.373	0.349	0.278	0.49	1.03	0.49	0.32	1.03	0.32	-0.121	-0.033	0
5	22	8.78	13.98	6.12	28.42	17.58	31.6	0.89	0.79	0.83	0.923	688.74	688.78	28.62	17.88	30.65	0.365	0.363	0.272	0.48	1.04	0.48	0.32	1.04	0.32	-0.118	-0.032	-0
6	23	5.76	13.3	7.04	38.19	17.21	26.68	0.9	0.79	0.83	0.926	636.64	635.74	37.71	17.97	25.5	0.342	0.376	0.282	0.45	1.06	0.45	0.35	1.06	0.35	-0.138	-0.034	-0
7	24	7.52	12.5	5.06	31.43	18.8	35.68	0.89	0.79	0.83	0.921	651.91	652.53	31.38	19.37	34.46	0.362	0.371	0.267	0.48	1.05	0.48	0.32	1.05	0.32	-0.143	-0.037	-0
8	25	8.92	14.28	5.08	31.3	19.37	40.57	0.89	0.79	0.83	0.918	761.88	763.56	31.12	20.17	38.96	0.364	0.377	0.259	0.49	1.05	0.49	0.31	1.05	0.31	-0.142	-0.032	-0
9	26	5.34	13.9	7.38	46.66	19.08	29.17	0.9	0.79	0.83	0.924	729.64	729.65	45.61	20.17	27.87	0.334	0.384	0.282	0.44	1.07	0.44	0.36	1.07	0.36	-0.148	-0.033	-0
10	27	7.46	12.5	6.5	37.92	22.75	34.64	0.9	0.79	0.83	0.923	792.38	792.25	38.47	22.49	34.49	0.362	0.355	0.283	0.47	1.04	0.47	0.33	1.04	0.33	-0.118	-0.034	-0
11	28	7.2	11.08	7.56	40.05	26	31.45	0.9	0.79	0.83	0.928	814.25	815.78	41.78	24.38	32.39	0.369	0.331	0.3	0.46	1.03	0.46	0.34	1.03	0.34	-0.111	-0.034	0
12	29	7.5	12.62	7.12	41.83	25.13	35.47	0.9	0.79	0.83	0.924	883.34	883.48	42.68	24.47	35.74	0.362	0.35	0.288	0.46	1.04	0.46	0.34	1.04	0.34	-0.112	-0.033	0
13	30	7	13	6	43.79	24.14	40.13	0.89	0.79	0.83	0.92	861.17	861.31	43.69	24.51	39.47	0.355	0.37	0.275	0.47	1.05	0.47	0.33	1.05	0.33	-0.129	-0.036	0
14	31	7	13.5	6.36	46.54	24.89	40.56	0.89	0.79	0.83	0.92	919.69	919.78	46.35	25.29	39.93	0.353	0.371	0.276	0.46	1.05	0.46	0.33	1.05	0.33	-0.125	-0.035	0
15	32	7.26	12.72	6.14	45.96	26.76	42.42	0.89	0.79	0.83	0.92	934.47	934.51	46.22	26.66	42.33	0.359	0.363	0.278	0.47	1.05	0.47	0.33	1.05	0.33	-0.125	-0.035	0
16	33	7.84	11.56	4.96	42.18	28.53	49.28	0.89	0.79	0.83	0.917	904.92	905.36	42.69	28.11	49.54	0.37	0.359	0.271	0.49	1.04	0.49	0.31	1.04	0.31	-0.144	-0.037	-0
17	34	6.04	11.86	7.56	55.64	29.55	37.17	0.9	0.79	0.83	0.924	967.52	967.78	56.58	28.72	37.75	0.353	0.352	0.295	0.45	1.05	0.45	0.35	1.05	0.35	-0.129	-0.033	-0
18	35	7.2	12.28	7.28	52.25	31.37	41.51	0.89	0.79	0.83	0.922	1063.68	1064.66	53.49	30.1	42.57	0.362	0.347	0.291	0.46	1.04	0.46	0.34	1.04	0.34	-0.114	-0.033	0
19	36	7.96	13.76	5.42	49.64	29.37	54.11	0.89	0.79	0.83	0.914	1092.51	1092.51	49.27	29.83	53.48	0.359	0.376	0.265	0.48	1.05	0.48	0.32	1.05	0.32	-0.134	-0.034	-0
20	37	7.46	14.6	7.7	58.32	31.14	45.24	0.89	0.79	0.83	0.919	1238.11	1237.88	58.47	30.91	45.51	0.352	0.365	0.283	0.46	1.05	0.46	0.34	1.05	0.34	-0.11	-0.03	-0
21	38	6.24	11.94	7.18	61.07	33.35	43.32	0.89	0.79	0.83	0.921	1090.37	1090.81	61.97	32.35	44.27	0.354	0.354	0.291	0.45	1.05	0.45	0.35	1.05	0.35	-0.127	-0.034	-0
22	39	6.34	14.22	7.54	66.68	31.74	45.81	0.89	0.79	0.83	0.918	1219.51	1219.38	66.08	32.05	45.72	0.344	0.374	0.283	0.45	1.06	0.45	0.35	1.06	0.35	-0.126	-0.032	0
23	40	9	12.86	4.76	49.61	34.8	66.06	0.89	0.79	0.83	0.912	1208.51	1207.39	49.78	34.43	66.51	0.371	0.367	0.262	0.5	1.04	0.5	0.3	1.04	0.3	-0.151	-0.033	-0
24	41	7.4	13.04	6.22	60.24	35.39	54.84	0.89	0.79	0.83	0.916	1248.31	1247.5	60.46	34.83	55.62	0.359	0.364	0.277	0.47	1.05	0.47	0.33	1.05	0.33	-0.123	-0.034	0
25	42	5.46	13.96	5.54	72.95	31.03	56.47	0.89	0.79	0.83	0.912	1144.33	1146.79	69.97	33.13	54.56	0.333	0.403	0.264	0.45	1.07	0.45	0.34	1.07	0.34	-0.156	-0.041	-0
26	43	5.86	13.1	7.76	75.9	36.48	47.46	0.89	0.79	0.83	0.919	1290.89	1290.82	75.86	36.06	48.18	0.344	0.366	0.29	0.44	1.06	0.44	0.36	1.06	0.36	-0.133	-0.032	-0
27	44	7.3	13.46	4.22	61.09	34.49	74.72	0.89	0.79	0.83	0.908	1225.44	1224.7	59.32	36.02	72.71	0.354	0.396	0.251	0.49	1.06	0.49	0.31	1.06	0.31	-0.173	-0.039	-0
28	45	7.88	14.34	4.2	61.32	35.04	79.97	0.89	0.79	0.83	0.906	1321.52	1320.73	59.35	36.8	77.45	0.354	0.4	0.246	0.49	1.06	0.49	0.3	1.06	0.3	-0.175	-0.036	-0
29	46	6.28	11.16	6.06	70.57	41.49	56.98	0.89	0.79	0.83	0.916	1251.45	1251.04	71.46	39.9	58.92	0.359	0.356	0.285	0.46	1.05	0.46	0.34	1.05	0.34	-0.134	-0.038	-0
30	47	5.4	12.52	6.98	84.18	39.37	53.28	0.89	0.79	0.83	0.917	1319.43	1318.8	83.45	39.26	53.97	0.342	0.373	0.286	0.44	1.06	0.44	0.36	1.06	0.36	-0.146	-0.035	-0
31	48	6.7	13.28	5.14	73.01	39	70.52	0.89	0.79	0.83	0.91	1369.56	1366.89	71.38	39.79	70.08	0.35	0.387	0.264	0.47	1.06	0.47	0.33	1.06	0.33	-0.146	-0.039	-0
AVE:	33	7.16	12.94	6.25	49.24	27.4	43.9	0.89	0.79	0.83	0.92	964.01	963.97	49.24	27.4	43.9	0.356	0.366	0.277	0.47	1.05	0.47	0.33	1.05	0.33	-0.133	-0.034	-0

