My father has a farm service center and mechanization service center in Shida Kartli Region (Kaspi District). He provides agricultural services for farmers such as ploughing, cultivation, harvesting and so etc. This fall, number of his customers half diminished, even though autumn is a busy season as farmers are cultivating land for grain cultures (wheat and barley mostly). The reason for this is that farmers are waiting for new government to cultivate their land for free, which I doubt will happen. It was just like this after collapse of Soviet Union; People had expectation that new government would come and assist them to do something on their land. I believe such a low number for cultivated agricultural lang for Georgian farmers is that they don't realize that they are the ones who has to take care of their privatized land and after everyone has done little something on their land it is possible that government or other donor organizations will assist them.
Another thing I want to mention is that in my area if farmer wants to expand his farm he or she has to go through tough process to find original owner of the land who migrated somewhere else and in worse case passed away. Family members need to do paperwork to legalize land on their name and then sell it, which increases final price of the land and in most cases paperwork costs more than a land. So mostly farmers have to deal with the area they got after land privatization.

It is worth looking at houshold incomes in Marneuli also, a district with an Azeri-majority population.

If nothing else, this issue brings the problem of measuring or indicating productivity to the forefront. Not only is it difficult to measure or estimate agricultural productivity within a region, but cross region or international comparisons are difficult to make, even under more stable circumstances over longer periods of time in relatively developed economies. Add in the transition context, additional statistical collection, verification, and values for inputs, outputs, as well as qualitative changes in what is grown, and demographic changes, and well, I would not put too much faith in relative differences that show up, unless they are overwhelmingly large, consistent, and are under conditions where most factors are reasonably constant over a long number of years. This does not mean that productivity measures should not be made, or attempted, in these contexts, just that we should be hesitant to draw too rash a conclusion from weak diagnostics.

Your survey appers to confirm that the amount if land cultivated is not correlated to income. Am I correct?

I have trouble understanding why one would choose income as a proxy for productivity. One could use GDP per capita (better: GDP per worker), far more appropriate. If one would do so Samtskhe-Javakheti is the second-poorest region of Georgia, not really indicating an "Armenian productivity factor".

Sorry, but it is a very poor proxy as income includes transfers and remittances. They later are likely to be important in Javakheti and probably explain the discrepancy. Geostat has GDP data by region, which combined with population numbers gives GDP per capita.

Ah well, now we are onto the bigger issues of productivity. While economic convention would have it that productivity is measured using output/input(s), the problem is in carrying it out. Output per worker is simply output per worker, it is not productivity. It is also not labour productivity. Output per worker, even in real terms, has to be adjusted for factors that changes other than productivity, such as product specific prices, etc. cylces, climate, accounting definition changes over time, etc. to get at whether, all else equal, the input it able to produce more output that before, and whether it is "more productive" that other inputs used in other contexts. Income per worker of per household is by standard productivity measures not a proxy for productivity. It still has to be adjusted, and derived from the inputs in the process at hand.

Surely productivity cab be measured by yield per hectare. I achieved 4 tons of wheat and 7 of corn this year. Cost and amount of inputs was much higher than the average in Georgia.

Yes, you can start by using yield per hectare, to get land productivity, and then make adjustments to the stats for the different amounts of other inputs used (quality and quantity of labour and capital, etc. among other adjustments) to see, if all else equal, some land is more productive than others. Or, you can resort to total factor productivity, which combines all inputs to produce the output, and then is similarly adjusted for those factors that need to be held (all else equal) such as quality differences, price fluctuation differences, etc. or base measures, different statistical approaches to totaling up the amount of labour used, etc.

How do you determine the employment in agriculture in Georgia? In Armenia there is always this problem of accounting as employed in agriculture persons who just possess a piece of land (larger than a defined minimum) and isn't employed in any other place.

Still it is strange that those living in S-J have reported lower than average reliance on the remittances. Armenians living there usually (and historically) are very active on the Russian labor market.

Why don't you use the statics on value added by sectors of economy and regions ? is there such statistics in Georgia available?

Yes, you need to use value added as part of the output, but the problem remains choosing what inputs were used to produce that value added (output). There is no perfect answer I am afraid and usually a mixed approach is needed - based on the specific case, data availability, conditions, etc. Some people who are part of the household, for example, are given tasks on the farm just so that they are making a contribution. But in fact, even if they were not there, the farm would produce the same amount with the remaining people - this labour actually did not produce anything, and maybe the person was given tasks simply for moral or ethical reasons - to make someone feel useful, or part of the family, or to earn their keep/maintenance! This is called "latent" labour because it is hidden in the statistics and can throw off productivity measures. It is also highly relevant in the Caucasus and Central Asia after 1990 or so when many people returned to family farms - not really adding to value added, but adding to the inputs - thereby forcing productivity to appear to decline more than it really did. This is especially true in areas where there was little private sector, urban development and partially (not fully) explains some of the possible differences in agricultural productivity observed between transition economies in Eastern Europe versus Central Asia and the Caucasus.

I think that yield per hectare may represent a true measure of input irrespective of the problem of measuring and valuing inputs as land is a finite resourse and Georgia is a net importer of almost all types of food. If Georgia increased the yield per hectare by a factor of say 4 and increased the amount of kand cultivated by 4 times I posit that would be positive for the economy. Do you agree?

David, I've just interviewed Fadi Asli related to a project we are doing on Georgia's competitiveness. Among other things we talked about agriculture. According to him, 1kg of Brazilian poultry costs about 70c in Poti, compared to $1.5 for a Georgian equivalent (ok, fresh, not frozen).

Now, 70% of the cost of poultry is the cost of feed (grain) and, according to Fadi, Brazil is vastly more competitive in grain because of its vast size and climate (three harvests a year!). Even assuming that Georgian yields per hectare go up by a factor of four (at the cost of additional inputs), Georgia is not going to be able to compete with Brazil on grains (and on poultry).

An ag statistician (quoted in the post) I talked to suggested that Georgia could do relatively well in special "niche" crops that are not as scale intensive. He was telling me how important it is to collect data and monitor productivity in these crops. At the moment, GeoStat is doing a fairly good job of covering the major crops (potato, corn, grapes), but the smaller ones need a different sampling approach.

BTW, have you been able to estimate your own (farmgate) costs of producing one unit of grain (ignoring your personal time )? Say, labor, fertilizer, machinery, fuel, the cost of capital (depreciation), whatever else you used...

It is highly interesting that on average the Armenians in Tbilisi have just half the income of the Georgians. Could this be caused by an ingroup bias (discrimination) on part of the Georgians? Does anyone have an explanation why the Armenians in Tbilis are economically doing so poorly?