Hi all,
I have been struggling to get help on this
I have sales data during an intervention (the introduction of a carbon label) in a standard difference-in-differences way. That is, I have one variable for the treatment period (binary), one for the treatment group (binary) and one for the interaction of both (did). The data is indexed by product (i) and week (time). Thus the basic regression would look like Y = Btreat + Bpost + Bdid.
However, I would like to see the effect of the label of the colour of the product (it can have 6 colour and I have one variable for the colour id and one dummy for each colour). I was thinking on adding it an interaction of each dummy with treat, post and did. Would that make sense? I am looking for the effect of the particular colour of the label.
My second question is: what is the best and most effective way to control for the category of the product. Should I include dummies for each category, or include them interacting them with treat, post and did?
I have been looking for the literature on this but have been unsuccessful. Either I find papers that had a simple treatment that can be translated to a binary variable (introduction of a label) or studies that did not use difference in difference.
Find below an example of my data:
Thanks in advance!
I have been struggling to get help on this
I have sales data during an intervention (the introduction of a carbon label) in a standard difference-in-differences way. That is, I have one variable for the treatment period (binary), one for the treatment group (binary) and one for the interaction of both (did). The data is indexed by product (i) and week (time). Thus the basic regression would look like Y = Btreat + Bpost + Bdid.
However, I would like to see the effect of the label of the colour of the product (it can have 6 colour and I have one variable for the colour id and one dummy for each colour). I was thinking on adding it an interaction of each dummy with treat, post and did. Would that make sense? I am looking for the effect of the particular colour of the label.
My second question is: what is the best and most effective way to control for the category of the product. Should I include dummies for each category, or include them interacting them with treat, post and did?
I have been looking for the literature on this but have been unsuccessful. Either I find papers that had a simple treatment that can be translated to a binary variable (introduction of a label) or studies that did not use difference in difference.
Find below an example of my data:
Code:
* Example generated by -dataex-. For more info, type help dataex clear input int i byte(time treat) float timetreatment byte CarbonColourN double CarbonScoreN float(redscore darkredscore) double amountsold float(categoryid categoryid1 categoryid2 revenueperproduct) 422 10 1 0 3 1737.836383 0 0 35 0 0 0 17.15 141 26 0 1 3 1564.235445 0 0 51.68010156814764 0 0 0 20.15524 142 10 0 0 3 1702.223617 0 0 50 0 0 0 49.5 142 11 0 0 3 1702.223617 0 0 43.35 0 0 0 42.9165 142 12 0 0 3 1702.223617 0 0 41.3559 0 0 0 40.94234 142 13 0 0 3 1702.223617 0 0 46.029116699999996 0 0 0 45.56882 142 14 0 0 3 1702.223617 0 0 56.0174350239 0 0 0 55.45726 142 15 0 0 3 1702.223617 0 0 47.3347325951955 0 0 0 46.86139 142 16 0 0 3 1702.223617 0 0 47.3347325951955 0 0 0 46.86139 142 17 0 0 3 1702.223617 0 0 44.68398756986455 0 0 0 44.23715 142 19 0 1 3 1702.223617 0 0 50 0 0 0 49.5 142 20 0 1 3 1702.223617 0 0 52.400000000000006 0 0 0 51.876 142 21 0 1 3 1702.223617 0 0 43.5444 0 0 0 43.10896 142 22 0 1 3 1702.223617 0 0 49.205172 0 0 0 48.71312 142 23 0 1 3 1702.223617 0 0 52.452713352 0 0 0 51.92818 142 24 0 1 3 1702.223617 0 0 50.039888537808004 0 0 0 49.53949 142 25 0 1 3 1702.223617 0 0 66.20277253551998 0 0 0 65.54075 142 26 0 1 3 1702.223617 0 0 47.66599622557439 0 0 0 47.18933 144 10 0 0 3 1701.648323 0 0 14.5 0 0 0 7.105 144 11 0 0 3 1701.648323 0 0 13.1805 0 0 0 6.458445 144 12 0 0 3 1701.648323 0 0 10.544400000000001 0 0 0 5.166756 144 13 0 0 3 1701.648323 0 0 13.180500000000002 0 0 0 6.458445 144 14 0 0 3 1701.648323 0 0 36.9054 0 0 0 18.083647 144 15 0 0 3 1701.648323 0 0 14.5038222 0 0 0 7.106873 144 16 0 0 3 1701.648323 0 0 11.8641265596 0 0 0 5.813422 144 17 0 0 3 1701.648323 0 0 30.3247074863376 0 0 0 14.859107 144 19 0 1 