The Generalized CES production function as specified:

q = 1 * [0.35 * L^^{- 0.17647} + 0.4 * K^^{- 0.11823} + 0.25 *M^^{- 0.26339}]^^(-1/0.17647) = f(L,K,M).

À3: Estimate the factor demand equations separately, with nu1 = 1.

XVI. For these coefficients of the CES Generalized production function, I generated a sequence (displayed in the "Generalized CES-Diewert Cost Function" table) of factor prices, outputs, and the corresponding cost minimizing inputs. Then I used these data to estimate the coefficients of each factor share equation separately:

QR Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cLL	-0.319947	0.075	-4.293
dLK	0.888702	0.074	12.025
dLM	0.627837	0.065	9.696

R2 = 0.9627

R2b = 0.9601

# obs = 31

QR Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cKK	0.152282	0.092	1.662
dKL	0.470032	0.095	4.959
dKM	0.466891	0.079	5.918

R2 = 0.6696

R2b = 0.646

# obs = 31

QR Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cMM	-0.260305	0.012	-21.391
dML	0.676227	0.015	44.504
dMK	0.592572	0.015	40.419

R2 = 0.9986

R2b = 0.9986

# obs = 31

The three estimated factor demand functions are:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/1) * [-0.3199 + 0.8887 * (wK / wL)^^(1/2) + 0.6278 * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/1) * [0.1523 + 0.47 * (wL / wK)^^(1/2) + 0.4669 * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/1) * [-0.2603 + 0.6762 * (wL / wM)^^(1/2) + 0.5926 * (wK / wM)^^(1/2)]

The estimated factor demand elasticities are obtained by:

For example, with wL = 7, wK = 13, wM = 6, and q = 30:

ε_L,wL	ε_L,wK	ε_L,wM	ε_L,q
ε_K,wL	ε_K,wK	ε_K,wM	ε_K,q
ε_M,wL	ε_M,wK	ε_M,wM	ε_M,q

-0.6086	0.4113	0.1974	1
0.2118	-0.4065	0.1947	1
0.2721	0.3249	-0.597	1

XVII. The Diewert cost function as obtained from the unrestricted factor demand equations is:

C(q;wL,wK,wM) = q^^(1/nu1) * [cLL * wL + cKK * wK + cMM * wM + (dLK+dKL) * (wL*wK)^^(1/2) + (dLM +dML) * (wL*wM)^^(1/2) + (dKM+dMK) * (wK*wM)^^(1/2)]

= q^^(1/1) * [-0.31995 * wL + 0.15228 * wK + -0.2603 * wM + 1.35873 * (wL*wK)^^(1/2) + 1.30406 * (wL*wM)^^(1/2) + 1.05946 * (wK*wM)^^(1/2)] (***)

XVIII. The Restricted Factor Demand Equations.

Having obtained the unrestricted estimates of the coefficients of the factor demand functions, we compute the restricted least squares estimates with dLK = dKL, dLM = dML, and dKM = dMK.

