1. ILRI, Informal Traders Lock Horns with the
Formal Milk Industry: The role of researching propoor dairy policy shift in Kenya (May 2006).
2. ILRI, Adaptation of Planted Forages
by
Smallholder Milk Producers in Kenya.
3. IMF, World Economic and Financial

of the program, Godtland and others (2004) applied three
different steps for generating a common support of
propensity scores to match nonparticipants to the
participant sample. These steps, as described here,
combined methods that have been formally disc

1. T. J. Dalton, G. K. Criner, and J. Halloran, Fluid
Milk
Processing
Costs:
Current
State
and
Comparisons, American Dairy Science Association
(2002)
2. FAO Briefs on Import Surges: No 7, Kenya: Milk
powder, sugar, maize (February 2007)
3. Gadd H., Hansso

1.1.1 Binary Logit Model
Following Madalla (1983, 2001), the probability, p, that a
small scale milk farmer adopts the chilling hub model is
given by a Logit model;
P=ez/1+ez
Z= latent variable that takes values of 1 if a farmer adopts
and uses the chilli

the balancing test was performed by dividing each
comparison and treatment group into two strata, ordered
by probability propensity scores. Within each stratum, a ttest of equality of means across participants and matched
nonparticipants was conducted for

the matched companies in control. The results concerning
the effects of the RDG subsidy were therefore mixed: a
positive effect with respect to employment but no effect
concerning return on total assets. This result is in
accordance with previous results

estimator has the same form as the kernel-matching
estimator, except for the weighting function:
(i, j )LLR=Kij Kik(Pk-Pi)2-( Kij(Pj-Pi) Kik(Pk-Pi)
Kij Kik(Pk-Pi)2-( Kij(Pj-Pi)
Kik(Pk-Pi)
Difference-in-difference matching. With data on
participant and co

common support) was used to construct a weighted match
for each participant, applying a nonparametric kernel
regression method proposed by Heckman, Ichimura, and
Todd (1998).
Gadd,Hansson and Manson (2009) while evaluating the
impact of firm subsidy using

ponds presents a pathway for reducing rural poverty in
rural Rwanda.
2.6 Theoretical framework
This gives a discussion of the theories that form the basis
for this study. The main theories include those of the firm
and consumption. The basis of this study

the main outcome of interest (amount of milk produced).
The effect of participation will be measured relative to
non-participation or participation
For the purposes of this study, the unit of analysis will be
an individual farmer or farming household. Let

particular, for the household/farmer engaged in the milk
cooling plants, we cannot assess the worth of the observed
outcome without some information on the counterfactual
i.e. what the household/farmer would have experienced
had it not engaged in the cool

1. highlands:
breed
preferences
and
breeding
practices. Livestock Production Science 82 (2003)
117-127
begin_of_the_skype_highlighting
82
(2003) 117-127
2. Bryson, Alex, Richard Dorsett, and Susan Purdon.
2002. The Use of Propensity Score Matching in
the

Takashi and Jayne (2003) while measuring the impacts of
working-age adult mortality on small scale farm
households in Kenya, they used households size and
composition, crop production, asset levels, and off-farm
income to estimate the impact. Difference-i

within the common support and thus construct the
counterfactual outcome. Nonparametric matching
estimators such as kernel matching and LLM use a
weighted average of all nonparticipants to construct the
counterfactual match for each participant. If Pi is t

With only cross-sections over time rather than panel data
(Todd, 2007), TOT PSM can be written as:
TOTDDPSM= 1/NT2 (Yi2T- (i, j ) YCj2 )- )- 1/NT1 (
Yi1T - (i, j ) -Yj1C)
For NT2 = iT2 & jC2
For NT1 = iT1 & j C1
Here, YitT and YjtC , t = cfw_1,2 are the o

subset of the population as is the case here, many of the
methods suggest turning to non-exposed units (nonparticipants) in search of the missing information. They
also specify circumstances under which the use of such
information yields reliable estimate

1. Peruvian Andes. Economic Development and
Cultural Change 52 (1): 12958.
2. Hahn, Jinyong, Keisuke Hirano, and Dean Karlan.
2008. Adaptive Experimental Design Using the
Propensity Score. Working Paper 969, Economic
Growth Center, Yale University, New Ha

1.1 Data Analysis and Estimation of Parameters
This study will adopt different approaches both
econometric and qualitative for testing the postulated
hypothesis concerning milk industry in the county and
inferring the happenings to the overall milk indust

constitutes a blue print for collection, measurement and
analysis of data. Various types of research design
approaches exist to answer different research problems or
questions, the commonly used ones include that of
explanatory, exploratory, casual-compar

Farmer i's profitability without the cooling plant (Ii = 0) is
y0i = 0 X0i + 0i;
In the model, Zi is a vector of farm characteristics that
affect farmers decisions to join the cooling plant; X1i and
X0i are two vectors of farm characteristics that affect

1. Dehejia, Rajeev. 2005. Practical Propensity Score
Matching: A Reply to Smith and Todd. Journal of
Econometrics 125 (12): 35564.
2. Efron, Bradley, and Robert J. Tibshirani. 1993. An
Introduction to the Bootstrap. Boca Raton, FL:
Chapman & Hall.
3. Fan,

participate tend to have higher profitability than those
who did.
1_1 , 0_1 , 0_0 , and 1_0 measure farmers selection bias
on participation. There are four patterns.
(1) 1_1 > 0 ; 1_0 < 0 and 0_1 > 0; 0_0 < 0
This situation indicates that the sampled farm

general farmer (with the same characteristics) under
participation. A positive mean of 1_1 indicates that under
participation, farmers who actually joined tend to have
higher profitability than those who did not.
According to equations (2) and (4), 0_1 co

population, the weights would be 1/ P(X ) for the
participants and 1/(1 P(X ) for the control units.
2.3 Concepts of Endogenous Switching Regression
Model
While the p-score comparisons compare the performance
of participation and non- participation farmer

yc1_0i = E (y1i | Ii = 0, x0i) = x0i1 - 11 (Zi) / [1 - F(Zi)]
xb1i represents the unconditional expectation of farmers
performance under the cooling plant;
xb0i represents the unconditional expectation of farmers
performance without the cooling plant;
yc1

groups came from a similar economic environment: 80
percent of Trabajar workers came from the poorest 20
percent of the population, and the study used a sample of
about 2,800 Trabajar participants along with
nonparticipants from a large national survey.
K

provide a good comparison with randomized estimates.
To the degree participation variables are incomplete; the
PSM results can be suspect. This condition is, as
mentioned earlier, not a directly testable criteria; it
requires careful examination of the fa

each matched participant- nonparticipant set. As discussed
below, the choice of a particular matching technique may
therefore affect the resulting program estimate through the
weights assigned:
Nearest-neighbor matching. One of the most frequently
used m

without the participation. We also compare farmers'
expected performance under the participation and without
the participation.
2.3.1
Indicators for Premiums of participation
Based on equations (1) to (6), three indicators can be
constructed to compare fa

1. Bay M B, 2000 Milk among the Kel-Tamacheqs,
Mali cultural and qualitative aspects. Laitsudnord2/2000 pp 60-61.
2. Bayemi. P. H, Bryant M J, Pingpoh D, Imele H,
Mbanya J, Tanya V, Cavestany D, Awoh J,
Ngoucheme A, Sali D, Ekoue F, Njakoi H and
Webb E C