3 1701.648323 0 0 14.5 0 0 0 7.105 144 20 0 1 3 1701.648323 0 0 17.4 0 0 0 8.526 144 21 0 1 3 1701.648323 0 0 29.005799999999997 0 0 0 14.212842 144 22 0 1 3 1701.648323 0 0 21.75435 0 0 0 10.659632 144 23 0 1 3 1701.648323 0 0 31.91363145 0 0 0 15.63768 144 24 0 1 3 1701.648323 0 0 21.7650966489 0 0 0 10.664897 144 25 0 1 3 1701.648323 0 0 30.471135308459996 0 0 0 14.930857 539 10 1 0 5 3942.692129 1 0 35 0 0 0 66.15 539 11 1 0 5 3942.692129 1 0 46.655 0 0 0 88.17795 539 12 1 0 5 3942.692129 1 0 36.67083 0 0 0 69.30787 539 13 1 0 5 3942.692129 1 0 28.346551590000004 0 0 0 53.57498 539 14 1 0 5 3942.692129 1 0 51.70411010016 0 0 0 97.72077 539 15 1 0 5 3942.692129 1 0 36.7099181711136 0 0 0 69.381744 539 16 1 0 5 3942.692129 1 0 35.057971853413484 0 0 0 66.25957 539 17 1 0 5 3942.692129 1 0 28.396957201264925 0 0 0 53.67025 539 19 1 1 5 3942.692129 1 0 35 0 0 0 66.15 539 20 1 1 5 3942.692129 1 0 45.5 0 0 0 85.995 539 21 1 1 5 3942.692129 1 0 26.2535 0 0 0 49.61911 539 22 1 1 5 3942.692129 1 0 33.263184499999994 0 0 0 62.86742 539 23 1 1 5 3942.692129 1 0 45.50403639599999 0 0 0 86.00263 539 24 1 1 5 3942.692129 1 0 29.759639802983994 0 0 0 56.24572 539 25 1 1 5 3942.692129 1 0 40.26479265343734 0 0 0 76.10046 539 26 1 1 5 3942.692129 1 0 31.527332647641437 0 0 0 59.58666 144 26 0 1 3 1701.648323 0 0 21.756390610240437 0 0 0 10.66063 145 10 0 0 5 3695.590017 1 0 4.5 0 0 0 8.955 145 11 0 0 5 3695.590017 1 0 6.75 0 0 0 13.4325 145 12 0 0 5 3695.590017 1 0 6.75 0 0 0 13.4325 145 13 0 0 5 3695.590017 1 0 8.2485 0 0 0 16.414515 145 14 0 0 5 3695.590017 1 0 8.9991135 0 0 0 17.908236 145 15 0 0 5 3695.590017 1 0 9.7460399205 0 0 0 19.39462 145 16 0 0 5 3695.590017 1 0 3.0017802955140005 0 0 0 5.973543 145 17 0 0 5 3695.590017 1 0 3.7522253693925007 0 0 0 7.466928 145 19 0 1 5 3695.590017 1 0 14.5 0 0 0 28.855 145 20 0 1 5 3695.590017 1 0 14.5 0 0 0 28.855 145 21 0 1 5 3695.590017 1 0 14.5 0 0 0 28.855 145 22 0 1 5 3695.590017 1 0 21.0975 0 0 0 41.98402 145 23 0 1 5 3695.590017 1 0 10.54875 0 0 0 20.99201 145 24 0 1 5 3695.590017 1 0 13.1859375 0 0 0 26.240015 145 25 0 1 5 3695.590017 1 0 22.416093749999998 0 0 0 44.60803 145 26 0 1 5 3695.590017 1 0 17.148311718749998 0 0 0 34.12514 146 10 0 0 5 4270.563581000001 1 0 14.5 0 0 0 27.405 146 11 0 0 5 4270.563581000001 1 0 15.7035 0 0 0 29.679615 146 12 0 0 5 4270.563581000001 1 0 8.448483000000001 0 0 0 15.967633 146 13 0 0 5 4270.563581000001 1 0 13.272566793000001 0 0 0 25.08515 146 14 0 0 5 4270.563581000001 1 0 24.129526429674 0 0 0 45.6048 146 15 0 0 5 4270.563581000001 1 0 13.271239536320701 0 0 0 25.082644 146 16 0 0 5 4270.563581000001 1 0 13.271239536320701 0 0 0 25.082644 146 17 0 0 5 4270.563581000001 1 0 6.038413989025918 0 0 0 11.412602 146 19 0 1 5 4270.563581000001 1 0 4.5 0 0 0 8.505 146 20 0 1 5 4270.563581000001 1 0 14.625 0 0 0 27.64125 146 21 0 1 5 4270.563581000001 1 0 11.246625 0 0 0 21.25612 146 22 0 1 5 4270.563581000001 1 0 8.997300000000001 0 0 0 17.004896 146 23 0 1 5 4270.563581000001 1 0 15.745275000000001 0 0 0 29.75857 146 24 0 1 5 4270.563581000001 1 0 12.375786150000001 0 0 0 23.390236 146 25 0 1 5 4270.563581000001 1 0 11.249589610350002 0 0 0 21.261724 146 26 0 1 5 4270.563581000001 1 0 13.499507532420003 0 0 0 25.51407 147 10 0 0 5 7292.542534 1 0 14.5 0 0 0 34.655 147 11 0 0 5 7292.542534 1 0 10.033999999999999 0 0 0 23.98126 147 12 0 0 5 7292.542534 1 0 5.578904 0 0 0 13.33358 147 13 0 0 5 7292.542534 1 0 6.694684799999999 0 0 0 16.000298 147 14 0 0 5 7292.542534 1 0 22.3133844384 0 0 0 53.32899 147 15 0 0 5 7292.542534 1 0 11.1566922192 0 0 0 26.664494 147 16 0 0 5 7292.542534 1 0 13.38803066304 0 0 0 31.99739 147 17 0 0 5 7292.542534 1 0 6.69401533152 0 0 0 15.998696 147 19 0 1 5 7292.542534 1 0 14.5 0 0 0 34.655 147 20 0 1 5 7292.542534 1 0 7.25 0 0 0 17.3275 147 21 0 1 5 7292.542534 1 0 12.08575 0 0 0 28.884943 147 22 0 1 5 7292.542534 1 0 14.5029 0 0 0 34.66193 147 23 0 1 5 7292.542534 1 0 19.3323657 0 0 0 46.20435 147 24 0 1 5 7292.542534 1 0 6.0316980984000015 0 0 0 14.415758 147 25 0 1 5 7292.542534 1 0 15.682415055840005 0 0 0 37.480972 147 26 0 1 5 7292.542534 1 0 14.474869096540326 0 0 0 34.594936 296 21 0 1 4 1894.408927 0 0 16.4931435 0 0 0 13.029583 296 22 0 1 4 1894.408927 0 0 6.003504233999999 0 0 0 4.7427683 end format %tw time
Thanks in advance!