QR Restricted Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cLL	-0.207589	0.050251	-4.131079
dLK	0.7465	0.041918	17.808517
dLM	0.713019	0.032878	21.686517
cKK	-0.109956	0.045193	-2.433035
dKL	0.7465	0.041918	17.808517
dKM	0.548434	0.03495	15.692119
cMM	-0.235908	0.040302	-5.853497
dML	0.713019	0.032878	21.686517
dMK	0.548434	0.03495	15.692119

R2 = 0.9938

R2b = 0.9932

# obs = 93

dLK = dKL, dLM = dML, and dKM = dMK

The three estimated, restricted factor demand functions are:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/1) * [-0.2076 + 0.7465 * (wK / wL)^^(1/2) + 0.713 * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/1) * [-0.11 + 0.7465 * (wL / wK)^^(1/2) + 0.5484 * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/1) * [-0.2359 + 0.713 * (wL / wM)^^(1/2) + 0.5484 * (wK / wM)^^(1/2)]

The estimated factor demand elasticities are obtained by:

For example, with wL = 7, wK = 13, wM = 6, and q = 30:

ε_L,wL	ε_L,wK	ε_L,wM	ε_L,q
ε_K,wL	ε_K,wK	ε_K,wM	ε_K,q
ε_M,wL	ε_M,wK	ε_M,wM	ε_M,q

-0.5706	0.3461	0.2246	1
0.338	-0.5678	0.2299	1
0.287	0.3009	-0.5879	1

XIX. The Diewert cost function as obtained from the restricted factor demand equations is:

C(q;wL,wK,wM) = q^^(1/nu) * [cLL * wL + cKK * wK + cMM * wM + (dLK+dKL) * (wL*wK)^^(1/2) + (dLM +dML) * (wL*wM)^^(1/2) + (dKM+dMK) * (wK*wM)^^(1/2)]

= q^^(1/1) * [-0.20759 * wL + -0.10996 * wK + -0.23591 * wM + 1.493 * (wL*wK)^^(1/2) + 1.42604 * (wL*wM)^^(1/2) + 1.09687 * (wK*wM)^^(1/2)] (***)

XX. Note:
1. C(q;wL,wK,wM) linear homogeneous in factor prices requires for any t > 0 that the unit cost function c(wL,wK,wM) obey:

c(t*wL,t*wK,t*wM) = t * c(wL,wK,wM).

For example, with wL = 7, wK = 13, wM = 6, and t = 2:

2 * c(7, 13, 6) = 57.75 = 57.75 = c(14, 26,12).

2. The matrix ∇²C of second order partial derivatives of the cost function C(q;wL,wK,wM) = h(q)*c(wL,wK,wM) is symmetric:

H = ∇²_wwc =

-0.11982	0.03913	0.05501
0.03913	-0.0354	0.03105
0.05501	0.03105	-0.13145

The principal minors of H are H1 = -0.119817, H2 = 0.00271, and H3 = 0.

If these principal minors alternate in sign, starting with negative, with H3 <= 0, the matrix H is negative (semi)definite,
and the cost function C(q;wL,wK,wM) is a concave function in factor prices at wL = 7, wK = 13, and wM = 6.

The eigenvalues of H are e1 = -0.181, e2 = -0.1056, and e3 = 0.
H3 = e1 * e2 * e3 = 0.

XXI. The factor share functions are:

XXII. Uzawa Partial Elasticities of Substitution:

Imposing the dLK = dKL, dLM = dML, and dKM = dMK restrictions in the factor demand functions, we get (approximate?) equality of the cross partial elasticities of substitution:

u_LK = u_KL, u_LM = u_ML, and u_KM = u_MK.

as seen in the following table.

XXIII. Table of Results: check that the estimated Diewert cost function and input amounts for a given level of output agree with the Generalized CES production function's minimized cost and inputs. Also, compare the Allen partial elasticities of substitution, s_LK, s_LM, and s_MK, with the Uzawa partial elasticities of substitution, u_LK, u_LM, and u_KM.

Generalized CES-Diewert Cost Function À3: Estimate the Translog cost function using restricted factor shares Parameters: rho = 0.17647, rhoL = 0.17647, rhoK = 0.11823, rhoM = 0.26339
					nu = 1 — Generalized CES Cost Data —								nu1 = 1 — Diewert Cost Data —				Factor Shares			Uzawa Elasticities						∇²_wwc(w)
obs #	q	wL	wK	wM	L	K	M	s_LK	s_LM	s_KM	ε_LKM	cost	est cost	est L	est K	est M	sL	sK	sM	u_LK	u_LM	u_KL	u_KM	u_ML	u_MK	e₁	e₂	e₃
1	18	8.36	11.3	7.84	23.28	16.5	20.75	0.9	0.79	0.84	0.934	543.76	567.95	24.31	17.8	20.86	0.358	0.354	0.288	0.91	0.89	0.91	0.8	0.89	0.8	-0.136	-0.095	-0
2	19	6.62	11.18	4.82	24.95	14.54	27.04	0.9	0.79	0.83	0.925	458.12	479.01	26.05	15.67	27.26	0.36	0.366	0.274	0.97	0.81	0.97	0.8	0.81	0.8	-0.215	-0.119	0
3	20	8.14	14.92	6.44	27.59	15.02	27.8	0.9	0.79	0.83	0.924	627.72	653.61	28.75	16.03	28.01	0.358	0.366	0.276	0.96	0.8	0.96	0.81	0.8	0.81	-0.165	-0.094	-0
4	21	8.84	12.46	5.92	25.77	17.68	29.77	0.9	0.79	0.83	0.925	624.41	646.89	26.51	18.83	30.05	0.362	0.363	0.275	0.97	0.84	0.97	0.77	0.84	0.77	-0.17	-0.094	0
5	22	8.78	13.98	6.12	28.42	17.58	31.6	0.89	0.79	0.83	0.923	688.74	711.4	29.25	18.58	31.83	0.361	0.365	0.274	0.97	0.82	0.97	0.78	0.82	0.78	-0.168	-0.091	-0
6	23	5.76	13.3	7.04	38.19	17.21	26.68	0.9	0.79	0.83	0.926	636.64	654.2	39.45	17.95	26.75	0.347	0.365	0.288	0.91	0.8	0.91	0.89	0.8	0.89	-0.202	-0.098	-0
7	24	7.52	12.5	5.06	31.43	18.8	35.68	0.89	0.79	0.83	0.921	651.91	668.78	32.15	19.63	35.89	0.362	0.367	0.272	0.98	0.8	0.98	0.79	0.8	0.79	-0.205	-0.106	-0
8	25	8.92	14.28	5.08	31.3	19.37	40.57	0.89	0.79	0.83	0.918	761.88	779.29	31.88	20.18	40.71	0.365	0.37	0.265	1	0.8	1	0.76	0.8	0.76	-0.208	-0.091	0
9	26	5.34	13.9	7.38	46.66	19.08	29.17	0.9	0.79	0.83	0.924	729.64	742.21	47.71	19.56	29.21	0.343	0.366	0.29	0.9	0.79	0.9	0.91	0.79	0.91	-0.222	-0.093	-0
10	27	7.46	12.5	6.5	37.92	22.75	34.64	0.9	0.79	0.83	0.923	792.38	804.01	38.46	23.28	34.79	0.357	0.362	0.281	0.94	0.83	0.94	0.82	0.83	0.82	-0.165	-0.101	0
11	28	7.2	11.08	7.56	40.05	26	31.45	0.9	0.79	0.83	0.928	814.25	823.16	40.57	26.46	31.47	0.355	0.356	0.289	0.9	0.87	0.9	0.83	0.87	0.83	-0.155	-0.098	0
12	29	7.5	12.62	7.12	41.83	25.13	35.47	0.9	0.79	0.83	0.924	883.34	890.85	42.21	25.45	35.56	0.355	0.36	0.284	0.92	0.84	0.92	0.83	0.84	0.83	-0.157	-0.096	0
13	30	7	13	6	43.79	24.14	40.13	0.89	0.79	0.83	0.92	861.17	866.2	44.1	24.31	40.25	0.356	0.365	0.279	0.95	0.81	0.95	0.82	0.81	0.82	-0.181	-0.106	0
14	31	7	13.5	6.36	46.54	24.89	40.56	0.89	0.79	0.83	0.92	919.69	922.39	46.77	24.92	40.65	0.355	0.365	0.28	0.94	0.8	0.94	0.84	0.8	0.84	-0.176	-0.102	0
15	32	7.26	12.72	6.14	45.96	26.76	42.42	0.89	0.79	0.83	0.92	934.47	934.65	45.96	26.72	42.52	0.357	0.364	0.279	0.95	0.82	0.95	0.82	0.82	0.82	-0.174	-0.104	-0
16	33	7.84	11.56	4.96	42.18	28.53	49.28	0.89	0.79	0.83	0.917	904.92	902.32	41.78	28.51	49.43	0.363	0.365	0.272	0.98	0.82	0.98	0.77	0.82	0.77	-0.206	-0.105	-0
17	34	6.04	11.86	7.56	55.64	29.55	37.17	0.9	0.79	0.83	0.924	967.52	962.79	55.63	29.26	37	0.349	0.36	0.291	0.89	0.84	0.89	0.88	0.84	0.88	-0.187	-0.094	-0
18	35	7.2	12.28	7.28	52.25	31.37	41.51	0.89	0.79	0.83	0.922	1063.68	1056.01	51.95	30.94	41.49	0.354	0.36	0.286	0.91	0.84	0.91	0.84	0.84	0.84	-0.159	-0.096	0
19	36	7.96	13.76	5.42	49.64	29.37	54.11	0.89	0.79	0.83	0.914	1092.51	1080.73	49.04	28.87	54.07	0.361	0.368	0.271	0.98	0.8	0.98	0.79	0.8	0.79	-0.193	-0.1	-0
20	37	7.46	14.6	7.7	58.32	31.14	45.24	0.89	0.79	0.83	0.919	1238.11	1222.81	57.76	30.41	45.18	0.352	0.363	0.285	0.92	0.82	0.92	0.85	0.82	0.85	-0.157	-0.089	-0
21	38	6.24	11.94	7.18	61.07	33.35	43.32	0.89	0.79	0.83	0.921	1090.37	1074.87	60.42	32.49	43.17	0.351	0.361	0.288	0.9	0.83	0.9	0.86	0.83	0.86	-0.182	-0.098	-0
22	39	6.34	14.22	7.54	66.68	31.74	45.81	0.89	0.79	0.83	0.918	1219.51	1198.66	65.83	30.73	45.67	0.348	0.365	0.287	0.91	0.8	0.91	0.88	0.8	0.88	-0.183	-0.091	-0
23	40	9	12.86	4.76	49.61	34.8	66.06	0.89	0.79	0.83	0.912	1208.51	1182.89	48.13	33.93	65.84	0.366	0.369	0.265	1.01	0.81	1.01	0.74	0.81	0.74	-0.221	-0.092	-0
24	41	7.4	13.04	6.22	60.24	35.39	54.84	0.89	0.79	0.83	0.916	1248.31	1221.06	58.92	34.08	54.77	0.357	0.364	0.279	0.95	0.82	0.95	0.82	0.82	0.82	-0.172	-0.102	0
25	42	5.46	13.96	5.54	72.95	31.03	56.47	0.89	0.79	0.83	0.912	1144.33	1115.03	71.58	29.5	56.39	0.351	0.369	0.28	0.95	0.75	0.95	0.88	0.75	0.88	-0.227	-0.12	0
26	43	5.86	13.1	7.76	75.9	36.48	47.46	0.89	0.79	0.83	0.919	1290.89	1258.57	74.35	34.89	47.14	0.346	0.363	0.291	0.89	0.82	0.89	0.89	0.82	0.89	-0.196	-0.09	0
27	44	7.3	13.46	4.22	61.09	34.49	74.72	0.89	0.79	0.83	0.908	1225.44	1187.57	59.32	32.86	73.98	0.365	0.372	0.263	1.01	0.76	1.01	0.78	0.76	0.78	-0.257	-0.109	0
28	45	7.88	14.34	4.2	61.32	35.04	79.97	0.89	0.79	0.83	0.906	1321.52	1277.27	59.4	33.31	78.94	0.366	0.374	0.26	1.02	0.76	1.02	0.77	0.76	0.77	-0.262	-0.101	-0
29	46	6.28	11.16	6.06	70.57	41.49	56.98	0.89	0.79	0.83	0.916	1251.45	1212.38	68.45	39.29	56.77	0.355	0.362	0.284	0.92	0.83	0.92	0.83	0.83	0.83	-0.187	-0.112	0
30	47	5.4	12.52	6.98	84.18	39.37	53.28	0.89	0.79	0.83	0.917	1319.43	1275.61	81.77	37.12	52.91	0.346	0.364	0.29	0.9	0.8	0.9	0.9	0.8	0.9	-0.215	-0.099	0
31	48	6.7	13.28	5.14	73.01	39	70.52	0.89	0.79	0.83	0.91	1369.56	1317.61	70.46	36.55	70.07	0.358	0.368	0.273	0.97	0.78	0.97	0.82	0.78	0.82	-0.209	-0.114	-0
AVE:	33	7.16	12.94	6.25	49	27.04	44.15	0.89	0.79	0.83	0.92	964.01	957.77	49	27.04	44.15	0.356	0.365	0.279	0.94	0.81	0.94	0.82	0.81	0.82	-0.191	-0.1	-0

À4: Estimate the Diewert cost function directly, with nu1 = 1.

XXIV. If we have a data set relating the input (factor) prices, wL, wK, and wM, to the total (minimum) cost of producing output for varying levels output, but do not have data on the required levels of inputs, we can estimate the Diewert cost function directly. We will use the same sequence (displayed in the "Diewert Cost Function" table) of factor prices, outputs, and total (minimum) cost as used in À1. The estimated coefficients of the cost function will vary with the parameters nu, rho, rhoL, rhoK, rhoM, alpha, beta and gamma of the Generalized CES production function used to generate these data.

Under these circumstances, with nu1 = 1, the Diewert cost function may fail to be concave in factor prices, depending on the generated sequence of random factor prices, as one or more of the eigenvalues of the Hessian matrix H = ∇²_wwc(wL,wK,wM) turn positive.

SVD Least Squares
Parameter Estimates
Parameter	Coefficient	std error	t-ratio
cLL	-2.856595	2.122	-1.346
cKK	-0.888393	1.605	-0.553
cMM	2.733301	1.644	1.663
2*dLK	6.485889	3.379	1.92
2*dLM	-0.76376	2.506	-0.305
2*dKM	-1.465339	2.355	-0.622

R2 = 0.8814	R2b = 0.8577	# obs = 31
Observation Matrix Rank: 6

The Diewert cost function as obtained by direct estimation is:

C(q;wL,wK,wM) = q^^(1/nu1) * [cLL * wL + cKK * wK + cMM * wM + 2 * dLK * (wL*wK)^^(1/2) + 2 * dLM * (wL*wM)^^(1/2) + 2 * dKM * (wK*wM)^^(1/2)]

= q^^(1/1) * [-2.85659 * wL + -0.88839 * wK + 2.7333 * wM + 6.48589 * (wL*wK)^^(1/2) + -0.76376 * (wL*wM)^^(1/2) + -1.46534 * (wK*wM)^^(1/2)] (***)

XXVI. Its three derived factor demand functions are:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/1) * [-2.8566 + 3.2429 * (wK / wL)^^(1/2) + -0.3819 * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/1) * [-0.8884 + 3.2429 * (wL / wK)^^(1/2) + -0.7327 * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/1) * [2.7333 + -0.3819 * (wL / wM)^^(1/2) + -0.7327 * (wK / wM)^^(1/2)]

The derived factor demand elasticities are obtained by:

For example, with wL = 7, wK = 13, wM = 6, and q = 30:

ε_L,wL	ε_L,wK	ε_L,wM	ε_L,q
ε_K,wL	ε_K,wK	ε_K,wM	ε_K,q
ε_M,wL	ε_M,wK	ε_M,wM	ε_M,q

-1.6812	1.8273	-0.1462	1
1.1976	-0.9471	-0.2505	1
-0.166	-0.434	0.6	1

XXVII. Notes:
1. As derived, dLK = dKL, dLM = dML, and dKM = dMK: Young's Theorem holds by construction.

2. C(q;wL,wK,wM) linear homogeneous in factor prices requires for any t > 0 that the unit cost function c(wL,wK,wM) obey:

c(t*wL,t*wK,t*wM) = t * c(wL,wK,wM).

For example, with wL = 7, wK = 13, wM = 6, and t = 2:

2 * c(7, 13, 6) = 57.67 = 57.67 = c(14, 26,12).

3. The matrix ∇²C of second order partial derivatives of the cost function C(q;wL,wK,wM) = h(q)*c(wL,wK,wM) is symmetric.

H = ∇²_wwc =

-0.29042	0.16998	-0.02946
0.16998	-0.07238	-0.04148
-0.02946	-0.04148	0.12424

The principal minors of H are H1 = -0.290417, H2 = -0.007871, and H3 = -0.

If these principal minors alternate in sign, starting with negative, with H3 <= 0, the matrix H is negative (semi)definite,
and the cost function C(q;wL,wK,wM) is a concave function in factor prices at wL = 7, wK = 13, and wM = 6.

The eigenvalues of H are e1 = -0.3834, e2 = 0.1448, and e3 = -0.
H3 = e1 * e2 * e3 = 0.

XXVIII. Table of Results: check that the estimated Diewert cost function and input amounts for a given level of output agree with the Generalized CES production function's minimized cost and inputs. Also, compare the Allen partial elasticities of substitution, s_LK, s_LM, and s_MK, with the Uzawa partial elasticities of substitution, u_LK, u_LM, and u_KM.

Generalized CES-Diewert Cost Function À4: Estimate the Diewert cost function directly Parameters: rho = 0.17647, rhoL = 0.17647, rhoK = 0.11823, rhoM = 0.26339
					nu = 1 — Generalized CES Cost Data —								nu1 = 1 — Diewert Cost Data —				Factor Shares			Uzawa Elasticities						∇²_wwc(w)
obs #	q	wL	wK	wM	L	K	M	s_LK	s_LM	s_KM	ε_LKM	cost	est cost	est L	est K	est M	sL	sK	sM	u_LK	u_LM	u_KL	u_KM	u_ML	u_MK	e₁	e₂	e₃
1	18	8.36	11.3	7.84	23.28	16.5	20.75	0.9	0.79	0.84	0.934	543.76	550.31	9.79	23.23	26.27	0.149	0.477	0.374	7.27	-0.91	7.27	-0.63	-0.91	-0.63	-0.325	0.107	-0
2	19	6.62	11.18	4.82	24.95	14.54	27.04	0.9	0.79	0.83	0.925	458.12	476.11	19.61	21.39	22.23	0.273	0.502	0.225	4.06	-0.7	4.06	-0.95	-0.7	-0.95	-0.406	0.185	0
3	20	8.14	14.92	6.44	27.59	15.02	27.8	0.9	0.79	0.83	0.924	627.72	653.57	23.88	20.51	23.78	0.297	0.468	0.234	3.93	-0.61	3.93	-1	-0.61	-1	-0.33	0.137	-0
4	21	8.84	12.46	5.92	25.77	17.68	29.77	0.9	0.79	0.83	0.925	624.41	626.2	14.3	28.1	25.28	0.202	0.559	0.239	5.06	-0.96	5.06	-0.79	-0.96	-0.79	-0.309	0.149	-0
5	22	8.78	13.98	6.12	28.42	17.58	31.6	0.89	0.79	0.83	0.923	688.74	702.5	20.17	26.33	25.71	0.252	0.524	0.224	4.26	-0.78	4.26	-0.9	-0.78	-0.9	-0.307	0.145	0
6	23	5.76	13.3	7.04	38.19	17.21	26.68	0.9	0.79	0.83	0.926	636.64	660.07	37.93	16.39	31.76	0.331	0.33	0.339	4.52	-0.38	4.52	-1.1	-0.38	-1.1	-0.474	0.119	0
7	24	7.52	12.5	5.06	31.43	18.8	35.68	0.89	0.79	0.83	0.921	651.91	666.29	24.27	27.86	26.79	0.274	0.523	0.203	3.96	-0.76	3.96	-0.99	-0.76	-0.99	-0.358	0.179	0
8	25	8.92	14.28	5.08	31.3	19.37	40.57	0.89	0.79	0.83	0.918	761.88	782.43	23.96	30.94	24.97	0.273	0.565	0.162	3.79	-0.93	3.79	-1.09	-0.93	-1.09	-0.304	0.186	0
9	26	5.34	13.9	7.38	46.66	19.08	29.17	0.9	0.79	0.83	0.924	729.64	749.11	50.09	15.28	36.48	0.357	0.284	0.359	4.79	-0.32	4.79	-1.26	-0.32	-1.26	-0.524	0.113	0
10	27	7.46	12.5	6.5	37.92	22.75	34.64	0.9	0.79	0.83	0.923	792.38	795.32	26.59	29.39	35.32	0.249	0.462	0.289	4.61	-0.63	4.61	-0.84	-0.63	-0.84	-0.358	0.132	0
11	28	7.2	11.08	7.56	40.05	26	31.45	0.9	0.79	0.83	0.928	814.25	815.84	21.7	31.38	41.26	0.192	0.426	0.382	6.09	-0.66	6.09	-0.71	-0.66	-0.71	-0.37	0.111	-0
12	29	7.5	12.62	7.12	41.83	25.13	35.47	0.9	0.79	0.83	0.924	883.34	883.16	28.36	30.78	39.61	0.241	0.44	0.319	4.89	-0.6	4.89	-0.81	-0.6	-0.81	-0.355	0.119	-0
13	30	7	13	6	43.79	24.14	40.13	0.89	0.79	0.83	0.92	861.17	865.04	36.28	29.81	37.27	0.294	0.448	0.259	4.08	-0.57	4.08	-0.97	-0.57	-0.97	-0.383	0.145	-0
14	31	7	13.5	6.36	46.54	24.89	40.56	0.89	0.79	0.83	0.92	919.69	922.88	39.77	29.26	39.22	0.302	0.428	0.27	4.1	-0.52	4.1	-0.99	-0.52	-0.99	-0.384	0.136	0
15	32	7.26	12.72	6.14	45.96	26.76	42.42	0.89	0.79	0.83	0.92	934.47	928.7	34.71	33.68	40.43	0.271	0.461	0.267	4.29	-0.61	4.29	-0.9	-0.61	-0.9	-0.369	0.141	-0
16	33	7.84	11.56	4.96	42.18	28.53	49.28	0.89	0.79	0.83	0.917	904.92	883.7	25.66	42.98	37.44	0.228	0.562	0.21	4.5	-0.93	4.5	-0.88	-0.93	-0.88	-0.347	0.181	0
17	34	6.04	11.86	7.56	55.64	29.55	37.17	0.9	0.79	0.83	0.924	967.52	976.89	42.85	28.59	50.13	0.265	0.347	0.388	5.19	-0.44	5.19	-0.9	-0.44	-0.9	-0.441	0.11	-0
18	35	7.2	12.28	7.28	52.25	31.37	41.51	0.89	0.79	0.83	0.922	1063.68	1050.83	34.81	36.07	49.07	0.239	0.422	0.34	5.05	-0.57	5.05	-0.81	-0.57	-0.81	-0.37	0.115	-0
19	36	7.96	13.76	5.42	49.64	29.37	54.11	0.89	0.79	0.83	0.914	1092.51	1082.14	39.31	40.26	39.71	0.289	0.512	0.199	3.81	-0.73	3.81	-1.03	-0.73	-1.03	-0.338	0.168	0
20	37	7.46	14.6	7.7	58.32	31.14	45.24	0.89	0.79	0.83	0.919	1238.11	1225.77	47.81	33.21	49.9	0.291	0.396	0.313	4.44	-0.48	4.44	-0.95	-0.48	-0.95	-0.359	0.11	0
21	38	6.24	11.94	7.18	61.07	33.35	43.32	0.89	0.79	0.83	0.921	1090.37	1082.88	46.35	33.74	54.43	0.267	0.372	0.361	4.94	-0.47	4.94	-0.89	-0.47	-0.89	-0.427	0.116	-0
22	39	6.34	14.22	7.54	66.68	31.74	45.81	0.89	0.79	0.83	0.918	1219.51	1208.81	61.76	29	53.7	0.324	0.341	0.335	4.5	-0.39	4.5	-1.07	-0.39	-1.07	-0.429	0.111	0
23	40	9	12.86	4.76	49.61	34.8	66.06	0.89	0.79	0.83	0.912	1208.51	1167.58	29.69	55.15	40.16	0.229	0.607	0.164	4.3	-1.14	4.3	-0.99	-1.14	-0.99	-0.305	0.198	0
24	41	7.4	13.04	6.22	60.24	35.39	54.84	0.89	0.79	0.83	0.916	1248.31	1214.07	45.03	42.99	51.49	0.274	0.462	0.264	4.24	-0.6	4.24	-0.91	-0.6	-0.91	-0.362	0.139	0
25	42	5.46	13.96	5.54	72.95	31.03	56.47	0.89	0.79	0.83	0.912	1144.33	1120.62	81.66	28.48	50.03	0.398	0.355	0.247	3.76	-0.4	3.76	-1.38	-0.4	-1.38	-0.515	0.159	0
26	43	5.86	13.1	7.76	75.9	36.48	47.46	0.89	0.79	0.83	0.919	1290.89	1278.61	66.76	30.82	62.33	0.306	0.316	0.378	4.95	-0.37	4.95	-1.04	-0.37	-1.04	-0.462	0.107	0
27	44	7.3	13.46	4.22	61.09	34.49	74.72	0.89	0.79	0.83	0.908	1225.44	1220.22	55.29	47.94	40.59	0.331	0.529	0.14	3.31	-0.82	3.31	-1.34	-0.82	-1.34	-0.372	0.231	0
28	45	7.88	14.34	4.2	61.32	35.04	79.97	0.89	0.79	0.83	0.906	1321.52	1323.46	55.77	50.36	38.54	0.332	0.546	0.122	3.23	-0.92	3.23	-1.45	-0.92	-1.45	-0.345	0.238	0
29	46	6.28	11.16	6.06	70.57	41.49	56.98	0.89	0.79	0.83	0.916	1251.45	1207.29	50.2	46.2	62.11	0.261	0.427	0.312	4.64	-0.55	4.64	-0.86	-0.55	-0.86	-0.425	0.14	0
30	47	5.4	12.52	6.98	84.18	39.37	53.28	0.89	0.79	0.83	0.917	1319.43	1291.2	77.42	32.63	66.56	0.324	0.316	0.36	4.74	-0.37	4.74	-1.09	-0.37	-1.09	-0.505	0.119	0
31	48	6.7	13.28	5.14	73.01	39	70.52	0.89	0.79	0.83	0.91	1369.56	1329.75	65.98	46.04	53.74	0.332	0.46	0.208	3.61	-0.59	3.61	-1.14	-0.59	-1.14	-0.404	0.176	0
AVE:	33	7.16	12.94	6.25	39.93	32.86	41.17	0.89	0.79	0.83	0.92	964.01	959.4	39.93	32.86	41.17	0.279	0.447	0.274	4.48	-0.64	4.48	-0.99	-0.64	-0.99	-0.386	0.146	0

Mathematical Notes

1. The Diewert (Generalized Leontief) cost function

C(q;wL,wK,wM) = h(q) * c(wL,wK,wM) (**)

where the returns to scale function is: h(q) = q^^(1/nu), a continuous, increasing function of q (q >= 1), with h(0) = 0 and h(1) = 1,

and the unit cost function is: c(wL,wK,wM) = cLL * wL + cKK * wK + cMM * wM + (dLK+dKL) * (wL*wK)^^(1/2) + (dLM +dML) * (wL*wM)^^(1/2) + (dKM+dMK) * (wK*wM)^^(1/2),

linear in its parameters cLL, cKK, cMM, dLK, dKL, dLM, dML, dKM, and dMK.

2. The Factor Demand Functions:

∂C/∂wL = L(q; wL, wK, wM) = q^^(1/nu) * [cLL + dLK * (wK / wL)^^(1/2) + dLM * (wM / wL)^^(1/2)]

∂C/∂wK = K(q; wL, wK, wM) = q^^(1/nu) * [cKK + dKL * (wL / wK)^^(1/2) + dKM * (wM / wK)^^(1/2)]

∂C/∂wM = M(q; wL, wK, wM) = q^^(1/nu) * [cMM + dML * (wL / wM)^^(1/2) + dMK * (wK / wM)^^(1/2)]

3. The Factor Share Functions:

4. The Factor Demand Elasticities:

ε_L,wL = ∂ln(L(q;wL,wK,wM))/∂ln(wL) = -.5 * (q^^1/nu) / L(q;wL,wK,wM)) * (dLK * (wK/wL)^^1/2 + dLM * (wM/wL)^^1/2),

ε_L,wK = ∂ln(L(q;wL,wK,wM))/∂ln(wK) = .5 * (q^^1/nu) / L(q;wL,wK,wM)) * dLK * (wK/wL)^^1/2,

ε_L,wM = ∂ln(L(q;wL,wK,wM))/∂ln(wM) = .5 * (q^^1/nu) / L(q;wL,wK,wM)) * dLM * (wM/wL)^^1/2,

ε_L,q = ∂ln(L(q;wL,wK,wM))/∂ln(q) = 1/nu, etc.

5. Cost Function C(q;wL,wK,wM) Concave in Factor Prices:

∂²c/∂wL∂wL = -.25((dLK+dKL)*wK^^(1/2) + (dLM+dML)*wM^^(1/2))/wL^^(3/2),

∂²c/∂wL∂wK = .25 * (dLK+dKL)/(wL*wK)^^(1/2) = ∂²c/∂wK∂wL,

∂²c/∂wL∂wM = .25 * (dLM+dML)/(wL*wM)^^(1/2) = ∂²c/∂wM∂wL,

∂²c/∂wK∂wK = -.25((dKL+dLK)*wL^^(1/2) + (dKM+dMK)*wM^^(1/2))/wK^^(3/2),

∂²c/∂wK∂wM = .25 * (dKM+dMK)/(wL*wK)^^(1/2) = ∂²c/∂wM∂wK, and

∂²c/∂wM∂wM = -.25((dML+dLM)*wL^^(1/2) + (dMK+dKM)*wK^^(1/2))/wM^^(3/2).